Borrowing it
Nothing to install: this file belongs to McGo/claude-code-specumentation. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/McGo/claude-code-specumentation/main/CLAUDE.mdgit clone --depth 1 https://github.com/McGo/claude-code-specumentationWrote 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/mcgo/claude-code-specumentation/claude-md)<a href="https://agentmods.dev/instructions/mcgo/claude-code-specumentation/claude-md"><img src="https://agentmods.dev/badge/instructions/mcgo/claude-code-specumentation/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.
<a href="https://agentmods.dev/instructions/mcgo/claude-code-specumentation/claude-md"><img src="https://agentmods.dev/badge/instructions/mcgo/claude-code-specumentation/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01096 | $0.01096 |
| Opus 5.5 | $0.00438 | $0.00438 |
| Sonnet 5.5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
claude-code-specumentation 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
specumentation is a Claude Code skill (invoked via /specumentation) that combines specification and documentation into a single workflow. It enforces a "spec first" development approach and maintains living documentation throughout the product lifecycle, with the ability to generate various document types as PDF.
Skill Architecture
The skill has two parts:
Declarative Skill (no runtime code)
SKILL.md— Core skill definition with frontmatter metadata and phased execution instructions. This is what Claude Code reads and executes.documents/— Document type definitions shipped with the skill. Each.mdfile defines a document type (frontmatter + generation prompt) that the publish phase uses.install.sh— Installer that symlinks the skill and deploys the MCP server.
MCP Server (Python)
mcp-server/server.py— FastMCP-based server (~250 lines) that exposes concept documents to Claude Desktop via 6 tools:list_projects,set_project,get_overview,list_concepts,get_concept,update_concept.mcp-server/specumentation-mcp— Bash CLI (~100 lines) for project registration (init) and listing (list).
Deployed to ~/.claude/specumentation-mcp/ by install.sh.
Document Type System
Document types live in documents/ and follow this pattern:
---
name: user-manual # Identifier for publish command
title: "User Manual" # Human-readable title
output: "[project]-user-manual-[date]" # Filename pattern
description: "..." # What this type produces
---
[Generation prompt with structure and style instructions]
Built-in types: user-manual, elevator-pitch, executive-summary, architecture, ticket-overview.
New types can be added by creating a new .md file in documents/.
Key Conventions
- Skills are installed as symlinks in
~/.claude/skills/ SKILL.mdfrontmatter usesname,description,disable-model-invocation- PDF generation uses headless Chrome (
--headless --disable-gpu --print-to-pdf) - Documents are never deleted — they form an audit trail
- Language support via
lang=XXparameter parsing - MCP server uses FastMCP with stdio transport
- Project registry at
~/.claude/specumentation-mcp/projects.json
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.
- 2mo ago First seen · 110 lines · 1,096 tokens per session scan A 29ef14339b25
claude-code-specumentation CLAUDE.md is an instructions file published in the GitHub repository McGo/claude-code-specumentation (2 stars, last pushed 7mo ago), licensed MIT. It adds 1,096 tokens to every session, about $0.0044 per session on Opus 5.5. 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.