llm-wiki-hub: Instructions file for Claude Code

CLAUDE.md

llm-wiki-hub CLAUDE.md is an instructions file for Claude Code from bipark/llm-wiki-hub. It costs 1,051 tokens per session, scanned A, original, MIT.

Project instructions for a read-only hub that collects status information from several separate software projects. It explains how to refresh generated wiki pages, track tasks, and record decisions.

In plain words
What is it for?
Use it when updating the hub dashboard, adding projects, reviewing blockers and tasks, or changing project status through each project's STATUS.md file.
Why use it?
It prevents the hub from being edited in the wrong place and keeps its summaries reproducible from the source projects.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is bipark/llm-wiki-hub's own configuration. It tells Claude Code how to work on llm-wiki-hub itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki-hub configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bipark/llm-wiki-hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bipark/llm-wiki-hub/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bipark/llm-wiki-hub

Made for: Claude Code.

Wrote 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.

agentmods badge for llm-wiki-hub CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bipark/llm-wiki-hub/claude-md/github.svg)](https://agentmods.dev/instructions/bipark/llm-wiki-hub/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bipark/llm-wiki-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/bipark/llm-wiki-hub/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for llm-wiki-hub CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bipark/llm-wiki-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/bipark/llm-wiki-hub/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,051 This file is loaded in full into every session.
When invoked 1,051 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01051 $0.01051
Opus 5 $0.00526 $0.00526
Sonnet 5 $0.00210 $0.00210
Haiku 4.5 $0.00105 $0.00105

Measured 8d ago against content hash 90e390090d47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

llm-wiki-hub 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 8d 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM-Wiki-Hub — Claude Code 운영 규칙

이 저장소는 여러 독립 프로젝트의 상태를 읽기 전용으로 집계하는 매니징 허브다. 각 프로젝트 git 은 별도로 존재하며, 여기서는 절대 수정하지 않는다.

핵심 원칙

  • 통합은 단방향(읽기)·멱등이다. 허브는 각 프로젝트를 들여다보기만 한다.
  • wiki/ 의 생성물은 모두 파생물이다. 직접 편집하지 말고 항상 스크립트로 재생성한다.
  • 프로젝트 상태를 바꿔야 하면, 그 변경은 해당 프로젝트의 STATUS.md 에서 하고 그 프로젝트 git 에 커밋한다.

생성물 (wiki/)

  • index.md : 프로젝트별 요약·상세. 맨 위에 블로커/정체 경고 섹션. 각 프로젝트명은 상세 페이지로 링크.
  • projects/<name>.md : 프로젝트별 상세 페이지. 최근 커밋 10개 + STATUS 메모 + 미커밋 파일 + 할일 전체 + ADR.
  • todos.md : 모든 프로젝트의 미완료 할일(- [ ])을 한데 모은 통합 리스트.
  • adr.md : 모든 프로젝트의 결정사항(ADR)을 한데 모은 목록.

작업 시작 시 (항상)

  1. python scripts/aggregate.py 를 실행해 대시보드를 최신화한다.
  2. wiki/index.md 를 읽고 전체 상태 + 경고(정체/블로커)를 파악한다.
  3. 우선순위가 필요하면 wiki/todos.md 로 통합 할일을 본다.
  4. 설계 맥락이 필요하면 wiki/adr.md 로 결정사항을 본다.

프로젝트 추가

  • projects.txt 에 프로젝트 절대경로(또는 ~/...)를 한 줄 추가한다.
  • 그 프로젝트 루트에 STATUS.md 가 없으면 templates/STATUS.md 를 복사하도록 제안한다. (반드시 그 프로젝트 git 에서 커밋하도록 안내)

프로젝트 상태 갱신

  • 진행 상황·마일스톤·블로커가 바뀌면:
    • 해당 프로젝트의 STATUS.md 를 수정한다.
    • 그 프로젝트 디렉토리에서 git add STATUS.md && git commit 한다.
    • 허브로 돌아와 python scripts/aggregate.py 를 재실행한다.

정체/경고 동작

  • 마지막 커밋이 LLMWIKIHUB_STALE_DAYS(기본 7일)를 넘으면 💤 정체로 표시된다.
  • STATUS.mdstatus: blocked 는 🚫 로 경고 섹션 맨 위에 노출된다.

할일 수집 규칙

  • 기본은 '할일 목적' 파일만 스캔한다: TODO.md, tasks.md, *-tasks.md, PLAN.md, *-plan.md, ROADMAP.md, STATUS.md 등. (설계문서·README·setup 문서의 체크박스 노이즈를 배제하기 위함)
  • .venv/, node_modules/, vendor/, build/, dist/ 등 벤더/빌드 산출물 경로는 항상 제외된다. (단 wiki/ 는 제외하지 않는다 — 프로젝트가 거기에 진짜 계획 문서를 두기도 한다. 허브 자신의 생성물 자기참조는 위 task-명 글롭만으로 이미 막힌다.)
  • 프로젝트가 다른 파일에 할일을 둔다면 그 프로젝트 STATUS.mdtodos: 글롭으로 재정의한다. 예) todos: README.md, docs/*-tasks.md / 옛 전체 스캔은 todos: *.md.

ADR 수집 규칙

  • 각 프로젝트의 docs/adr/, adr/, wiki/decisions/, decisions/ 중 처음 발견된 디렉토리의 *.md 를 모은다.
  • 각 ADR 파일의 첫 # 제목status: 줄을 읽어 표로 정리한다.

하지 말 것

  • wiki/생성물(*.md, _sidebar.md) 직접 수정 금지 (다음 집계 때 덮어써짐). 단 wiki/index.html(docsify 뷰어 셸)은 집계가 안 건드리는 관리 자산이라 편집해도 된다.
  • 각 프로젝트의 소스 코드를 허브에서 직접 건드리지 말 것. 작업은 그 프로젝트 git 안에서.
  • 프로젝트 git 들을 하나로 합치지 말 것. 흩어진 상태가 정상이다.

Read the full file on GitHub · 60 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. 8d ago First seen · 60 lines · 1,051 tokens per session scan A 90e390090d47

Subscribe to this mod's changes

llm-wiki-hub CLAUDE.md is an instructions file published in the GitHub repository bipark/llm-wiki-hub (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,051 tokens to every session, about $0.0053 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 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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 · 5,153 tokens

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).

microsoft/vscode · 6,785 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

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens