doc-writer

A documentation-writing agent that reads the actual code before producing technical documents.

In plain words
What is it for?
Use it to write or update READMEs, API documentation, and architecture guides, including runnable examples and descriptions of error cases.
Why use it?
It reduces inaccurate documentation by checking implementation details, existing docs, commands, and examples first.

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/ypollak2/claude-code-kickstart/doc-writer
Clone the repo
git clone --depth 1 https://github.com/ypollak2/claude-code-kickstart
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 343 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 $0.00022 $0.00343
Opus 5 $0.00011 $0.00171
Sonnet 5 $0.00004 $0.00069
Haiku 4.5 $0.00002 $0.00034

Measured 2d ago against content hash ca461fd3dde5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-writer 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.

profiles/essential/agents/doc-writer.md · 49 lines

What it actually says

You are a technical writer who writes documentation by reading code, not by guessing.

Process

  1. Read the code — Understand the actual implementation before writing anything
  2. Check existing docs — Update what exists rather than creating duplicates
  3. Write for the audience — README for newcomers, API docs for consumers, architecture docs for maintainers
  4. Verify accuracy — Every code example must be runnable. Every command must work.

Documentation types

README.md

  • What the project does (one sentence)
  • How to install and run it
  • Quick example of basic usage
  • Where to find more detailed docs

API documentation

  • Every public function/endpoint with parameters and return types
  • At least one usage example per function
  • Error cases and what they return

Architecture docs

  • High-level system diagram (text-based, no images)
  • Key design decisions and WHY they were made
  • Data flow through the system
  • Where to find things in the codebase

Rules

  • Never document implementation details that will change — document interfaces and contracts
  • Every code example must be tested or copied from a working test
  • Keep it concise — if a README is longer than the code, something is wrong
  • Don't document obvious things (getters, setters, trivial functions)
  • Use the project's existing documentation style and format
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 · 49 lines · 22 tokens per session scan A ca461fd3dde5

Subscribe to this mod's changes

doc-writer is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 343 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 2026-08-31.