claude-forge

sangrokjung/claude-forge is ranked 19,049 among these 8 peers; xdevplatform/xmcp is ranked 19,044.

• Install • What's inside • How to use • Architecture • FAQ • 한국어 **v4. ** Same hook, same report; it detects whether a transcript is a Claude Code transcript or a Codex rollout log and counts either. Wiring for Codex is two entries you add to (how). Resume-aware, so a session you picked back up days later reports that sitting rather than a bogus 400-hour total. md + rules) and shrink it back under budget without losing governance. 0

itself, the loop caught three real defects in the maintainer's own PRs (#58, #61); worked example: . If ever showed ( ), that bug is fixed as of v4. 1 (Anthropic 2026 standard alignment: Hooks 21+ events, Subagent frontmatter v2, Skills/Commands hybrid policy, 4-server MCP minimum). **Plain English version:** Claude Code is an AI coding assistant that lives in your terminal. Claude Forge is the **equipment pack** for that assistant. Claude Forge does the same thing for Claude Code. Agents, hooks

, rules, and MCP connections need Option B. If Claude Forge helps you, a star on GitHub helps others find it. Claude calls the right one automatically. | | **Commands** (shortcut buttons) | 35 | Type and Claude creates a full implementation plan. Type and it writes tests first, then code. All 35 are pre-built shortcuts for common developer tasks. turns any repetitive task into a reusable slash command in seconds; runs the maker≠checker verification cycle. | | **Hooks** (silent safety checks) | 22 built-in

+ 9 opt-in examples | These run before and after every action Claude takes. 0, they auto-resume a session after a retryable API error and nudge you when you're stuck editing the same file. | | **MCP connections** (external tools) | 4 | Browser automation (Playwright), live library docs (context7), web page reader (jina-reader), and Chrome DevTools for performance audits. Waits for your sign-off before any code is written. | | **architect** | Designs system structure, makes scalability decisions, reviews technical architecture. | | **code-reviewer** | Checks

code quality, security, and maintainability after you write it. | | **security-reviewer** | Scans for OWASP Top 10 vulnerabilities, leaked secrets, injection risks. | | **tdd-guide** | Enforces test-first development: RED (failing test) → GREEN (passing) → IMPROVE (refactor). | | **database-reviewer** | Optimizes PostgreSQL/Supabase queries, reviews schema design. | | **e2e-runner** | Generates and runs Playwright end-to-end browser tests. | | **refactor-cleaner** | Finds and removes dead code using knip, depcheck, ts-prune. | | **doc-updater** | Keeps documentation and code maps in sync after changes. | | **skeptical-auditor** | Re

-audits a pass another agent already claimed: re-runs each step that was reported green and compares the real exit codes against the claim. | | **systematic-debugger** | Reproduce → bisect → hypothesize → verify. Never guesses at a fix without a failing test that proves the hypothesis. Waits for your confirmation before coding. | | | Security + quality check on the code you just wrote. | | | Auto-verify build/test/lint all at once. | | | Fast commit for simple, well-tested changes. | | | Auto-retry build/lint/test up to

3x with auto-fix. | | | One-button automation: plan to PR without stopping. | | | Interactive 3-minute tour for first-time users.