Check out Piebald

We've released Piebald, the ultimate agentic AI developer experience.
Download it and try it out for free! https://piebald.ai/

Scroll down for Claude Code's system prompts. :point_down:

Claude Code System Prompts

[!tip] NEW (June 12, 2026): We've greatly expanded this list with many more of Claude Code's prompts—from 350 to 515 (+165)—our most complete coverage yet.

This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of Claude Code v2.1.290 (October 5th, 2026). It also contains a CHANGELOG.md for the system prompts across 306 versions since v2.0.14. From the team behind Piebald.

This repository is updated within minutes of each Claude Code release. See the changelog, and follow @PiebaldAI on X for a summary of the system prompt changes in each release.

[!note] ⭐ Star this repository to get notified about new Claude Code versions. For each new Claude Code version, we create a release on GitHub, which will notify all users who've starred the repository.

Why multiple "system prompts?"

Claude Code doesn't just have one single string for its system prompt.

Instead, there are:

• Large portions conditionally added depending on the environment and various configs.
• Descriptions for builtin tools like Write, Bash, and TodoWrite, and some are fairly large.
• Separate system prompts for builtin agents like Explore and Plan.
• Numerous AI-powered utility functions, such as conversation compaction, CLAUDE.md generation, session title generation, etc. featuring their own systems prompts.

The result—500+ strings that are constantly changing and moving within a very large minified JS file.

[!important] Want to modify a particular piece of the system prompt in your own Claude Code installation? Use tweakcc. It—

• lets you customize the individual pieces of the system prompt as markdown files, and then
• patches your npm-based or native (binary) Claude Code installation with them, and also
• provides diffing and conflict management for when both you and Anthropic have conflicting modifications to the same prompt file.

Extraction

This repository contains the system prompts extracted using a script from the latest npm version of Claude Code. As they're extracted directly from Claude Code's compiled source code, they're guaranteed to be exactly what Claude Code uses. If you use tweakcc to customize the system prompts, it works in a similar way—it patches the exact same strings in your local installation as are extracted into this repository.

Prompts

Note that some prompts contain interpolated bits such as builtin tool name references, lists of available sub agents, and various other context-specific variables, so the actual counts in a particular Claude Code session will differ slightly—likely not beyond ±20 tokens, however.

Agent Prompts

Sub-agents and utilities.

Sub-agents

• Agent Prompt: Explore (862 tks) - System prompt for the Explore subagent.
• Agent Prompt: Plan mode (enhanced) (1066 tks) - Enhanced prompt for the Plan subagent.

Creation Assistants

• Agent Prompt: CLAUDE.md creation (631 tks) - Instructs the /init command to analyze a codebase and create or improve a CLAUDE.md file.
• Agent Prompt: Status line setup (4815 tks) - System prompt for the statusline-setup agent that configures status line display.

Slash Commands

• Agent Prompt: /batch slash command (1524 tks) - Instructions for orchestrating a large, parallelizable change across a codebase.
• Agent Prompt: /code-review GitLab comment posting (312 tks) - Directs code review findings to a general GitLab merge request note when the comment flag is enabled.
• Agent Prompt: /code-review inline gap sweep phase (105 tks) - Adds a final same-context sweep for defects missed by an inline code review when subagents are unavailable.
• Agent Prompt: /code-review minimal mode (632 tks) - Minimal /code-review prompt that performs one careful diff pass and reports up to fifteen concrete correctness findings.
• Agent Prompt: /code-review part 1 base finder angles (145 tks) - Line-by-line diff scan instructions for the /code-review slash command's finder-angle phase.
• Agent Prompt: /code-review part 10 ReportFindings output format (448 tks) - Output-format instructions for /code-review runs that report verified findings once through the ReportFindings tool with capped, severity-ranked findings.
• Agent Prompt: /code-review part 2 low effort minimum findings mode (740 tks) - Low-effort /code-review prompt that reads the diff once, targets at least min(files_changed, 4) hunk-visible runtime correctness findings, and performs one extra pass when short.
• Agent Prompt: /code-review part 2 low effort mode (778 tks) - Low-effort /code-review prompt that reads the diff once and returns up to four hunk-visible runtime correctness findings.
• Agent Prompt: /code-review part 3 extra-high and maximum effort modes (553 tks) - Extra-high and maximum-effort /code-review prompt that runs five finder angles, one-vote verification, a gap sweep, and capped JSON findings.
• Agent Prompt: /code-review part 4 three-state verification phase (98 tks) - Verification phase for /code-review that asks one agent verifier to classify each candidate as confirmed, plausible, or refuted.
• Agent Prompt: /code-review part 5 recall-biased verification phase (175 tks) - Recall-biased /code-review verification phase that treats realistic uncertain findings as plausible unless code refutes them.
• Agent Prompt: /code-review part 6 medium effort mode (466 tks) - Medium-effort /code-review prompt that favors precision with three finder angles, one-vote verification, and up to eight JSON findings.
• Agent Prompt: /code-review part 7 high effort mode (511 tks) - High-effort /code-review prompt that favors recall with three finder angles, recall-biased verification, and up to ten JSON findings.
• Agent Prompt: /code-review part 8 GitHub comment posting (152 tks) - Optional /code-review instructions for posting findings as GitHub inline PR comments when --comment is passed.
• Agent Prompt: /code-review part 9 fix application (250 tks) - Optional /code-review instructions for applying findings to the working tree when --fix is passed.
• Agent Prompt: /code-review unavailable-agent inline mode (403 tks) - Builds a single-pass inline code-review prompt that gathers a diff, evaluates configured angles, deduplicates findings, optionally sweeps gaps, and reports capped results when the Agent tool is unavailable.
• Agent Prompt: /rename auto-generate session name (80 tks) - Prompt used by /rename (no args) to auto-generate a kebab-case session name from conversation context.
• Agent Prompt: /schedule slash command (4469 tks) - Guides the user through scheduling, updating, listing, or running remote Claude Code agents on cron triggers via the Anthropic cloud API.
• Agent Prompt: /security-review slash command (2521 tks) - Comprehensive security review prompt for analyzing code changes with focus on exploitable vulnerabilities.
• Agent Prompt: /simplify slash command (362 tks) - Instructions for the /simplify slash command that reviews changed code for reuse, simplification, efficiency, and altitude cleanups, then applies the fixes.
• Agent Prompt: /simplify unavailable-agent inline mode (621 tks) - Runs the /simplify cleanup workflow inline across reuse, simplification, efficiency, and altitude angles when the Agent tool is unavailable.
• Agent Prompt: Artifact type creation slash command (quickstart flow) (277 tks) - Directs an Artifact creation slash command to quickstart the requested published type, create the new Artifact, and follow the returned type instructions.
• Agent Prompt: Artifact type creation slash command (347 tks) - Directs an Artifact creation slash command to discover the named published Artifact type, create from its type URL, and follow the returned type instructions.

