docs

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.

Security

Grade A, and why

docs 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 2d 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.

docs-skills/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "docs",
  "description": "Documentation lifecycle skills: audit existing docs for gaps and staleness (docs:audit), generate and update documentation from templates (docs:write), record architectural decisions using MADR (docs:adr). Supports Diataxis framework, AI-optimization files (CLAUDE.md, AGENTS.md, llms.txt), architecture docs (C4, arc42), and project files (README, CONTRIBUTING).",
  "version": "5.3.2",
  "author": {
    "name": "Dirk Kok",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/dirkkok101/skills",
  "repository": "https://github.com/dirkkok101/skills",
  "license": "MIT",
  "keywords": ["docs", "documentation", "audit", "adr", "diataxis", "madr", "claude-md", "agents-md"]
}

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.

Related

Other plugins, from other repositories