docs

A documentation tool that maps a codebase, remembers that map, and uses it to create, update, and check project documents.

In plain words
What is it for?
Use it to maintain architecture diagrams, API or interface references, and project overview files such as READMEs.
Why use it?
It helps keep documentation accurate as code changes, reducing outdated descriptions and repeated discovery work. It supports different project types, including web APIs, libraries, command-line tools, data pipelines, and monorepos, which are repositories containing several related projects.

Skill for Claude CodeCodex

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 skills/mountainunicorn/add/docs
Any agent
npx skills add MountainUnicorn/add --skill docs
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,078 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00020 $0.04078
Opus 5 $0.00010 $0.02039
Sonnet 5 $0.00004 $0.00816
Haiku 4.5 $0.00002 $0.00408

Measured 2d ago against content hash e2730d6587dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

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.

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.

core/skills/docs/SKILL.md · 353 lines

How it starts

The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Docs Skill v{{VERSION}}

Generate, update, and verify project documentation. Uses a discovery-first approach: the skill learns your codebase structure on first run, caches that knowledge in a manifest, and uses it for fast, accurate doc generation on every subsequent run.

Works with any project type — web APIs, libraries, CLIs, data pipelines, monorepos, or anything else.

Token economy: doc rendering is mechanical work. When sub-agent dispatch is available, delegate bulk generation (diagram emission, API doc rendering, README regen) to the fast tier per rules/model-roles.md; keep the frontier-model context for judgment — what to document, staleness calls, and review.

Overview

The Docs skill manages documentation artifacts that drift as code evolves:

  1. Discovery Manifest — Cached codebase map (entry points, types, services, architecture) that powers all other scopes
  2. Architecture Diagrams — Mermaid diagrams reflecting current flows, traced from manifest data
  3. API / Interface Documentation — Appropriate to project type: OpenAPI for web APIs, module docs for libraries, usage docs for CLIs
  4. README / CLAUDE.md — Keep project overview accurate (structure, commands, architecture)
  5. Freshness Check — Detect stale docs without modifying anything, with file-level fingerprinting

Documentation is generated from code, not written by hand. The source of truth is always the implementation. The manifest bridges the gap between raw source and generated docs.

All archetype lookup tables, the manifest schema, report formats, and configuration defaults live in ${CLAUDE_PLUGIN_ROOT}/references/docs-archetypes.md — referenced throughout as "the archetype reference".

Pre-Flight Checks

  1. Read .add/config.json
    • Load project name, stack, maturity level
    • Load architecture details (languages, frameworks, database)
    • Load docs configuration block (defaults in the archetype reference)
    • Determine project archetype (see Project Archetypes section)

Read the full file on GitHub · 353 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. 2d ago First seen · 353 lines · 20 tokens per session scan A e2730d6587dc

Subscribe to this mod's changes

docs is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 4,078 once invoked, about $0.0001 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 2026-08-30.