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/lazymac2x/agent-wiki/claude-mdgit clone --depth 1 https://github.com/lazymac2x/agent-wikiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/lazymac2x/agent-wiki/claude-md)<a href="https://agentmods.dev/instructions/lazymac2x/agent-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/lazymac2x/agent-wiki/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00904 | $0.00904 |
| Opus 5 | $0.00452 | $0.00452 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
agent-wiki 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 6d 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
@AGENTS.md
CLAUDE.md — Claude Code 전용 오버레이
규칙의 본체는 위
@AGENTS.md에 있다(런치 시 전량 펼쳐짐). 여기는 Claude Code에서만 의미 있는 것만. ≤200줄 유지.
세션 시작 시
- 루트
llms.txt(기계지도)를 먼저 본다 — INDEX는 거기서 링크 따라간다. 전체 트리를 통厰로 읽지 말 것(토큰낭비). - 작업 대상 프로젝트가 정해지면 그 코어 에이전트 카드(
agents/<name>.agent.md) +projects/<name>/llms.txt만 적재. - 나머지 지식은 JIT:
rg -l "^name:|^description:|^type:" wiki/ projects/로 frontmatter 검색 → 후보만 Read.
이 저장소와 라이브 메모리의 경계 (중요 — [[memory-bridge]])
- 에이전트 auto-memory 파일(세션마다 자동 로드되는 메모리) = 에이전트 학습. agent-wiki가 여기 사실을 복제하지 않는다.
- 외부 자격/수익 SOT 파일(
<your-secrets-sot>) = 민감정보. agent-wiki는 point만(복붙·재기재 금지). agent-wiki/wiki/= 방법론 + 프로젝트/도메인 지식 owns. 셋이 겹치면 [[sot-registry]] 1:1 등록 규칙으로 해소.- 새 노하우가 생기면: 재사용·범용 → agent-wiki, 휘발성 학습 → auto-memory, 민감정보 → 외부 SOT. 세 곳에 동시 기록 금지.
SKILL 브리지 (재구현 금지, 호출만 — 당신 환경의 스킬/루틴을 연결)
| 작업 | 연결할 것(예) |
|---|---|
| 전수조사→실증→무한 90점 | 심층-피드백/적대비평 스킬 — harness 문서가 그 사용설명서 역할 |
| 런타임 이상 자율수복 | 자가수복 루틴 ≈ [[self-healing]] |
| 멀티에이전트 풀스택 빌드 | 멀티에이전트 빌드 스킬/스쿼드 |
| 교차검증 다관점 | 다관점 토론 스킬 |
| 디바이스 제어·배포 | 디바이스 제어 스킬 |
| UI/로고/색/디자인 | 전용 디자인 에이전트 위임 (crude 자가처리 금지 — [[design]]) |
강제(enforcement)
- 규칙은 컨텍스트일 뿐 강제가 아니다. 실제 강제는
.claude/settings.json+.claude/hooks/pre-commit.sh가 한다. - 커밋 전
scripts/check-all.sh가 fail이면 라운드/배포 미종료. 이걸 우회하면 doc-rot가 그대로 재현된다(build-green≠live-works의 문서판).
Telegram 보고
- 마일스톤(PDCA Act 완료 · 배포 · 머지)마다
mcp telegram notify_user로 1줄 보고. → [[notify]] - 캐시 TTL 5분: 백그라운드 폴링으로 캐시 태우지 말 것(작업 완료 시 자동 재호출됨).
작업 규율 (권장 — 자신의 규율로 교체·확장)
- 정직: 안 되는 건 "안 된다".
build-green ≠ live-works. 가짜0 금지. - 두눈 실증 + 결정론 테스트(무음스킵 = vacuous green = 금지).
- prod 쓰기·비가역 작업 = AskUserQuestion 명시인증 먼저.
- 문서 커지면 쪼개고
[[link]]. 절단(200줄/25KB) 전에 compaction-on-write.
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.
- 6d ago First seen · 41 lines · 904 tokens per session scan A 3d65227b5866
agent-wiki CLAUDE.md is an instructions file published in the GitHub repository lazymac2x/agent-wiki (43 stars, last pushed 2mo ago), licensed MIT. It adds 904 tokens to every session, about $0.0045 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
langchain AGENTS.md
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.