Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/ggombee/code-forge/claude-mdgit clone --depth 1 https://github.com/ggombee/code-forgeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00766 | $0.00766 |
| Opus 5 | $0.00383 | $0.00383 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
code-forge CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
code-forge
프로젝트 스택에 맞는 에이전트, 스킬, 규칙을 자동으로 제공하는 Claude Code 플러그인.
설치 후 /setup 한 번이면 프로젝트에 맞는 CLAUDE.md + AGENTS.md가 자동 생성된다.
(에이전트/스킬 개수는 디스크가 진실 — ls agents/*.md | wc -l, ls skills/*/SKILL.md | wc -l)
설치
claude plugin marketplace add https://github.com/ggombee/forge-market.git
claude plugin install code-forge
로컬: claude --plugin-dir /path/to/code-forge · 설치 후 /setup → 상세: README.md
역할
/setup→ 스택 감지 → CLAUDE.md + AGENTS.md 자동 생성, 스택 모듈(컨벤션) 주입/setup --profile→ 코딩 스타일 분석 →.candidate/profile.md생성- Smith: 프로젝트 전용 에이전트 빌드 (STATE+ACT 컴파일, setup이 자동 호출)
핵심 워크플로우
/start feature.md → 분석 → 구현 → 검증 → 커밋 → PR (원큐; 완료 검증/버그 옵션 제시는 규칙·훅에 흡수 — docs/CATALOG.md)
/handoff → 세션 핸드오프 (중요 맥락 → progress.md + 킥오프 프롬프트 클립보드)
/test → 테스트 통합 진입점 (유닛/E2E/세팅 자동 라우팅)
/setup → 스택 감지 → CLAUDE.md + AGENTS.md 생성
자동 적재 규칙 (매 세션/파일별 — 실제 frontmatter가 진실)
| 규칙 | 적재 시점 |
|---|---|
rules/thinking-model.md |
alwaysApply — GROUND→APPLY→VERIFY→ADAPT |
rules/candidate-profile.md |
alwaysApply — 프로필 참조 + 소통 보장선 + 커밋 컨벤션 |
rules/coding-standards.md |
path-scoped *.{ts,tsx,js,jsx} |
rules/review-guide.md |
자동 주입 없음 — 리뷰 에이전트 @-include 전용 (이중 적재 해소) |
rules/build-guide.md |
path-scoped *.{tsx,jsx} |
카탈로그 (단일 소스 — 여기 표를 복제하지 말 것)
| 찾는 것 | 위치 |
|---|---|
| 에이전트 전체 (4단계 권한) · 스킬 전체 · 훅 · quality-gate · State Layer · 멀티에이전트 · 대장간 체계 | docs/REFERENCE.md |
| 폐지 스킬(/done /bug-fix /refactor /quality → 대체 매핑) · 모듈 · 프리셋 | docs/CATALOG.md |
| 상태/이벤트/통합 계약 | docs/contracts/ (state-schema · event-schema · INTEGRATION) |
| 외부 도구의 상태 접근 | bin/forge status --json (파일 직독 금지) |
수정 규칙
이 저장소를 수정할 때의 규칙·금지 작업은 AGENTS.md 참조.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 53 lines · 766 tokens per session scan A bc7484da4b66
code-forge CLAUDE.md is an instructions file published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 766 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.