agentmods.dev

code-forge AGENTS.md

Instructions for maintaining code-forge, a plugin collection containing coding agents, hooks, rules, skills, templates, and stack-specific guidance. It also describes Smith, the build system used for project-specific agents.

In plain words
What is it for?
Use them when editing plugin agents, creating project-specific agents, changing design rules, or building those agents with Smith.
Why use it?
They show where changes belong and when generated project agents need to be built, reducing conflicts between source files and generated files.

Instructions file for CodexOpenCode

13 2mo ago A scan 1,227 tokens original MIT
View the source file ggombee/code-forge
Install

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.

agentmods
npx agentmods add instructions/ggombee/code-forge/agents-md
Clone the repo
git clone --depth 1 https://github.com/ggombee/code-forge

Made for: Codex, OpenCode.

Per session 1,227 This file is loaded in full into every session.
When invoked 1,227 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.01227 $0.01227
Opus 5 $0.00613 $0.00613
Sonnet 5 $0.00245 $0.00245
Haiku 4.5 $0.00123 $0.00123

Measured 2d ago against content hash 1fcce395fc29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-forge AGENTS.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.

AGENTS.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — code-forge Agent Instructions

이 파일은 AAIF(Agent Architecture Instruction Format) 표준에 따라 작성되었다. AI 에이전트(Codex/Cursor 포함)가 이 저장소에서 작업할 때 준수해야 할 규칙을 정의한다.

카탈로그(에이전트/스킬/훅/규칙 표)는 여기 없다 — 단일 소스 docs/REFERENCE.md 참조. 이 파일은 멀티모델 진입점 델타(수정 규칙 + 금지 작업)만 유지한다 (2026-06-12 H1 dedup).

프로젝트 구조 개요

code-forge/
├── agents/          # 플러그인 에이전트 .md (직접 편집 가능)
├── docs/            # 설계 원칙, 가이드, REFERENCE.md(카탈로그 단일 소스)
├── hooks/           # Claude Code 훅 스크립트
├── instructions/    # 멀티에이전트 협업 가이드
├── modules/         # 스택별 컨벤션 모듈
├── plugins/smith/   # Smith 빌드 시스템 (프로젝트 에이전트 소스)
├── presets/         # 스택 프리셋
├── rules/           # 사고 모델 + 코딩 표준
├── skills/          # 스킬 커맨드 (/start, /handoff 등 — 목록은 REFERENCE.md)
├── CLAUDE.md        # 플러그인 메인 설명서 (포인터 중심)
└── AGENTS.md        # 이 파일

설계 원칙

이 플러그인을 수정/확장할 때 docs/design-principles.md를 반드시 참조한다. 모든 변경은 설계 원칙에 위배되지 않아야 한다.

에이전트 수정 규칙

플러그인 에이전트 (agents/)

agents/ 파일은 직접 편집한다. Smith 빌드 불필요.

프로젝트 전용 에이전트

1. /code-forge:smith-create-agent → .agents/agents/ 에 생성 (STATE+ACT 조합, setup에서 자동 호출됨)
2. /code-forge:smith-build --project → .claude/agents/ 컴파일

Smith 빌드는 프로젝트 에이전트 전용. STATE/ACT 부품은 plugins/smith/agents/state/, plugins/smith/agents/act/.

릴리스 절차 (버전 범프 시 필수)

  1. CHANGELOG.md 최상단에 새 버전 섹션 작성 — 추가/변경/수정/제거, 사용자 관점 패치노트
  2. .claude-plugin/plugin.json version 범프 — CHANGELOG 갱신과 같은 커밋에
  3. git push origin main → claude plugin update code-forge@forge-market --scope project (+ --scope local)
  4. 캐시(~/.claude/plugins/cache/forge-market/code-forge/<ver>/)에서 핵심 변경 1개 spot-check — "소스 수정 ≠ 배포" (2026-06-11 교훈: 픽스가 소스에만 있고 캐시는 한 달 stale이었음)

금지 작업

금지 이유
CHANGELOG.md 갱신 없는 버전 범프 패치노트 없는 릴리스 — 변경 추적 불가 (§릴리스 절차)
.claude/agents/ (프로젝트 컴파일 출력) 직접 수정 smith-build 출력물 — 다음 컴파일 시 덮어씌워짐. 소스는 .agents/agents/
hooks/hooks.json 수동 수정 후 검증 생략 JSON 파싱 오류로 훅 전체 비활성화됨
rules/ 파일 삭제 alwaysApply/path-scoped 규칙 — 모든 에이전트 동작에 영향
presets/ 스키마 변경 /setup 스킬 파싱 오류 유발
민감한 파일(.env, credentials) 커밋 write-guard.sh가 Write를 차단하지만 직접 커밋은 차단 안 됨
폐지 스킬(/done /bug-fix /refactor /quality)을 문서/표에 재추가 v4.0에서 규칙·훅으로 흡수됨 — 대체 매핑은 docs/CATALOG.md
에이전트/스킬 개수를 손으로 세서 문서에 박기 3중 불일치 사고(17/19/21, 2026-06-11 검출) 재발 방지 — 산출 명령 표기

Read the full file on GitHub · 87 lines

Changes

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.

  1. 2d ago First seen · 87 lines · 1,227 tokens per session scan A 1fcce395fc29

Subscribe to this mod's changes

code-forge AGENTS.md is an instructions file published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 1,227 tokens to every session, about $0.0061 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.

ai-agentsclaudeclaude-code-plugin
Related

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,040 tokens

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.

langchain-ai/langchain · 4,345 tokens