Utilities

• Agent Prompt: Agent Hook (282 tks) - Evaluates agent hook conditions against the codebase and, when available, the conversation transcript, then returns a structured pass/fail result.
• Agent Prompt: Artifact comment completion reply and resolution (256 tks) - Directs an Artifact comment worker to post one completion reply when needed and resolve an open thread after acting unless the conversation remains active.
• Agent Prompt: Artifact comment thread analyst (750 tks) - Instructs a read-only agent to analyze one Artifact comment thread and return a constrained analysis brief for a separate composer.
• Agent Prompt: Artifact comment thread background directive (300 tks) - Directs a forked background agent to handle one Artifact comment thread on its own, leaving the main session's pending work alone and treating thread and artifact content as material rather than instructions.
• Agent Prompt: Artifact editor thread follow-up (328 tks) - Delivers a tagged Artifact thread message to the active editor worker, requiring page-scoped edits and republishing for relevant requests and no changes for unrelated ones.
• Agent Prompt: Auto mode rule reviewer (292 tks) - Reviews and critiques user-defined auto mode classifier rules for clarity, completeness, conflicts, and actionability.
• Agent Prompt: Away summary generation (73 tks) - Prompts a no-tools away-summary generation run to recap the goal, current task, and next action when the user returns.
• Agent Prompt: Background agent state classifier (6237 tks) - Classifies the tail of a background agent transcript as working, blocked, done, or failed and returns concise state JSON.
• Agent Prompt: Background job agent instructions (581 tks) - Instructs the built-in background job agent to narrate progress, restate tool results, and emit explicit result, needs input, or failed status signals.
• Agent Prompt: Claude Code guide (408 tks) - Describes when to use the Claude Code guide agent for Claude Code, Agent SDK, Claude API, and Claude Tag questions.
• Agent Prompt: Claude Test author (346 tks) - Subagent definition for the Claude Test plugin's background spec author, which reads the app's source and writes spec drafts into a run folder's proposed/ directory for the person to approve.
• Agent Prompt: Claude Test explorer (777 tks) - Subagent definition for the Claude Test plugin's read-only explorer, which maps a web application's source for a browser test suite using only Read, Grep and Glob and must avoid credential and out-of-project paths.
• Agent Prompt: Claude guide agent (2975 tks) - Instructs the Claude guide agent to answer documentation-based questions about Claude Code, the Claude Agent SDK, the Claude API, Claude Tag, plugin evaluation, and skill diagnostics.
• Agent Prompt: Coding session title generator (898 tks) - Generates a short noun-phrase title for a coding session from untrusted session content.
• Agent Prompt: Conversation summarization (capped variant) (166 tks) - Asks for a summary of the entire conversation in 2000 words or fewer inside summary tags, preserving facts, file paths, function names, error messages and open threads.
• Agent Prompt: Conversation summarization (lean variant) (486 tks) - Tells a compaction run that its reply replaces the conversation, lists what the next context window will carry, and requires the summary to preserve the user's goals, decisions, ruled-out approaches, exact limits, current status and next step.
• Agent Prompt: Conversation summarization (short variant) (496 tks) - Asks for a no-tools summary block that preserves problems, options, decisions, constraints, current status, open items and exact details, weighting the user's words over Claude's own reasoning.
• Agent Prompt: Conversation summarization with additional instructions (1380 tks) - Extended summarization prompt with support for custom additional instructions.
• Agent Prompt: Conversation summarization (292 tks) - System prompt for creating detailed conversation summaries.
• Agent Prompt: Coordinator worker instructions (830 tks) - Instructions for worker agents executing coordinator-assigned tasks, covering scope control, concurrent branch changes, resumption, failure handling, and coordinator-facing output.
• Agent Prompt: Determine which memory files to attach (388 tks) - Agent for determining which memory files to attach for the main agent.
• Agent Prompt: Dream memory consolidation (1361 tks) - Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
• Agent Prompt: General purpose agent (63 tks) - Defines a general-purpose agent for researching complex questions, searching code, and executing multi-step tasks.
• Agent Prompt: General purpose (446 tks) - System prompt for the general-purpose subagent that searches, analyzes, and edits code across a codebase while reporting findings concisely to the caller.
• Agent Prompt: General task agent (99 tks) - Instructs a Claude Code task agent to complete the user's request fully and report the essential outcome.
• Agent Prompt: Hook condition evaluator (stop) (319 tks) - System prompt for evaluating hook conditions, specifically stop conditions, in Claude Code.
• Agent Prompt: Hook condition evaluator (88 tks) - Instructs an agent to judge whether a user-provided hook condition is met.
• Agent Prompt: Inherited context for worktree sub-agent (121 tks) - Briefs a sub-agent that it has inherited a parent session's context and is now working in its own isolated git worktree.
• Agent Prompt: Onboarding guide draft share link workflow (423 tks) - Adds instructions for sharing the draft ONBOARDING.md before review, then updating the same ShareOnboardingGuide link after the user answers the review questions.
• Agent Prompt: Onboarding guide generator (1135 tks) - Co-authors a team onboarding guide (ONBOARDING.md) for new Claude Code users by analyzing the creator's usage data, classifying session types, and iterating on the draft collaboratively.
• Agent Prompt: PR follow-up cron (PR Steward label check) (278 tks) - PR follow-up cron clause telling the agent not to fix or push a PR carrying PR Steward labels, to tell the user once, and to offer leave-it, one-change, or take-over choices.
• Agent Prompt: PR follow-up cron (332 tks) - Cron prompt for checking a pull request created in the session and fixing failures, comments, or conflicts.
• Agent Prompt: Plugin eval pilot trust requirement (205 tks) - Requires explicit user trust for a plugin directory before piloting its eval cases with --trust-plugin and otherwise limits work to writing case files.
• Agent Prompt: Project thread status card classifier (4299 tks) - Classifies a Project thread as needing a reply, needing approval, done, failed, or working and emits concise owner-facing status-card JSON.
• Agent Prompt: Prompt Suggestion Generator v2 (344 tks) - V2 instructions for generating prompt suggestions for Claude Code.
• Agent Prompt: Pull request creation (1151 tks) - Prompt for creating a single GitHub pull request from existing commits with branch, template, attribution, shell-formatting, and git-safety guidance.
• Agent Prompt: Quick PR creation (1741 tks) - Streamlined prompt for creating a commit and pull request with pre-populated context.
• Agent Prompt: Quick git commit (1312 tks) - Streamlined prompt for creating a single git commit with pre-populated context.
• Agent Prompt: Read-only search agent (93 tks) - Defines a read-only search agent for broad fan-out code searches that returns conclusions instead of file dumps.
• Agent Prompt: Recent Message Summarization (868 tks) - Agent prompt used for summarizing recent messages.
• Agent Prompt: Remote machine auto mode rules (228 tks) - Adds host-declared deny, allow, and environment rules to the security monitor prompt for commands that will run on another machine.
• Agent Prompt: Schedule action selection (114 tks) - Instructs the cloud scheduling agent to ask the user which schedule action to perform first.
• Agent Prompt: Schedule local MCP server limitation (1145 tks) - Explains that local Claude Code MCP servers cannot be attached to cloud routines and tailors Claude.ai connector guidance to why the connector list was unavailable.
• Agent Prompt: Security monitor Claude Tag connector writes (542 tks) - Allows the autonomous-action security monitor to accept delegated writes through exact Claude Tag connector tool prefixes while preserving all other safety boundaries.
• Agent Prompt: Security monitor attached machine call results (269 tks) - Explains how the auto mode security monitor reads _host call lines and result_from lines for calls served by a user-attached machine, and judges sending that machine's output to external destinations as cross-machine data exfiltration.
• Agent Prompt: Security monitor for autonomous agent actions (first part) (13991 tks) - Instructs Claude to act as a security monitor that evaluates autonomous coding agent actions against block/allow rules to prevent prompt injection, scope creep, and accidental damage.
• Agent Prompt: Security monitor forwarded user turns (761 tks) - Defines how the auto mode classifier authenticates harness-forwarded user turns and weighs direct, relayed, and unattributed messages as action-specific intent, consent, or restrictions.
• Agent Prompt: Security monitor host-context line guidance (614 tks) - Explains how the autonomous-action security monitor should interpret live and restored host-context lines when evaluating user intent and consent.
• Agent Prompt: Session title and branch generation (626 tks) - Agent for generating succinct session titles and git branch names.
• Agent Prompt: Session transcript chunk summary (89 tks) - Instructs an agent to summarize a chunk of a Claude Code session transcript concisely.
• Agent Prompt: Summarization no-tools guard (164 tks) - Shared prefix for compaction summarization agents that forbids tool use and requires a plain-text reply shaped as either an analysis block followed by a summary block or a summary block alone.
• Agent Prompt: Web fetch agent usage guidance (504 tks) - Explains when and how to delegate URL reading to the built-in web-fetch agent, including binary-file trust boundaries and follow-up messaging.
• Agent Prompt: Web reading specialist (905 tks) - System prompt for the built-in web-fetch agent that reads untrusted URL content with WebFetch and returns a focused, source-grounded report to its caller.
• Agent Prompt: Worker fork (412 tks) - Directive injected into a forked child agent, telling it to treat the inherited transcript as reference, execute one directive directly, and report once.
• Agent Prompt: Workflow script plain text return note (76 tks) - Appended note telling a workflow script agent that its final text response is parsed as the script return value.
• Agent Prompt: Workflow script structured return note (120 tks) - Appended note telling a workflow script agent to return its final answer by calling the structured output tool exactly once.
• Agent Prompt: Workflow subagent plain text output (154 tks) - Instructs an internal workflow subagent to return its final text verbatim as the calling workflow script's parsed result.
• Agent Prompt: Workflow subagent structured output (190 tks) - Instructs an internal workflow subagent to return its final answer by calling the StructuredOutput tool exactly once with schema-valid input.

Data

The content of various template files embedded in Claude Code.

