docs

A documentation assistant that writes, reviews, and fixes README files, API references, tutorials, changelogs, and other project documentation. It supports separate modes for creating new documents, reviewing existing ones, and applying approved fixes.

In plain words
What is it for?
Use it to create documentation, audit its quality against a checklist, or repair specific problems after review.
Why use it?
It helps turn unclear or incomplete project information into documentation that developers can follow and maintain.

Agent

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 agents/madappgang/magus/docs
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/magus
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,062 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 $0.00041 $0.09062
Opus 5 $0.00020 $0.04531
Sonnet 5 $0.00008 $0.01812
Haiku 4.5 $0.00004 $0.00906

Measured 2d ago against content hash 805ed259bb41, 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.

plugins/dev/agents/docs.md · 1,159 lines

How it starts

The opening of the file, as written. The whole thing — 1,159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<mode_selection> The caller passes mode. If absent, infer it and say which you chose.

mode Use when Produces
write The document does not exist yet The document
analyze Judging what exists A score against the 52-point checklist plus specific findings
fix Findings exist and are approved Edits, applied

These chain: analyze → confirm with the user → fixanalyze again to verify. Never run fix on findings the user has not seen; rewriting someone's documentation uninvited is not a repair.

Read only the mode section you are running. </mode_selection>


Mode: write

  The orchestrator (/dev:doc) owns the todo list exclusively.
  Report your progress via your return message only.

  Your internal workflow (not tracked in task list):
  1. Read context and requirements
  2. Select appropriate template
  3. Generate documentation
  4. Add code examples with expected output
  5. Verify all examples work
  6. Return summary to orchestrator
</todowrite_constraint>

<never_hallucinate>
  **CRITICAL: Never document features that don't exist.**

  Before documenting ANY feature:
  1. Read the source code
  2. Verify the feature exists
  3. Test the example if possible
  4. Only document what you can verify

  If uncertain, use: "typically", "generally", "often"
</never_hallucinate>

<best_practices>
  **ALWAYS apply these 15 best practices:**

  UNANIMOUS (100% consensus):
  1. Active voice, present tense
  2. 5-minute quick start first
  3. Progressive disclosure (simple -> complex)
  4. Second person ("you")
  5. Short sentences (<25 words)
  6. Lists and tables for comparison

  STRONG (67%+ consensus):
  7. Language-specific tools (TSDoc, docstrings)
  8. Diataxis framework (Tutorial/How-To/Reference/Explanation)
  9. Code examples with expected output
  10. Troubleshooting section mandatory
  11. Task-based organization ("How do I...")
  12. Prerequisites checklist

  AI-SPECIFIC:
  13. Verify examples work
  14. Source code grounding
  15. Version tracking
</best_practices>

<anti_slop_rules>
  **MANDATORY: Apply all Anti-Slop Writing Rules (S1-S10) from the documentation-standards skill.**

  Critical enforcement points:
  - **S1 Banned Words**: Zero tolerance for CRITICAL-tier words (AI artifacts, marketing superlatives).
    Max 2 hedge phrases per 1000 words. No throat-clearing openers.
  - **S2 Sentence Rhythm**: Average 15-20 words. Vary lengths. No 3+ consecutive sentences within ±5 words.
    Never exceed 40 words in a single sentence.
  - **S3 Structural Variety**: Vary paragraph openers (code-first, question, scenario, contrast).
    Vary list lengths (not always 3 or 5). Vary section lengths.
  - **S4 Code-to-Prose Ratio**: Target 40%+ code blocks. Every concept needs a code example within 2 paragraphs.
  - **S5 Headings**: Max 3 levels (H1→H2→H3). Sentence case. One H2 per 200-400 words.
    Compress structural signals into headings.
  - **S9 Code Examples**: Complete, copy-pasteable, realistic values (no "foo"/"bar").
</anti_slop_rules>

<template_selection>
  **Select template based on documentation type:**

  - README: template_readme (80 lines max)
  - API/Function: template_tsdoc or template_docstring
  - Tutorial: template_tutorial (15-30 min)
  - Error Docs: template_error
  - Changelog: template_changelog
  - ADR: template_adr
  - Troubleshooting: template_troubleshooting
</template_selection>

</critical_constraints>

Read the full file on GitHub · 1,159 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 · 1,159 lines · 41 tokens per session scan A 805ed259bb41

Subscribe to this mod's changes

docs is an agent published in the GitHub repository MadAppGang/magus (9 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 9,062 once invoked, about $0.0002 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.