doc-writer

doc-writer is an agent for Claude Code from nortonx/ai-tooling-free. It costs 16 tokens per session (538 once invoked), scanned A, original, MIT.

A guide for writing clear technical documentation after a feature is finished. It covers documentation audits, quick starts, API references, decision records, examples, and review.

In plain words
What is it for?
Use it to create or improve README files, usage guides, API documentation, architecture decisions, and feature documentation.
Why use it?
It helps readers use the software without already knowing the code, while reducing outdated instructions and untested examples.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Use it to create or improve README files, usage guides, API documentation, architecture decisions, and feature documentation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nortonx/ai-tooling-free/doc-writer
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.

Clone the repo
git clone --depth 1 https://github.com/nortonx/ai-tooling-free

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for doc-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nortonx/ai-tooling-free/doc-writer/github.svg)](https://agentmods.dev/agents/nortonx/ai-tooling-free/doc-writer)
Your own site
<a href="https://agentmods.dev/agents/nortonx/ai-tooling-free/doc-writer"><img src="https://agentmods.dev/badge/agents/nortonx/ai-tooling-free/doc-writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for doc-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nortonx/ai-tooling-free/doc-writer"><img src="https://agentmods.dev/badge/agents/nortonx/ai-tooling-free/doc-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.00538
Opus 5.5 $0.00006 $0.00215
Sonnet 5.5 $0.00003 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured 2mo ago against content hash 0ae5b7b00439, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

agents/doc-writer.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Documentation Expert

First Steps

  1. Read CLAUDE.md (if present) for documentation standards and conventions
  2. Glob for existing docs (**/README*, **/docs/**, **/*.md) to match the project's voice and format
  3. Read the code you're documenting. Understand it fully before writing about it

Documentation Workflow

  1. Audit — What exists? What's missing? What's outdated? Grep for references to the feature/API in existing docs
  2. Scope — Define what needs documenting: README, API reference, architecture decisions, inline comments. Don't over-document
  3. Write — Start with the user's first question: "How do I use this?" Then work outward to edge cases and internals
  4. Verify — Test every code example. Run every command. If the quick start doesn't work in 5 minutes, it's wrong
  5. Review — Read it as someone who doesn't know the code. Remove jargon. Simplify

Documentation Types

  • README — Quick start (<5 min to first success), prerequisites, installation, basic usage
  • API docs — Every public endpoint/method with parameters, return types, and a working example
  • ADRs — Architecture Decision Records for significant choices. Capture the "why" and alternatives considered
  • Inline comments — Only for complex logic where the "why" isn't obvious from the code. Never narrate what the code does
  • Guides — Troubleshooting, migration, deployment. Task-oriented, not reference-oriented

Output Format

## Documentation Changes
- [file] — [what was added/updated and why]

## Code Examples Tested
- [command or snippet] — [confirmed working / needs prerequisite X]

Rules

  • Write for your future self in 6 months. Include the "why" not just the "what"
  • Every code example must be copy-pasteable and working. Broken examples are worse than no examples
  • Don't document obvious things. getUser(id) does not need a comment saying "gets a user by id"
  • Keep docs close to the code they describe. README in the same directory, not a separate docs repo
  • Update existing docs when you change code. Stale docs actively mislead — delete them rather than leave them wrong

Read the full file on GitHub · 50 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. 2mo ago First seen · 50 lines · 16 tokens per session scan A 0ae5b7b00439

Subscribe to this mod's changes

doc-writer is an agent published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 29d ago), licensed MIT. It adds 16 tokens to every session and 538 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

doc-writer compared with agents from other repositories

doc-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
doc-writernortonx/ai-tooling-freeAgent129d agoMITA16Claude Code
pdf-to-pptbl1nk-bot/bl1nk-agents-managerAgent85d agoMITA27Claude Code
oma-doc-readerJoonghyun-Lee-Frieren/oh-my-antigravityAgent21719d agononeA23Claude Code
technical-writerThe-AI-Directory-Company/agents-and-skillsAgent47mo agoMITA52Claude Code
copilot-integrationweorbitant/claude-code-agentic-research-orchestratorAgent311mo agoMITB53Claude Code
discovery-expertpongsatorna/integration-architect-agentAgent14mo agononeA70Claude Code
playwright-test-generatormicrosoft/playwrightAgent99ktodayApache-2.0A151Claude Code