• Data: /auto-mode-setup usage (406 tks) - Defines /auto-mode-setup proposal and reviewed-apply command syntax, request ID ordering, save-target validation, and integrity requirements.
• Data: Artifact MCP connector guidance (351 tks) - Explains how Artifact MCP manifests declare claude.ai, built-in, and host connectors and how to discover exact server and upstream tool names.
• Data: Artifact capability verification pass (271 tks) - Requires one functional pass over a page's session-declared runtime capabilities before handing over its link, assembling the preview, database read and endpoint checks to run and what to report to the user.
• Data: Artifact connector call observation requirement (305 tks) - Explains how to obtain connector argument names from the loaded tool schema, learn result shapes from safe real calls, and disclose shapes that cannot be verified before publishing.
• Data: Artifact connector server naming guidance (241 tks) - Explains how connector tool prefixes map to manifest server identifiers and why in-page calls must use the resolved connector display name.
• Data: Artifact decision component HTML skeleton (1117 tks) - Provides the canonical HTML and JSON-island skeleton for embedding one reusable Artifact decision block.
• Data: Artifact host MCP server guidance (420 tks) - Explains how locally configured MCP servers may be declared as Artifact host servers and distinguishes them from Claude.ai connectors and built-in servers.
• Data: Artifact publish merged-over newer version file changes notice (481 tks) - Tool-result notice appended when an artifact publish was merged over a newer live version, listing files changed, added, or removed there since the base version, that stale copies must be read again, and how many further files are not listed.
• Data: Artifact runtime capability declarations (496 tks) - Defines Artifact runtime capability declaration, carry-forward, clearing, replacement, and contract pinning semantics.
• Data: Auto-compact inputs changed event schema (221 tks) - Schema description for worker-resolved auto-compaction state events used by thin clients to display the effective compaction countdown.
• Data: Background tasks changed event schema (342 tks) - Schema description for the background_tasks_changed system event and its replace-set semantics.
• Data: Built-in gh stand-in api command help (1149 tks) - Usage text for Claude Code's built-in gh stand-in, which supports only gh api REST requests to GitHub hosts through the session's GitHub proxy, listing its flags and how {owner}, {repo} and {branch} placeholders are filled in.
• Data: Chrome browser hints control request (207 tks) - Documents the set_chrome_browser_hints control request that tells a session which connected Claude in Chrome browser to prefer, and that the hints are session-only and never override the live relay roster.
• Data: Claude API reference — PHP (2877 tks) - PHP SDK reference.
• Data: Claude API reference — Ruby (2120 tks) - Ruby SDK reference including installation, client initialization, basic requests, streaming, and beta tool runner.
• Data: Claude Code agent proxy troubleshooting guide (2214 tks) - Troubleshooting guide for Claude Code's policy-enforcing HTTPS agent proxy, covering TLS trust setup, status checks, git, docker, and unsupported traffic.
• Data: Claude Code gateway customer-routed inference protocol (2945 tks) - Conditional extension to the Claude Code gateway protocol defining customer-routed inference authentication, forwarding, response hygiene, error recovery, policy blocking, discovery, and endpoint requirements.
• Data: Claude Code gateway protocol (7396 tks) - Markdown reference documenting the Claude Code gateway wire contract, including OAuth 2.0 device flow, RFC 8414 discovery, Messages API inference, managed settings, model discovery, OTLP telemetry, error envelopes, TLS certificate pinning, and proxying to Bedrock, Vertex, and Foundry.
• Data: Claude Code live documentation sources (2477 tks) - WebFetch URLs for fetching current Claude Code documentation from official sources.
• Data: Claude Code recent changes reference (1854 tks) - Reference mapping of recently removed or renamed Claude Code commands, flags, and terms to their current replacements.
• Data: Claude Platform on AWS reference (1805 tks) - Reference documentation for using the Claude Developer Platform through AWS infrastructure, including AnthropicAWS clients, required region and workspace configuration, SigV4 authentication, and short-term API keys.
• Data: Claude Tag (Claude in Slack) reference (1999 tks) - Offline reference for Claude Tag, Claude Code's org-managed Slack surface, covering what it is, availability, setup, configuration, and how it differs from the earlier Claude in Slack app.
• Data: Claude Test spec file format (1745 tks) - Reference for the Markdown spec files in .claude-test/specs/ — front matter keys, the three required parts, data-creating specs, and what makes a spec goal-oriented and checkable from a single end screenshot.
• Data: Claude gateway landing page (392 tks) - HTML status page served at a Claude Code gateway root, showing the gateway logo, the running gateway URL, the identity-provider host, an OAuth discovery link, and the gateway version.
• Data: Cloud session unverified remote branch push notice (255 tks) - Notice shown when no remote of the checkout could be read, so it could not be checked whether the current branch or detached HEAD commit exists on the remote host, telling the user to push their work to a branch and start a new cloud session from it.
• Data: Code change published event schema (349 tks) - Schema description for the code_change_published system event, including provenance, idempotency, trust boundaries, and best-effort delivery.
• Data: Command plugin source command field (160 tks) - Describes the command field for command-based plugin sources, including its one-line directory output contract, cache-copy lifecycle, platform shell, and re-resolution behavior.
• Data: Cowork plugin MCP discovery and connection (1746 tks) - Reference guidance for finding MCP connectors during plugin customization, using search and suggestion tools, mapping categories to keywords, and writing .mcp.json entries.
• Data: Cowork plugin examples (3158 tks) - Reference examples of minimal, medium, and complex Cowork plugin structures with plugin metadata, skills, agents, hooks, MCP config, README, and connectors.
• Data: Cross-session inbound setting (175 tks) - Describes crossSessionInbound delivery, hold, refusal, and permission-mode parity behavior for peer messages.
• Data: Data visualization anti-patterns (2339 tks) - Reference list of chart and dashboard anti-patterns to check against before shipping a data visualization.
• Data: Data visualization choosing a form (1177 tks) - Reference guidance for choosing the appropriate chart, stat tile, or non-chart form based on the data's job.
• Data: Data visualization components (836 tks) - Reference specification for the HTML/SVG pieces, layers, and system parameters that make up a data visualization.
• Data: Data visualization interaction (1318 tks) - Reference guidance for chart hover layers, tooltips, filters, linked highlighting, and interaction behavior.
• Data: Data visualization marks and anatomy (2164 tks) - Reference specifications for chart marks, spacing, labels, axes, legends, and stat-tile anatomy.
• Data: Dialog expiry setting (204 tks) - Describes dialogExpiry deadlines for remote permission dialogs and held cross-session messages, including defaults and overrides.
• Data: DirectoryAdded hook description (216 tks) - Describes when the DirectoryAdded hook fires, its input fields, and how failures and output are handled for add-dir and register_repo_root sources.
• Data: Files API reference — C# (378 tks) - C# Files API reference including beta file upload and use with beta message types.
• Data: Files API reference — Go (413 tks) - Go Files API reference including file upload, listing, deletion, and usage in messages.
• Data: Files API reference — Java (492 tks) - Java Files API reference including file upload, beta message references, listing, deletion, download, and metadata retrieval.
• Data: Files API reference — PHP (186 tks) - PHP Files API reference with a beta-era upload example and a warning that current SDKs use the stable Files API shape.
• Data: Files API reference — Python (1719 tks) - Python Files API reference including file upload, listing, deletion, and usage in messages.
• Data: Files API reference — TypeScript (961 tks) - TypeScript Files API reference including file upload, listing, deletion, and usage in messages.
• Data: Gateway device code entry page (261 tks) - HTML verification page served at a gateway device endpoint, prompting the user to enter the short device code shown by Claude Code so they can sign in through their company identity provider.
• Data: Gateway ignored X-Forwarded-For warning (254 tks) - Gateway startup warning that an X-Forwarded-For header was ignored because the requesting address is not covered by listen.trusted_proxies, and what to configure when a load balancer or ingress fronts the gateway.
• Data: Get task output control request (201 tks) - Schema description for the get_task_output control request that reads the last 8 KiB of a background shell or Monitor task's output without a model turn, and when it is refused.
• Data: GitHub Actions workflow for @claude mentions (525 tks) - GitHub Actions workflow template for triggering Claude Code via @claude mentions.
• Data: GitHub App installation PR description (409 tks) - Template for PR description when installing Claude Code GitHub App integration.
• Data: Hook classifier context field (654 tks) - Schema description for the classifierContext hook response field, including trust semantics, size and timing limits, transcript visibility, and rewrite-integrity requirements.
• Data: Hook mcp_server field (312 tks) - Describes the mcp_server object attached to tool-related hook payloads — the server's config key and the source its definition came from — and why trust must key on source rather than on the server name or tool-name prefix.
• Data: Interrupt cancel queued parameter (646 tks) - Schema description for the optional interrupt cancel_queued request parameter and its queued-command cancellation semantics.
• Data: Interrupt receipt cancelled field (291 tks) - Schema description for the cancelled UUID list returned when an interrupt request cancels queued commands.
• Data: Interrupt receipt still queued field (1116 tks) - Schema description for the still_queued UUID list returned by interrupt control responses.
• Data: Interrupt send_now message_uuid parameter (246 tks) - Schema description for the interrupt message_uuid parameter read only beside send_now, which restricts the request to one exact-match waiting user message and answers nothing_waiting when that message is not waiting.
• Data: Interrupt send_now parameter (596 tks) - Schema description for the optional interrupt send_now request parameter, which asks that waiting user messages reach the model now without acting as a Stop, and how the CLI chooses between moving the turn's waits to the background and aborting it.
• Data: Knowledge MCP search strategies (447 tks) - Reference query patterns for using knowledge MCPs to discover organization-specific tool names, project identifiers, team names, and workflow details during plugin customization.
