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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/lazymac2x/agent-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/lazymac2x/agent-wiki/agents-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 | $0.02399 | $0.02399 |
| Opus 5 | $0.01200 | $0.01200 |
| Sonnet 5 | $0.00480 | $0.00480 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade C, and why
agent-wiki AGENTS.md scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- 병렬 = worktree-per-agent + 에이전트스코프 브랜치. git작업 직렬화(`kill -15` + `git worktree remove`, `kill -9`/`rm -rf` 금지). rebase-before-merge 순차머지. How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — agent-wiki 헌장 (단일 정본 SOT)
이 한 파일이 규칙의 70~80%다. 도구무관(Claude Code / Cursor / Codex / 사람 공용). 다른 진입점(
CLAUDE.md)은 이걸 import 한다. 충돌 시 우선순위: 이 파일 > 폴더INDEX.md의 로컬 주석 > 개별 노트 frontmatter. 이 저장소는 자기 자신에게 규칙을 적용한다(dogfood) —scripts/check-all.sh를 통과 못하면 커밋 금지.
1. 정체성 — 이게 뭐가
agent-wiki는 지식 자산화 OS = "지식 공장". 흔어진 집단지성(하네스 노하우 + 도메인 지식 + 개인 운영지식)을
검색 가능·링크된·검증된·토큰효율적 자산으로 굳히고, 그 위에서 코어 에이전트가 일한다.
규모는 작게(알짜배기), 확장은 무한(이 폴더에서 바로 새 프로젝트/라인을 stamp).
6폴더 멘탈모델 (이 순서로 외운다):
| 폴더 | 한 단어 | 무엇 |
|---|---|---|
agents/ |
누가 | 코어 에이전트 — 프로젝트/라인별 비즈니스 로직 보유, wiki를 JIT로 끌어다 씀 |
wiki/ |
무엇을 | 지식 자산 — domain/(개발 공유) · factory/(제조) · personal/(개인 LLM wiki) |
harness/ |
어떻게 | 방법론 — workflows/(실행 how-to) · patterns/(개념·왜) |
projects/ |
어디서 | 프로젝트 미니 wiki(자기완결·자기유사) |
templates/ prompts/ |
재료 | 부트스트랩 템플릿 + 예시 프롬프트(폴더트리 동봉) |
scripts/ .ops/ .claude/ |
위생·강제 | 생성/린트 CI + 운영 SOT + hook 강제 |
2. 7대 법칙 (Laws) — 전부 dogfood 대상
L1. 단일 SOT chokepoint (문서판 단일소스 provider)
한 사실 = 한 노트에만 산다. 어디서나 [[link]]로 참조하고 복붙 절대 금지. → 상세 [[sot-registry]]
- 표면패치 = whack-a-mole. 단일소스가 근본. 같은 값이 두 곳에 있으면 그게 버그다(
wiki-lint의 dup-SOT가 잡는다). - 외부 소유경계: 자격증명/수익 같은 민감정보 = 외부 SOT 파일(
<your-secrets-sot>) owns(wiki는 point만). 에이전트 학습 = auto-memory가 owns. 방법론+프로젝트지식 = agent-wiki owns. → [[memory-bridge]]
L2. 프랙탈 INDEX + 위키링크 (자기유사 항해)
모든 폴더에 같은 모양 INDEX.md. 항목은 - [[name]] — ≤150자 헤드라인 1줄만. 루트 INDEX.md는 인덱스의 인덱스(본문 0).
- 고아노트 0: 어떤 INDEX에서도 링크 안 되면 금지(
check-orphans). - ⚠️
INDEX.md·llms.txt는 수기편집 금지 —scripts/gen-index.sh가 frontmatter에서 생성한다(상단[GENERATED]배너). 사람용 prose 서문만 롤업 위에 수기 유지.
L3. frontmatter 계약 (전 노트 의무)
모든 .md는 [[note]] 템플릿의 frontmatter를 가진다: name / description(≤150자) / type / track / status / owner / created / updated / source / links.
- 에이전트는 본문 전 frontmatter만 필터로 노트를 선별(progressive disclosure·메타데이터=신호).
status:PROVEN(실증·90점 통과) ·DRAFT(미검증) ·DEPRECATED(→ [[pruning]] tombstone).
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.
- 4d ago First seen · 88 lines · 2,399 tokens per session scan C 2b141436631d
agent-wiki AGENTS.md is an instructions file published in the GitHub repository lazymac2x/agent-wiki (43 stars, last pushed 2mo ago), licensed MIT. It adds 2,399 tokens to every session, about $0.0120 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).