agentmods.dev

claude-code-specumentation CLAUDE.md

claude-code-specumentation CLAUDE.md is an instructions file for coding agents from McGo/claude-code-specumentation. It costs 1,096 tokens per session, scanned A, original, MIT.

A Claude Code workflow that combines writing a product specification with maintaining its documentation, including publishing documents as PDFs.

In plain words
What is it for?
Use it to create specifications, maintain project concepts, generate document types, and expose project documentation through its MCP server.
Why use it?
It encourages agreeing on what to build before coding and keeps the documentation updated as the product changes.

Instructions file

not rated 2 5mo ago A scan 1,096 tokens original MIT
View the source file McGo/claude-code-specumentation
Install

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.

agentmods
npx agentmods add instructions/mcgo/claude-code-specumentation/claude-md
Clone the repo
git clone --depth 1 https://github.com/McGo/claude-code-specumentation

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 claude-code-specumentation CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mcgo/claude-code-specumentation/claude-md.svg)](https://agentmods.dev/instructions/mcgo/claude-code-specumentation/claude-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 1,096 This file is loaded in full into every session.
When invoked 1,096 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01096 $0.01096
Opus 5 $0.00548 $0.00548
Sonnet 5 $0.00219 $0.00219
Haiku 4.5 $0.00110 $0.00110

Measured 3d ago against content hash 29ef14339b25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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 · 110 lines

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 .md file 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.md frontmatter uses name, 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=XX parameter parsing
  • MCP server uses FastMCP with stdio transport
  • Project registry at ~/.claude/specumentation-mcp/projects.json

Read the full file on GitHub · 110 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. 3d ago First seen · 110 lines · 1,096 tokens per session scan A 29ef14339b25

Subscribe to this mod's changes

claude-code-specumentation CLAUDE.md is an instructions file published in the GitHub repository McGo/claude-code-specumentation (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,096 tokens to every session, about $0.0055 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.

DocumentsPDFWriting and docsagent-skillsai-agentsanthropicclaudeclaude-codedeveloper-tools
Related

Other instructions, from other repositories

docs-to-pdf CLAUDE.md

Claude Code instructions for jean-humann/docs-to-pdf, covering claude development guide for docs-to-pdf, project overview, development environment setup, using mise (recommended) and install mise (if not already installed).

jean-humann/docs-to-pdf · 4,714 tokens

PDF-Writer CLAUDE.md

Instructions for galkahana/PDF-Writer, covering claude code context - pdf-writer development guide, project overview, coding standards discovered, project structure and key components.

galkahana/PDF-Writer · 1,432 tokens

autorename-pdf CLAUDE.md

Instructions for ptmrio/autorename-pdf, covering autorename-pdf, development setup, source venv/bin/activate # linux/macos, commands and ai tool integration.

ptmrio/autorename-pdf · 1,295 tokens

pdfnative-mcp AGENTS.md

Instructions for Nizoka/pdfnative-mcp, covering agents.md — pdfnative-mcp, 1. tool catalogue (28 tools), 2. decision tree, 3. token-frugal responses and 4. output modes & environment.

Nizoka/pdfnative-mcp · 10,137 tokens

docsift CLAUDE.md

Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.

anishmoncivarghese/docsift · 718 tokens

notebooklm-wiki-pipeline CLAUDE.md

Instructions for capitalparser/notebooklm-wiki-pipeline, covering 05notebooklmwikipipeline — 프로젝트 컨텍스트, 핵심 문제, 아키텍처, 도구 구성 and 슬래시 커맨드.

capitalparser/notebooklm-wiki-pipeline · 571 tokens