• Data: MCP HTTP client capability validation rationale (189 tks) - Explains where required client capabilities are validated in the modern MCP HTTP request ladder and how the pre-dispatch gate affects observable precedence.
• Data: MCP HTTP parameter header validation rationale (247 tks) - Explains validation of Mcp-Param headers against tool declarations and request arguments, including error shape and pre-dispatch precedence.
• Data: MCP HTTP standard header validation rationale (326 tks) - Explains the modern MCP HTTP validation ladder's Mcp-Method and Mcp-Name header checks and their observed pre-dispatch precedence.
• Data: MCP read resource control request (397 tks) - Documents the mcp_read_resource control request that reads one MCP Apps (SEP-1865) ui:// resource from a connected MCP server, its sandboxed-render requirement, SDK-server rejection, refused lanes and error cases.
• Data: MCP server status error_code field (200 tks) - Schema description for the MCP server status error_code field, naming the host-fixable failure causes — a rejected claude.ai connector login, a rejected first-party Anthropic credential, and a project-scoped server awaiting approval — and noting that it is absent for every other failure and that new values are additive.
• Data: Managed Agents outcomes (3058 tks) - Reference documentation for Managed Agents outcomes, including user.define_outcome events, rubrics, outcome evaluation events, deliverables, and interaction rules.
• Data: Managed Agents quickstart — Contract tracker (689 tks) - Bundled Managed Agents quickstart template for a contract tracker agent that reads a Box contract, extracts clauses and dates, and creates Asana deadline and obligation tasks, with its agent.md definition and system prompt.
• Data: Managed Agents quickstart — Data analyst (579 tks) - Bundled Managed Agents quickstart template for a data analyst agent that loads, cleans and charts datasets and can query Amplitude, with its agent.md definition and system prompt.
• Data: Managed Agents quickstart — Deep researcher (798 tks) - Bundled Managed Agents quickstart template for a deep research agent that decomposes a question, cites primary sources and ends with a confidence-and-gaps section, with its agent.md definition and a user.define_outcome rubric.
• Data: Managed Agents quickstart — Field monitor (813 tks) - Bundled Managed Agents quickstart template for a field monitor agent that scans technical blogs and writes a weekly Notion digest, with its agent.md definition and a Monday-morning cron deployment.
• Data: Managed Agents quickstart — Incident commander (684 tks) - Bundled Managed Agents quickstart template for an incident commander agent that triages a Sentry alert, opens a Linear ticket and runs the Slack war room, with its agent.md definition and system prompt.
• Data: Managed Agents quickstart — Sprint retro facilitator (870 tks) - Bundled Managed Agents quickstart template for a sprint retro facilitator agent that pulls a closed Linear sprint, reads Slack sentiment and writes a retro doc, with its agent.md definition and a twice-monthly cron deployment.
• Data: Managed Agents quickstart — Structured extractor (545 tks) - Bundled Managed Agents quickstart template for a structured extractor agent that parses unstructured text into JSON that validates against a target schema, with its agent.md definition and system prompt.
• Data: Managed Agents quickstart — Support agent (532 tks) - Bundled Managed Agents quickstart template for a support agent that answers from Notion docs with quoted sources and escalates low-confidence questions to Slack, with its agent.md definition and system prompt.
• Data: Managed Agents quickstart — Support-to-eng escalator (709 tks) - Bundled Managed Agents quickstart template for an escalator agent that reads an Intercom conversation, reproduces the bug and files a linked Jira issue with a Slack note, with its agent.md definition and system prompt.
• Data: Managed settings helper onFailure field (593 tks) - Schema description for the managed settings helper onFailure field, including source-dependent defaults, startup refusal behavior, static fallbacks, and background refresh handling.
• Data: Managed settings helper retries field (311 tks) - Schema description for the managed settings helper retries field, including retryable failures, limits, per-attempt timeouts, backoff, and terminal failure handling.
• Data: Message Batches API reference — C# (188 tks) - C# Batches API reference including batch creation, status polling, and result retrieval.
• Data: Message Batches API reference — PHP (196 tks) - PHP Batches API reference including batch creation, status polling, and result retrieval.
• Data: Message Batches API reference — Python (2038 tks) - Python Batches API reference including batch creation, status polling, and result retrieval at 50% cost.
• Data: Message Batches API — TypeScript (1022 tks) - TypeScript usage guide for Claude's asynchronous Message Batches endpoint.
• Data: Peer sender display name field (199 tks) - Schema description for the normalized display name on cross-session peer message senders.
• Data: Plugin manifest types field (214 tks) - Schema description for the plugin manifest types field naming a self-contained .d.ts type contract for the noun the plugin's hooks module adds in engine.create, which dependent mods receive under .claude-plugin/types and claude plugin validate checks.
• Data: Prompt suggestions paused control request (229 tks) - Documents the set_prompt_suggestions_paused control request that pauses or resumes a session's prompt suggestions at runtime and the process-local, non-persisted scope of that state.
• Data: Query result pending command count (167 tks) - Describes the query result field that counts queued user sends still awaiting turns and clarifies when it is absent or zero.
• Data: Rate limit grace signal (306 tks) - Describes the usage-limit grace-window signal tracked from the latest served response, including when it sets, clears, and how it interacts with overage status at hard exhaustion.
• Data: Rate limit unified windows (325 tks) - Describes per-window subscription rate-limit utilization and reset data derived from unified rate-limit response headers.
• Data: Remote tools reannounce control request (220 tks) - Documents the remote_tools_reannounce control request a replacement worker sends so the attached client re-announces a machine missing from its tool roster, including worker-epoch, once-per-epoch, ten-second and deadline rules.
• Data: Review upload excluded changes error (327 tks) - Error shown when a review upload has no new commits or uploadable changes because every uncommitted file was excluded from the git bundle.
• Data: Rewind files skippedLinks field (223 tks) - Describes the rewindFiles skippedLinks count, including link-safety refusal semantics and dry-run behavior.
• Data: SDK API error kind field (1370 tks) - Documents the typed api_error kinds carried on SDK assistant messages that wrap an API error, and what each kind means for replaying, rewinding, or remedying the request.
• Data: SDK footer indicator schema (249 tks) - Schema description for the SDK footer indicator, its environment-variable and cached-bootstrap sources, and its delivery on system/init and initialize responses so host UIs can render the terminal status pill.
• Data: SDK frame_intake_phases_ms field (444 tks) - Schema description for the SDK turn-timing frame_intake_phases_ms field, breaking the wait between frame receipt and enqueue into named steps and their sum and presence invariants.
• Data: SDK frame_received_wall_ms field (193 tks) - Schema description for the SDK turn-timing frame_received_wall_ms field recording when the triggering send's frame arrived on a session reading input from the session server's SSE stream, how it pairs with the enqueue and turn-start timestamps to split transit from queue wait, and when it is absent.
• Data: SDK initialize response sdk_mcp_manifests_parked field (482 tks) - Schema description for the SDK initialize response sdk_mcp_manifests_parked field, reporting per server whether a manifest entry was parked, already connected, mismatched on protocol version, malformed, or not honoured, and when the field is absent.
• Data: SDK set max thinking tokens request schema (477 tks) - Schema description for the SDK set_max_thinking_tokens control request, covering null reset versus omitted budget, session-scoped thinking_display overrides, and when the highlights display mode is accepted, downgraded to omitted, or refused.
• Data: SDK set model system prompt field (243 tks) - Schema description for the internal set_model system_prompt field, including next-turn application with unchanged tool definitions, non-empty updates, feature overrides, and compatibility behavior.
• Data: SDK system init plugin_errors field (315 tks) - Schema description for the plugin_errors array on the SDK system/init message, covering failed versus partially loaded plugins, name@marketplace and positional inline/synced tags, open-set error types, omission when clean, and Remote Control workers always omitting it.
• Data: SDK thinking_duration_ms field (184 tks) - Schema description for the display-only thinking_duration_ms wrapper field giving how long a streamed thinking block took, excluding the wait for the first token, and when it is absent or not replayed to the model.
• Data: Sandbox TLS termination setting (199 tks) - Describes the experimental sandbox.network.tlsTerminate setting, certificate behavior, Windows trust requirements, source precedence, and initialization validation.
• Data: Sandbox credential environment no-match setting (188 tks) - Describes sandbox credential environment-variable onExtractNoMatch behavior, including warn, deny, error, and decode-path constraints.
• Data: Sandbox credential file mask claims setting (179 tks) - Describes sandbox credential file maskClaims behavior for selectively masking decoded JWT payload claims while preserving other claims.
• Data: Sandbox credential mask empty injectHosts warning (174 tks) - Warns that sandbox credential masks with empty injectHosts expose only sentinel values and explains how to resolve adapter, managed-settings, and local configuration causes.
• Data: Sandbox deniedResolvedAddresses setting (209 tks) - Schema description for the sandbox deniedResolvedAddresses setting listing IP addresses or CIDR ranges an allowed hostname must not resolve to, its interaction with allowedDomains IP literals, and its exemption for parentProxy and mitmProxy routes.
• Data: Sandbox filesystem disabled setting (227 tks) - Describes sandbox.filesystem.disabled behavior, platform limits, read-protection effects, and configuration precedence.
• Data: Sandbox network domain spelling warning (278 tks) - Formats the sandbox diagnostic for unreliable network domain spellings and explains conservative enforcement until entries are corrected.
• Data: Sandbox root without CAP_SETFCAP error (140 tks) - Linux sandbox dependency error explaining that running as uid 0 without CAP_SETFCAP makes every sandboxed command fail while writing a uid map on kernels 5.12+ and backports, and telling the user to grant CAP_SETFCAP or run as non-root.
• Data: Self-hosted runner Anthropic git proxy credential warning (338 tks) - Runner warning that sources on hosts not routed through Anthropic-managed git clone with this machine's credentials, which --use-anthropic-git-proxy wipes from HOME-level git config, so credentials must live in /etc/gitconfig, GIT_ASKPASS, or an SSH key.
