project-wiki: Instructions file for Claude Code

CLAUDE.md

project-wiki CLAUDE.md is an instructions file for Claude Code from shrimbly/project-wiki. It costs 2,698 tokens per session, scanned A, original, MIT.

A project guide for a project wiki: an agent-maintained knowledge base that turns documents, meeting transcripts, web pages, design files, and notes into linked reference pages. It explains the repository structure and how the wiki is maintained.

In plain words
What is it for?
Use it when building or maintaining a project wiki. It supports collecting source material, synthesizing it into wiki pages, tracking decisions and open questions, and publishing cleaned-up documents.
Why use it?
It keeps information from many sources organized and connected instead of leaving it in separate, hard-to-find files. This gives a project a durable shared understanding that can be updated as new material arrives.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is shrimbly/project-wiki's own configuration. It tells Claude Code how to work on project-wiki 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 project-wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shrimbly/project-wiki. 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/shrimbly/project-wiki/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shrimbly/project-wiki

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 project-wiki CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shrimbly/project-wiki/claude-md.svg)](https://agentmods.dev/instructions/shrimbly/project-wiki/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shrimbly/project-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/shrimbly/project-wiki/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,698 This file is loaded in full into every session.
When invoked 2,698 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 $0.02698 $0.02698
Opus 5 $0.01349 $0.01349
Sonnet 5 $0.00540 $0.00540
Haiku 4.5 $0.00270 $0.00270

Measured 6d ago against content hash 41f2e5ad1f8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

project-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.

CLAUDE.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{{PROJECT_NAME}}

Project

  • What this is: {{PROJECT_DESCRIPTION}}
  • Deliverable: {{PROJECT_DELIVERABLE}}
  • Audience: {{PROJECT_AUDIENCE}}
  • Owner: {{PROJECT_OWNER}}

New here? This is a project-wiki: an agent-maintained knowledge base that turns scattered source material into a durable, cross-linked synthesis. If the placeholders above are still {{...}}, run /wiki-setup first.

What a project-wiki is

A working repository for building a precise, shared understanding of a problem space — its entities, concepts, decisions, and open questions — out of whatever raw material you can point it at (docs, meeting transcripts, web pages, design files, pasted notes). The agent keeps the synthesis current and consistent as new material lands, and can publish the core of it back out as clean documents.

Architecture

Three layers, inspired by Karpathy's LLM Wiki:

  1. Sources (sources/) — faithful captures of external material. One file per source, original URL preserved in frontmatter so we can always re-fetch. Sources are mostly immutable — edited only to fix mistakes.

  2. Wiki (wiki/) — the persistent synthesis layer. Markdown pages, owned by the agent, that compile, cross-link, and keep current the understanding extracted from sources. Entity pages, concept pages, decisions, open questions. New sources update existing wiki pages; substantive questions can produce new pages.

  3. Schema (this file) — the operating manual. How the wiki is structured, what the conventions are, and how each operation works.

The viewer (viewer/) renders both sources and wiki for browsing + commenting via annotations.

Repo layout

{{PROJECT_SLUG}}/
├── CLAUDE.md              # this file — operating manual (Claude)
├── AGENTS.md              # operating manual for other agents (Codex, etc.)
├── README.md             # human-facing intro + quickstart
├── log.md                # append-only chronological record of operations
├── sources/              # faithful captures of external material
│   ├── INDEX.md          # one-line pointer to each source
│   ├── <slug>.md         # per-source capture
│   └── assets/           # binary assets (images, diagrams)
├── wiki/                 # synthesis layer — agent-owned, interlinked
│   ├── index.md          # wiki page catalog
│   ├── overview.md       # top-level synthesis (the project in one page)
│   ├── open-questions.md # rolling list of unresolved items
│   ├── entities/         # one page per entity
│   ├── concepts/         # one page per cross-cutting concept
│   ├── decisions/        # ADR-style notes for decisions made
│   ├── diagrams/         # mermaid diagrams of the model
│   └── references/       # external / competitive captures used as input
├── annotations/          # user highlights + comments captured in the viewer
│   └── <slug>.json
├── _templates/           # source + wiki page templates
└── viewer/               # Astro web viewer

Read the full file on GitHub · 248 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. 6d ago First seen · 248 lines · 2,698 tokens per session scan A 41f2e5ad1f8f

Subscribe to this mod's changes

project-wiki CLAUDE.md is an instructions file published in the GitHub repository shrimbly/project-wiki (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,698 tokens to every session, about $0.0135 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 · 5,182 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