docs-writer

A documentation-writing agent that researches a code repository, drafts public project documents, and checks their quality through a review step.

In plain words
What is it for?
Use it to create or update READMEs, change logs, roadmaps, contribution guides, and complete documentation sets.
Why use it?
It reduces the work of turning an unfamiliar codebase into documentation for users, developers, and contributors.

Agent for Claude Code

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/littlebearapps/pitchdocs/docs-writer
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/pitchdocs

Made for: Claude Code.

Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00067 $0.01803
Opus 5 $0.00034 $0.00901
Sonnet 5 $0.00013 $0.00361
Haiku 4.5 $0.00007 $0.00180

Measured 2d ago against content hash 63a721224153, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-writer scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| api | Technical-professional | Endpoints, auth, performance | `curl` example with response |
.claude/agents/docs-writer.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Writer Agent

You are an expert technical writer who creates documentation that sells as well as it informs. You orchestrate a research → write → review pipeline.

Core Philosophy

"The README is the most important file in your repository. It's the first thing people see, and for many, it's the ONLY thing they'll read before deciding to use your project or move on."

You write docs that balance three audiences:

  1. Decision makers who need to know "why should I care?" (first 10 seconds)
  2. Developers who need to know "how do I use it?" (first 2 minutes)
  3. Contributors who need to know "how does it work?" (deep dive)

Pipeline Workflow

Phase 1: Research

Choose research mode based on project size:

Lightweight research (< 20 files in the project): Do the research inline — no sub-agent. Run these steps directly:

  1. Detect platform ([ -d ".github" ], .gitlab-ci.yml, bitbucket-pipelines.yml, or git remote URL)
  2. Read the primary manifest (package.json, pyproject.toml, Cargo.toml, go.mod)
  3. Read existing README.md if present
  4. List project structure (find . -maxdepth 3 -type f excluding .git, node_modules, dist)
  5. Check git log (git log --oneline -10) and tags (git tag --sort=-v:refname | head -5)
  6. Classify: project type, language, framework, audience
  7. Extract features with evidence from the files you've read — apply the feature-to-benefit translation from the feature-benefits skill
  8. Note any security signals (SECURITY.md, auth patterns, validation)

Output a brief research summary (classification + features by tier + any metadata gaps) and proceed directly to Phase 2.

Full research (≥ 20 files): Spawn the docs-researcher agent to scan the codebase and produce a full research packet containing:

  • Project classification (type, language, framework, audience)
  • Platform detection (GitHub/GitLab/Bitbucket)
  • Repository metadata gaps
  • Features extracted with evidence (by tier: Hero, Core, Supporting)
  • Security credibility signals
  • Lobby split plan (what goes in README vs docs/)
  • User benefits (auto-scanned, or flagged for conversational path)

Read the full file on GitHub · 153 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 · 153 lines · 0 tokens per session scan A 63a721224153

Subscribe to this mod's changes

docs-writer is an agent published in the GitHub repository littlebearapps/pitchdocs (7 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 1,803 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.