• Data: Self-hosted runner GIT_ASKPASS governed hosts warning (311 tks) - Runner warning that a GIT_ASKPASS program answers for every host, so later git config could send this machine's credential for governed hosts through Anthropic's relay, and directs scoping or unsetting it along with core.askPass and SSH_ASKPASS.
• Data: Self-hosted runner GIT_SSL_CAINFO trust bundle warning (254 tks) - Runner warning that GIT_SSL_CAINFO prevented building the combined certificate file for Anthropic-managed git, giving the failure cause and first remedy and directing the company CA into a per-server http sslCAInfo entry.
• Data: Self-hosted runner GIT_SSL_NO_VERIFY lifecycle hook exception (330 tks) - Runner warning addendum explaining that checkout and post-session hooks of sessions with a repository on Anthropic-managed git get http.sslVerify=false with certificate checks re-enabled for the mount, while other sessions' hooks inherit the switch.
• Data: Self-hosted runner GIT_SSL_NO_VERIFY session relocation note (325 tks) - Runner warning addendum explaining that inside a session GIT_SSL_NO_VERIFY becomes http.sslVerify=false that no longer covers the git mount or governed hosts, that per-server sslVerify takes precedence, and to name a company CA on certificate failures.
• Data: Self-hosted runner client certificate relay warning (539 tks) - Runner warning that TLS client certificate variables set on the runner would be offered to the session relay rather than governed hosts, with remedies of asking for direct listing, unsetting the variables, or scoping sslCert and sslKey per URL.
• Data: Self-hosted runner decode-token command help (869 tks) - Documents self-hosted runner token decoding, redaction, validation, input, and output command-line options.
• Data: Self-hosted runner deferred shutdown timing notice (320 tks) - Explains deferred shutdown release and drain timing, supervisor timeout sizing, forced-kill consequences, and second-signal behavior for self-hosted runners.
• Data: Self-hosted runner git-lfs hook warning (342 tks) - Runner warning that git-lfs's pre-push hook never runs inside lifecycle hooks, so a post-session git push sends LFS pointers without their objects, and how to push the objects or point core.hooksPath instead.
• Data: Self-hosted runner orchestrator command help (1390 tks) - Documents self-hosted runner orchestrator connection, hook, SCM connector, runtime, health, and debug command-line options.
• Data: Self-hosted runner session metrics help (622 tks) - Defines Prometheus HELP text for self-hosted runner session lifecycle counters.
• Data: Streaming reference — C# (376 tks) - C# streaming reference including streaming events and the RawMessageStreamEvent TryPick methods.
• Data: Streaming reference — Go (452 tks) - Go streaming reference including event handling, error checks, and final-message accumulation.
• Data: Streaming reference — Java (287 tks) - Java streaming reference including streamed content-block delta handling and text extraction.
• Data: Streaming reference — PHP (315 tks) - PHP streaming reference including streaming events and handling content block deltas (requires SDK v0.5.0+).
• Data: Streaming reference — Ruby (116 tks) - Ruby streaming reference including basic streamed text handling.
• Data: Structured tool output field schema (234 tks) - Schema description for the user-message tool_use_result field, including per-tool output shapes, the completed Agent or Task output contract, and the detachedToolCall placeholder for calls that stepped aside for a user message.
• Data: Structured usage rate-limit rows field (177 tks) - Schema description for structured usage rate-limit rows, including server-defined meter ordering, null and empty semantics, and the synthesized header-fallback row.
• Data: Submit feedback control request (231 tks) - Documents the internal submit_feedback control request that sends a /feedback report with the session transcript and sanitized error log, returns unavailable_reason when feedback is disabled or unsendable, and honors save_locally by writing a redacted local bundle instead.
• Data: Telemetry variables ignored notice (268 tks) - Settings-status warning listing OTEL/telemetry environment variables a settings file sets that Claude Code ignores because such files can only turn telemetry off, with guidance on where to set them intentionally.
• Data: Thin-client diff dialog schema (198 tks) - Internal data description for workspace git diff payloads used by the thin-client diff dialog.
• Data: Token counting reference (665 tks) - Reference documentation for counting Claude model tokens with the Messages count_tokens endpoint and Anthropic SDK or CLI examples, including warnings against OpenAI tokenizers.
• Data: Tool use display metadata field (172 tks) - Documents the tool_use_meta wire field carrying per-block display metadata for a message's tool_use blocks; it is wrapper-level UI metadata and is not replayed to the model.
• Data: Tool use reference — C# (2401 tks) - C# tool use reference including defining tools and reconstructing response content for the follow-up assistant message.
• Data: Tool use reference — PHP (3211 tks) - PHP tool use reference including the beta tool runner and the manual agentic loop with camelCase keys.
• Data: Tool use reference — Ruby (444 tks) - Ruby tool use reference including the beta tool runner and manual agentic-loop guidance.
• Data: Turn handoff available event schema (269 tks) - Schema description for the turn_handoff_available system event a cloud worker emits right after registering, carrying the tools and turn-handoff options its registration declared, and the rule that readers keep only the entry from the newest worker life.
• Data: Turn handoff file_names field (283 tks) - Schema description for the turn_handoff file_names member listing user-attached files and their client-facing names that a capable worker copies into the session's home directory before running the handed-over calls, and when a malformed member is ignored.
• Data: Turn handoff memory_context field (232 tks) - Schema description for the turn_handoff memory_context member carrying the claude.ai memory snapshot the client showed its model, how the worker writes it as a cowork_memory_context attachment line ahead of the handed-over messages, and when a malformed or uuid-colliding member is ignored.
• Data: Upload device hook template request (200 tks) - Describes the cloud device request that uploads a vetted hook template to a worker before device hooks are registered.
• Data: VCS state changed branch field (172 tks) - Describes the optional best-effort branch hint on vcs_state_changed events for commits and pushes, including multi-branch and uncertain-attribution behavior.
• Data: VCS state changed event schema (392 tks) - Schema description for the vcs_state_changed system event as a best-effort repository cache-invalidation signal.
• Data: Windows transcript read EBADF notice (180 tks) - Explains a Windows-only EBADF error reading the session transcript file likely caused by security or endpoint-management software intercepting file reads, and suggests excluding the .claude folder or allow-listing Claude Code before resuming.
• Data: Working tree upload refusal for duplicated withheld file (211 tks) - Error refusing a working-tree upload because an index entry appeared holding byte-for-byte the content of a file that must stay on this machine, indicating something outside the upload wrote into its index copy.
• Data: Working tree upload refusal for git dubious ownership (224 tks) - Error refusing a working-tree upload because git reports dubious ownership of the checkout or its .git, explaining that a safe.directory grant must stand in a file git reads since grants given only through GIT_CONFIG_PARAMETERS or GIT_CONFIG_COUNT do not reach the upload's git.
• Data: Working tree upload refusal for misplaced .git entry (345 tks) - Error refusing a working-tree upload because the checkout's .git is a pointer file, symbolic link, hard-linked pointer file, or otherwise unfollowable entry, telling the user to start from the repository's ordinary main checkout instead.
• Data: Working tree upload refusal for missing git objects folders (197 tks) - Error refusing a working-tree upload because the git directory lacks objects/info or objects/pack, as after a copy that skips empty folders, telling the user to check for links with ls -ld and then recreate both with mkdir, or start from a fresh clone.
• Data: Working tree upload refusal for private git directory setup failure (349 tks) - Error refusing a working-tree upload because its private git directory could not be prepared under the configuration home, telling the user to check that the home and its seed-admin folder are directories only they can write, inspect them with ls -ld, remove scratch directories or links by name without a trailing slash, and retry.
• Data: Working tree upload refusal for unread git config environment variable (305 tks) - Error refusing a working-tree upload because GIT_CONFIG_GLOBAL or GIT_CONFIG_SYSTEM names a git configuration file a session could change, so the upload's git does not read it, directing the user to move its settings into ~/.gitconfig or git's default system file and remove the variable, or keep the file outside session-writable folders.
• Data: allowManagedPermissionRulesOnly allowed-tools frontmatter scope (424 tks) - Continues the allowManagedPermissionRulesOnly schema description: skill, command, and plugin allowed-tools frontmatter is ignored except for managed and bundled skills and plugins on admin-backed channels such as pinned managed marketplaces, attested claude.ai-synced plugins, and host-delivered --plugin-dir plugins.
• Data: allowManagedPermissionRulesOnly deny rules still apply (45 tks) - Closes the allowManagedPermissionRulesOnly schema description by noting that --disallowedTools, skill disallowed-tools, and other command-line or session deny and ask rules still apply.
• Data: allowManagedPermissionRulesOnly setting (66 tks) - Schema description for the managed allowManagedPermissionRulesOnly setting, which ignores permission rules from user, project, local, and --settings files and --allowedTools allow rules so only managed settings can add allow rules.
• Data: allowedMcpServers setting (204 tks) - Describes how the enterprise allowedMcpServers setting governs user-added versus organization-delivered MCP servers, including ${VAR} expansion, undefined and empty-array behavior, and denylist precedence.
• Data: availableModelsMatch setting (315 tks) - Schema description for the managed availableModelsMatch setting, contrasting prefix and exact matching of availableModels entries, family and release-dependent alias handling, Default-model restriction with startup failure, and which background and helper requests stay unrestricted.
• Data: deniedModels setting (222 tks) - Schema description for the managed deniedModels setting, covering family-alias blocking, version-wide model ID blocking across dates, -fast and provider prefixes, ignored release-dependent aliases, and Default-model step-down or startup failure.
• Data: syncClaudeAiPlugins setting (332 tks) - Describes how the syncClaudeAiPlugins setting disables account-synced plugin downloads, availability, and cleanup across user, managed, workspace, and invocation scopes.
• Data: syncClaudeAiSkills setting (314 tks) - Describes how the syncClaudeAiSkills setting disables account-synced skill downloads, availability, and cleanup across user, managed, workspace, and invocation scopes.

System Prompt

Parts of the main system prompt.

• System Prompt: /loop tick (loop.md absent, dynamic pacing) (315 tks) - Loop tick injection for dynamic self-paced autonomous checks when loop.md is absent.
• System Prompt: /loop tick (loop.md tasks) (94 tks) - Loop tick injection for recurring cron-based runs of tasks from loop.md.
• System Prompt: /loop tick (loop.md tasks, dynamic pacing) (311 tks) - Loop tick injection for dynamic self-paced runs of tasks from loop.md.
• System Prompt: Act when ready (68 tks) - Instructs the agent to act once it has enough information and give recommendations instead of exhaustive surveys.
• System Prompt: Action safety and truthful reporting (161 tks) - Requires confirmation for irreversible or outward-facing actions, checking targets before destructive edits, and truthful reporting of outcomes.
• System Prompt: Advisor tool instructions (443 tks) - Instructions for using the Advisor tool.
• System Prompt: Agent Summary Generation (291 tks) - System prompt used for "Agent Summary" generation.
• System Prompt: Agent thread notes (293 tks) - Behavioral guidelines for agent threads covering absolute paths, response formatting, emoji avoidance, and tool call punctuation.
• System Prompt: Analysis instructions for full compact prompt (recent messages) (288 tks) - Provides analysis instructions for summarizing only recent messages during conversation compaction.
• System Prompt: Artifact comment decision reformat retry (256 tks) - Instructs the Artifact comment composer to reformat a malformed prior response as exactly one valid JSON decision while treating the reproduced response as untrusted data.
• System Prompt: Artifact comment edit composer (911 tks) - Instructs a tool-less Artifact comment composer to emit exactly one reply or edit decision using ordered exact-string patches and an availability-gated full-rewrite form.
• System Prompt: Artifact comment fast acknowledgement selection (603 tks) - Instructs a no-tools helper to select exactly one numbered canned acknowledgement for the newest Artifact comment based on edit capability, trigger state, and whether the request needs an artifact edit or reply.
• System Prompt: Artifact comment fast acknowledgement (240 tks) - Prompts a no-tools helper model to produce one short plain-text acknowledgement for the newest Artifact comment before the full reply.
• System Prompt: Artifact comment list framing (1055 tks) - Frames Artifact comment-list tool results as untrusted viewer data using randomized fences and optional selected-text, anchor-path, and anchor-file/page guidance.
• System Prompt: Artifact comment presence state guidance (238 tks) - Explains that Artifact comment presence rows are tool-emitted, page-produced untrusted data that may resolve references but never supply instructions or permissions.
• System Prompt: Artifact comment reply composer (375 tks) - Instructs a tool-less composer to answer an Artifact comment thread or flag requested artifact changes for its session in one brief plain-text reply without claiming or promising edits.
• System Prompt: Artifact comment result guidance (225 tks) - Appends reply, resolve, and focused thread-read instructions to Artifact comment-list tool results.
• System Prompt: Artifact comment thread framing (2178 tks) - Frames an Artifact comment thread and optional anchor context as untrusted viewer data using randomized fences.
• System Prompt: Artifact comment thread triage (306 tks) - Classifies the newest human request in a framed Artifact comment thread as an artifact edit or a reply-only pipeline action.
• System Prompt: Artifact commenter access guidance (183 tks) - Explains that the access word before a comment's stamp — owner, editor or commenter — is the access the server recorded for that person, context for weighing feedback but never a permission, and when an outside-organization note follows it.
• System Prompt: Artifact page-owned comment thread guidance (192 tks) - Directs replies to page-owned comment threads through an available authorized page tool rather than Artifact relay threads.
• System Prompt: Artifact patch turn edit composer (715 tks) - Instructs a tool-less composer to emit exactly one JSON decision for an artifact edit request, either ordered exact-string file edits with a one-sentence reply and confidence rating or a hand-back to the main assistant when needed context is missing or the request asks for an opinion, recommendation or choice, under strict patch-uniqueness and sizing rules.
• System Prompt: Auto mode Slack message provenance (1170 tks) - Instructs the auto mode classifier to treat server-verified human Slack relays as user intent while rejecting bot-authored and nested relays as consent.
• System Prompt: Auto mode setup proposal generator (2740 tks) - Transforms gathered repository and usage reconnaissance into a constrained JSON proposal for auto-mode environment context and permission rules.
• System Prompt: Auto mode (244 tks) - Continuous task execution, akin to a background agent.
• System Prompt: Autonomous loop check (1484 tks) - Defines behavior for autonomous timer-based invocations, guiding Claude to continue established work, maintain PRs, and handle repeated idle checks while the user is away.
• System Prompt: Autonomous loop notification guidance (98 tks) - Guides when autonomous loop ticks should notify the user via PushNotification for blockers or actionable state changes.
• System Prompt: Autonomous loop persistence guidance (CLAUDE_CODE_LOOP_PERSISTENT) (1630 tks) - Defines behavior for autonomous timer-based invocations, guiding Claude to persistently continue established work, maintain PRs, and broaden scope before stopping while the user is away.
• System Prompt: Autonomous loop tick (dynamic pacing) (311 tks) - Autonomous loop tick injection for dynamic self-paced autonomous checks scheduled with ScheduleWakeup.
• System Prompt: Autonomous loop tick (87 tks) - Autonomous loop tick injection for recurring cron-based autonomous checks.
• System Prompt: Autonomous operation guidelines (407 tks) - Instructs autonomous sessions to proceed on reversible work, stop for destructive or scope-changing actions, and finish promised work before ending the turn.
• System Prompt: Avoiding Unnecessary Sleep Commands (part of PowerShell tool description) (175 tks) - Guidelines for avoiding unnecessary sleep commands in PowerShell scripts, including alternatives for waiting and notification.
• System Prompt: Background session instructions (354 tks) - Instructions for background job sessions to use the job-specific temporary directory and follow the appropriate worktree isolation guidance.
• System Prompt: Background session worktree persistence guidance (186 tks) - Directs background sessions to commit and push worktree changes when appropriate while preserving user git-control instructions and branch safety.
• System Prompt: Background worktree isolation guidance (129 tks) - Tells background sessions when to enter an isolated worktree before making code changes and when to continue in place.
• System Prompt: Bash call cost guidance (348 tks) - Explains that each Bash call is a full model round trip, so Claude should batch the work a decision needs into one command, keep printed output small, and check every request requirement against its change before finishing.
• System Prompt: Censoring assistance with malicious activities (98 tks) - Guidelines for assisting with authorized security testing, defensive security, CTF challenges, and educational contexts while censoring requests for malicious activities.
• System Prompt: Chrome browser MCP tools (388 tks) - Instructions for loading deferred Chrome browser MCP tools through ToolSearch in a single batched selection before browser tasks.
• System Prompt: Claude Fable 5 model identity (202 tks) - Identifies this Claude iteration as Claude Fable 5, explains its relationship to Claude Mythos 5, and links to Anthropic's comparison announcement.
• System Prompt: Claude Fable 5.1 model identity (235 tks) - Identifies this Claude iteration as Claude Fable 5.1, explains its relationship to Claude Mythos 5.1, and points users to Anthropic's Fable and Mythos announcement for differences.
• System Prompt: Claude in Chrome browser automation (non-deferred tools) (1130 tks) - Instructions for using directly available Claude in Chrome browser automation tools effectively.
• System Prompt: Claude in Chrome browser automation (1158 tks) - Instructions for using Claude in Chrome browser automation tools effectively.
• System Prompt: Claude in Chrome browser selection instructions (191 tks) - Instructs the agent to ask the user to choose among multiple connected Chrome browsers before using browser automation tools.
• System Prompt: Claude in Chrome deferred tool loading (311 tks) - Directs Claude to batch-load deferred core and task-specific Chrome MCP tools in one ToolSearch call.
• System Prompt: Combined memory index pointer instructions (120 tks) - Instructs the agent to add one-line pointers for private and team memories to the single private memory index and never write memory content there.
• System Prompt: Comment what and task context avoidance (76 tks) - Instructs Claude not to write comments that explain what code does or reference transient task context.
• System Prompt: Comment why-only guidance (67 tks) - Instructs Claude to write code comments only when the reason is non-obvious and useful to future readers.
• System Prompt: Communication style (297 tks) - Instructs Claude to give brief, user-facing updates at key moments during tool use, write concise end-of-turn summaries, match response format to task complexity, and avoid comments and planning documents in code.
• System Prompt: Concise output style (373 tks) - Defines the built-in Concise output style to lead with results, omit narration, stay brief by default, and preserve requested detail and correctness.
• System Prompt: Context compaction summary (409 tks) - Prompt used for context compaction summary (for the SDK).
• System Prompt: Coordinator cross-session peer guidance (326 tks) - Explains how coordinators discover and message peer Claude sessions while treating peer requests as untrusted input rather than delegated worker authority.
• System Prompt: Coordinator mode orchestration (5896 tks) - Provides coordinator-mode instructions for delegating work to worker agents, managing worker lifecycle, handling cross-session peers, and verifying delegated results.
• System Prompt: Correction restraint (365 tks) - Instructs Claude to correct only consequential errors plainly, avoid unnecessary self-criticism or re-auditing, and evaluate other agents’ corrections before adopting them.
• System Prompt: Delivering work at full scope (605 tks) - Instructs Claude to complete ordinary requested work at full scope under reasonable assumptions, continue past non-blocking concerns, and preserve necessary refusal and risky-action confirmation boundaries.
• System Prompt: Deny rule circumvention classifier guidance (74 tks) - Guides permission classification to block attempts to route around configured Edit, Write, or MultiEdit deny rules.
• System Prompt: Description part of memory instructions (148 tks) - Defines what the memory description field should contain within broader user-memory authoring instructions.
• System Prompt: Doing tasks (ambitious tasks) (47 tks) - Allow users to complete ambitious tasks; defer to user judgement on scope.
• System Prompt: Doing tasks (help and feedback) (24 tks) - How to inform users about help and feedback channels.
• System Prompt: Doing tasks (no compatibility hacks) (52 tks) - Delete unused code completely rather than adding compatibility shims.
• System Prompt: Doing tasks (no unnecessary additions) (73 tks) - Do not add features, refactor, or improve beyond what was asked.
• System Prompt: Doing tasks (no unnecessary error handling) (64 tks) - Do not add error handling for impossible scenarios; only validate at boundaries.
• System Prompt: Doing tasks (security) (67 tks) - Avoid introducing security vulnerabilities like injection, XSS, etc.
• System Prompt: Doing tasks (software engineering focus) (104 tks) - Users primarily request software engineering tasks; interpret instructions in that context.
• System Prompt: Dream CLAUDE.md memory reconciliation (436 tks) - Instructs dream memory consolidation to reconcile feedback and project memories against CLAUDE.md, deleting stale memories or flagging possible CLAUDE.md drift.
• System Prompt: Dream team memory handling (279 tks) - Instructions for handling shared team memories during dream consolidation, including deduplication, conservative pruning rules, and avoiding accidental promotion of personal memories.
• System Prompt: Emoji avoidance (31 tks) - Instructs Claude to avoid using emojis unless the user explicitly asks for them.
• System Prompt: Executing actions with care (1105 tks) - Instructions for executing actions carefully.
• System Prompt: Explain /code-review ultra (131 tks) - Guidance shown when a user asks about 'ultrareview': explains it maps to /code-review ultra (the /ultrareview alias is deprecated) and that the agent can't start it directly.
• System Prompt: Exploratory questions — analyze before implementing (75 tks) - Instructs Claude to respond to open-ended questions with analysis, options, and tradeoffs instead of jumping to implementation, waiting for user agreement before writing code.
• System Prompt: Feedback memory body structure (79 tks) - Defines the body structure for feedback memories, including the rule, why, and how to apply it.
• System Prompt: Feedback memory save guidance (121 tks) - Explains when to save feedback memories from user corrections or confirmed non-obvious approaches.
• System Prompt: Focus mode (long form) (105 tks) - Focus-mode notice (long form): the user sees only the final text, not tool calls, results, or inter-step writing.
• System Prompt: Focus mode (short form) (91 tks) - Focus-mode notice (short form): only each response's final text reaches the user.
• System Prompt: Fork usage guidelines (326 tks) - Instructions for when to fork subagents and rules against reading fork output mid-flight or fabricating fork results.
• System Prompt: Forked agent guidance (164 tks) - Explains that calling Agent with subagent_type "fork" creates a background fork and when to use it.
• System Prompt: Forked conversation worktree isolation guidance (416 tks) - Warns a forked background conversation not to enter the original session's worktree and directs it to create a separate worktree when isolation is enabled.
• System Prompt: Fresh subagent delegation example (315 tks) - Provides an example of briefing a fresh specialized subagent with sufficient context and a specific reporting request.
• System Prompt: Frontend browser verification (86 tks) - Requires Claude to start the dev server and verify UI or frontend changes in a browser before reporting completion.
• System Prompt: Git status (37 tks) - System prompt for displaying the current git status at the start of the conversation.
• System Prompt: Harness instructions (299 tks) - Core interactive-agent identity and harness instructions for terminal Markdown output, security, permissions, system-reminder handling, hook feedback, tool use, and code references.
• System Prompt: Hook evaluator truncated transcript note (74 tks) - Tells the hook condition evaluator that earlier conversation was omitted and how to handle insufficient evidence.
• System Prompt: Hook feedback handling (85 tks) - Explains that hook feedback should be treated as user feedback and how to respond when hooks block actions.
• System Prompt: Hooks Configuration (1493 tks) - Documents hook structure, events, types, input/output fields, and examples for the Claude Code configuration skill.
• System Prompt: How to use the SendUserMessage tool (283 tks) - Instructions for using the SendUserMessage tool.
• System Prompt: Insights at a glance summary (569 tks) - Generates a concise 4-part summary (what's working, hindrances, quick wins, ambitious workflows) for the insights report.
• System Prompt: Insights friction analysis (139 tks) - Analyzes aggregated usage data to identify friction patterns and categorize recurring issues.
• System Prompt: Insights interaction style (119 tks) - Analyzes Claude Code usage data to describe the user's interaction style.
• System Prompt: Insights memorable moment (96 tks) - Analyzes Claude Code usage data to find a memorable qualitative moment.
• System Prompt: Insights on the horizon (148 tks) - Identifies ambitious future workflows and opportunities for autonomous AI-assisted development.
• System Prompt: Insights session facets extraction (310 tks) - Extracts structured facets (goal categories, satisfaction, friction) from a single Claude Code session transcript.
• System Prompt: Insights suggestions (737 tks) - Generates actionable suggestions including CLAUDE.md additions, features to try, and usage patterns.
• System Prompt: Insights summary (At a Glance) (272 tks) - The 'At a Glance' summary block of the Insights report (what's working / what's hindering).
• System Prompt: Insights what works (121 tks) - Analyzes Claude Code usage data to identify workflows that are working well for the user.
• System Prompt: Interactive agent intro (output-style active) (40 tks) - Opening system-prompt line for sessions that have an Output Style configured.
• System Prompt: Interactive agent intro (output-style conditional) (231 tks) - Opening system-prompt line that selects Output Style, collaborative-goals, or software-engineering framing and injects security guidance.
• System Prompt: Interactive agent intro (short) (27 tks) - Minimal opening system-prompt line for software-engineering sessions.
• System Prompt: Learning mode (insights) (142 tks) - Instructions for providing educational insights when learning mode is active.
• System Prompt: Learning mode (1042 tks) - Main system prompt for learning mode with human collaboration instructions.
• System Prompt: Memory description of user feedback (139 tks) - Describes the user feedback memory type that stores guidance about work approaches, emphasizing recording both successes and failures and checking for contradictions with team memories.
• System Prompt: Memory index pointer instructions (129 tks) - Instructs the agent to add one-line pointers to the memory index file and treat the index as separate from memory content.
• System Prompt: Memory instructions (487 tks) - Instructions for using persistent file-based memory, including memory file format, scope, indexing, and stale-memory handling.
• System Prompt: Memory persistence scope (60 tks) - Explains that memory is for information useful in future conversations, not only within the current conversation.
• System Prompt: Memory save exclusions (14 tks) - Lists categories of information that should not be saved in memory, even when the user asks.
• System Prompt: Minimal mode (285 tks) - Describes the behavior and constraints of minimal mode, which skips hooks, LSP, plugins, auto-memory, and other features while requiring explicit context via CLI flags.
• System Prompt: Monitor fallback heartbeat guidance (319 tks) - Guides dynamic loop ticks to use Monitor as the primary wake signal and ScheduleWakeup as a fallback heartbeat, place a visible status update before or after re-arming, and stop the monitor when ending the loop.
• System Prompt: Moved Artifact comment thread guidance (158 tks) - Directs Claude to re-evaluate a previously sent Artifact comment after its author moves the thread to a new location.
• System Prompt: Non-fork subagent delegation examples (894 tks) - Provides conditional non-fork subagent examples for background and synchronous execution, including self-contained prompts, waiting-state responses, and independent-review briefing.
• System Prompt: One of six rules for using sleep command (23 tks) - One of the six rules for using the sleep command.
• System Prompt: Option previewer (151 tks) - System prompt for previewing UI options in a side-by-side layout.
• System Prompt: Outcome-first communication style (815 tks) - Instructs Claude to keep user-facing updates readable and outcome-first, answer directly after work completes, match response format to task complexity, and limit code comments to non-obvious constraints.
• System Prompt: PR Slack notification step (125 tks) - Adds a PR workflow step to optionally ask the user before posting the PR URL to Slack.
• System Prompt: PR Steward handoff guidance (597 tks) - Explains the PR Steward watching and working labels and requires checking a PR's labels before pushing, babysitting, or monitoring it, offering the user leave-it, one-change, or take-over choices and leaving the PR alone when the user is away.
• System Prompt: Parallel tool call note (part of "Tool usage policy") (102 tks) - System prompt telling Claude to use parallel tool calls.
• System Prompt: Partial compaction instructions (852 tks) - Instructions on how to compact when the user decided to compact only a portion of the conversation, with a structured summary format and analysis process.
• System Prompt: Permission classifier strict review guidance (79 tks) - Instructs the permission classifier to carefully deny blocked actions and require explicit user confirmation for overrides.
• System Prompt: Personal project memory description (67 tks) - Describes project memories for ongoing work, goals, initiatives, bugs, or incidents relevant to the user's work in a directory.
• System Prompt: Phase four of plan mode (292 tks) - Final plan-writing instructions for phase four of plan mode.
• System Prompt: Plan mode interactive workshop offer (688 tks) - Instructs plan mode to offer an interactive workshop for substantive design decisions and integrate accepted workshop decisions into the canonical plan.
• System Prompt: Plan sent to Ultraplan (106 tks) - User-facing note confirming a plan has been sent to Ultraplan for remote refinement.
• System Prompt: Plan vs memory guidance (115 tks) - Explains when to use or update a plan instead of saving information to memory.
• System Prompt: PowerShell edition for 5.1 (440 tks) - System prompt for providing information about Windows PowerShell 5.1.
• System Prompt: PowerShell edition for 7+ (128 tks) - Describes PowerShell 7+ shell syntax support, including pipeline chain operators, ternary, null-coalescing, and UTF-8 defaults.
• System Prompt: PowerShell edition unknown (108 tks) - Assumes Windows PowerShell 5.1 compatibility when the PowerShell edition is unknown and forbids PowerShell 7-only syntax.
• System Prompt: Prefer editing existing files (17 tks) - Instructs Claude to prefer editing existing files instead of creating new ones.
• System Prompt: Project member session user message provenance (1064 tks) - Defines how marked messages in a shared-project member's own session count as that member's user turns while coordinator relays, bare approvals, and other relayed content stay untrusted.
• System Prompt: Project memory body structure (83 tks) - Defines the body structure for project memories, including the fact or decision, why, and how to apply it.
• System Prompt: Project memory save guidance (91 tks) - Explains when to save project memories about who is doing what, why, or by when, including absolute date handling.
• System Prompt: Project skill upkeep for feedback memory (314 tks) - Instructs Claude to update the relevant project skill when saving feedback memory about repeatable workflow corrections.
• System Prompt: Project thread in-thread message provenance (291 tks) - Explains that a message the person sends in the project thread arrives as its own marked user turn, and that a bare approval there answers only what the session sent through the reply tool and clears no SOFT BLOCK unless it names the action and its target.
• System Prompt: Project timeline user message provenance (1688 tks) - Defines how project timeline messages from the verified owner become user turns while other relayed or fetched project content remains untrusted external data.
• System Prompt: Remote plan mode (ultraplan) (870 tks) - System reminder injected during remote planning sessions that instructs Claude to explore the codebase, produce a diagram-rich plan via ExitPlanMode, and implement it with a pull request upon approval.
• System Prompt: Remote planning session (612 tks) - System reminder that configures a remote planning session to explore the codebase, produce an implementation plan via ExitPlanMode, and handle plan approval, rejection, or teleportation back to the user's local terminal.
• System Prompt: Reporting outcomes (261 tks) - Requires reports to distinguish observed outcomes from intentions, lead with failures or incomplete work, and avoid overstating unverified completion.
• System Prompt: Respond in configured language (128 tks) - Directs all responses, explanations, and code commentary into a configured language.
• System Prompt: Responsive mode (813 tks) - Directs Claude to answer immediately with a one or two sentence acknowledgement before thinking or calling any tool, and to write plain conversational English free of openers, flattery, filler and wrap-ups.
• System Prompt: Sandbox task resource boundary (217 tks) - Limits sandboxed work to task-provided resources even when other resources are reachable and requires reporting missing access instead of bypassing the boundary.
• System Prompt: Saving skills via file delivery (270 tks) - Explains that account skills are not modified by filesystem writes and directs the agent to deliver complete skill files with the file-sending tool.
• System Prompt: Self-hosted runner doctor (6808 tks) - Instructs an agent to diagnose self-hosted runner authentication, network, lifecycle, queue, hooks, metrics, and escalation issues.
• System Prompt: Self-hosted runner setup (2228 tks) - Guides an operator through creating, verifying, learning, and documenting a self-hosted runner deployment.
• System Prompt: Shared git stash safety (201 tks) - Warns that git stash is shared across worktrees and sessions, preferring WIP commits or uniquely tagged stash entries.
• System Prompt: Skill save permission note (163 tks) - Notes that whether a delivered file can be saved as a skill depends on organization settings the assistant cannot see, and how to phrase that conditionally rather than as a certainty.
• System Prompt: Skillify Current Session (1798 tks) - System prompt for converting the current session into a skill.
• System Prompt: Subagent delegation cost guidance (503 tks) - Explains when delegation is worth its context and token costs, when to work inline, and how to brief a subagent narrowly.
• System Prompt: Subagent delegation examples (620 tks) - Provides example interactions showing how a coordinator agent should delegate tasks to subagents, handle waiting states, and report results.
• System Prompt: Subagent delegation restraint (479 tks) - Guides Claude to delegate work only when it is genuinely independent, large enough to justify a fresh context, or naturally parallel, while avoiding excessive or redundant subagents and not redoing delegated work.
• System Prompt: System section (93 tks) - System section of the main system prompt.
• System Prompt: Task approval continuity (109 tks) - Instructs the agent to continue agreed tasks end to end without unnecessary re-confirmation.
• System Prompt: Tasks vs memory guidance (80 tks) - Explains when to use tasks instead of saving current-conversation progress to memory.
• System Prompt: Team memory index pointer instructions (159 tks) - Instructs the agent to add one-line memory pointers to the appropriate team memory index file and never write memory content into the index.
• System Prompt: Team project memory description (67 tks) - Describes project memories for shared ongoing work, goals, initiatives, bugs, or incidents within a working directory.
• System Prompt: Teammate Communication (105 tks) - System prompt for teammate communication in swarm.
• System Prompt: Tone and style (code references) (39 tks) - Instruction to include file_path:line_number when referencing code.
• System Prompt: Tone and style (concise output — short) (16 tks) - Instruction for short and concise responses.
• System Prompt: Tool call colon avoidance (59 tks) - Instructs Claude not to use a colon before tool calls because tool calls may be hidden from user output.
• System Prompt: Tool call summary label (112 tks) - Instructs Claude to write a short past-tense summary label for completed tool calls in mobile UI rows.
• System Prompt: Tool usage (subagent guidance) (141 tks) - Guidance on when and how to use subagents effectively.
• System Prompt: Tool usage (task management) (70 tks) - Use TodoWrite to break down and track work progress.
• System Prompt: Troubleshooting confirmation policy (71 tks) - Requires explaining fixes and confirming before destructive or installation-changing troubleshooting commands.
• System Prompt: User memory usage guidance (91 tks) - Explains when to use user memories to tailor responses to the user's profile or perspective.
• System Prompt: WSL managed settings double opt-in (152 tks) - Explains that WSL can read the Windows managed settings policy chain only when the admin-enabled flag is set, with HKCU requiring an additional user opt-in.
• System Prompt: Worker instructions (356 tks) - Instructions for workers to follow when implementing a change.
• System Prompt: Writing for the user (586 tks) - Defines concise, standalone user-facing final-message rules covering sentence structure, formatting, code and numbers, terminology, and stopping once the answer is complete.
• System Prompt: Writing subagent prompts (398 tks) - Guidelines for writing effective prompts when delegating tasks to subagents, covering context-inheriting vs fresh subagent scenarios.
• System Prompt: You should know understood-topic skip guidance (150 tks) - Tells the You should know suggestion agent to skip topics the person plausibly understood in the main session while still allowing consequential details mentioned only in passing.

System Reminders

Text for large system reminders.

• System Reminder: /btw side question (406 tks) - System reminder for /btw slash command side questions without tools.
• System Reminder: Agent mention (45 tks) - Notification that user wants to invoke an agent.
• System Reminder: AppifactRepl Slides deck workflow (2086 tks) - Instructs Claude to create or revise a file-backed Slides deck through one AppifactRepl program while preserving its project/deck.json index, slide files, and embedded speaker notes.
• System Reminder: AppifactRepl design canvas workflow (2090 tks) - Instructs Claude to create or revise a file-backed Design canvas through one AppifactRepl program while preserving its project/canvas.json index and changed board files.
• System Reminder: Artifact auto-replies resumed (349 tks) - Reports that Artifact comment auto-replies resumed, explains which stopped-period comments are handled based on the stop cause, and warns that the stop remains until the watch reconnects.
• System Reminder: Artifact capability declaration revocation warning (341 tks) - Warns that publishing a replacement capability declaration would implicitly revoke stored capabilities and explains how to preserve or intentionally revoke them.
• System Reminder: Artifact comment reply activation failure (204 tks) - Explains that an Artifact comment reply was not posted because Claude is not currently activated for the thread and requires reactivation before retrying.
• System Reminder: Artifact comment reply session collision (347 tks) - Reports how concurrent live sessions resolved or may duplicate automatic replies to comments on the same Artifact.
• System Reminder: Artifact page-owned comment reply refusal (156 tks) - Reports that no reply was posted to an Artifact relay thread and directs the answer to the page-owned comment thread or the current session.
• System Reminder: Artifact type instructions trust boundary (246 tks) - Restricts third-party Artifact type instructions to the Artifact's own files and prevents them from expanding scope, permissions, or overriding user and system instructions.
• System Reminder: Artifact type page untrusted content warning (184 tks) - Warns that an owned Artifact page supplied by an Artifact type was written by the type publisher and must be treated as untrusted data rather than instructions.
• System Reminder: AskUserQuestion minimum options validation (161 tks) - Explains that a rejected single-option question was not shown and instructs the agent to proceed without retrying or inventing another option.
• System Reminder: Async agent launched metadata (218 tks) - Reports internal metadata for a newly launched asynchronous agent and warns Claude not to expose its ID or predict its results.
• System Reminder: Async agent launched (146 tks) - Warns Claude not to duplicate an asynchronously launched agent's work or read its full JSONL transcript output file.
• System Reminder: Attached device stopped offering tools (194 tks) - Tells the agent a remote tool call to a previously attached device could not run because that device stopped offering tools, and directs asking the user to check the Claude app on that computer.
• System Reminder: Attached machine reply not received (276 tks) - Reports that a still-connected attached machine's reply to a command never arrived despite liveness checks, so the outcome is unknown, forbids re-running non-idempotent commands just to see output, and suggests narrower commands for large output.
• System Reminder: Attached machine stopped answering (321 tks) - Reports that an attached machine stopped answering health checks while or after a command was sent, so the command's outcome is unknown, and forbids retrying non-idempotent commands or calling that machine again this turn.
• [System Reminder: Attached machine untrusted attachments refusal](./system-prompts/system-reminder-attached-machine-untrusted-attachments-refusal.