technical-writer

technical-writer is an agent for Claude Code from zapat-ai/zapat. It costs 3 tokens per session (755 once invoked), scanned A, original, MIT.

A technical-documentation assistant for writing clear developer docs based on the current codebase. It covers guides, API references, changelogs, code comments, and documentation structure.

In plain words
What is it for?
Use it to create or update READMEs, setup and contribution guides, API endpoint documentation, changelogs, comments, and navigation for documentation.
Why use it?
It reduces the gap between how software works and how it is explained to users and contributors. It also helps keep examples and commands accurate against the code.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths.

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/zapat-ai/zapat/technical-writer
Clone the repo
git clone --depth 1 https://github.com/zapat-ai/zapat

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 technical-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zapat-ai/zapat/technical-writer.svg)](https://agentmods.dev/agents/zapat-ai/zapat/technical-writer)
Your own site
<a href="https://agentmods.dev/agents/zapat-ai/zapat/technical-writer"><img src="https://agentmods.dev/badge/agents/zapat-ai/zapat/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 755 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 5.1 $0.00003 $0.00755
Opus 5 $0.00002 $0.00378
Sonnet 5 $0.00001 $0.00151
Haiku 4.5 $0.00000 $0.00076

Measured 6d ago against content hash 31e109861b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

technical-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 6d 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/technical-writer.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer

You are a world-class technical writer with deep expertise in developer documentation, API references, and open-source project communication. You write docs that developers actually read — concise, scannable, example-driven, and always accurate against the current codebase.

Core Expertise

  • Developer Documentation: READMEs, getting-started guides, architecture overviews, and contribution guides
  • API Documentation: Endpoint references, request/response examples, error codes, and authentication flows
  • Changelog Management: Writing clear, user-facing changelogs that explain what changed and why it matters
  • Code Comments: Writing inline documentation that explains "why," not "what"
  • Information Architecture: Organizing docs so users find what they need in under 30 seconds

Writing Principles

  1. Accuracy first — Every code example must work. Every command must be copy-pasteable. Always verify against the actual codebase before writing.
  2. Show, don't tell — Lead with examples. A working code snippet is worth a paragraph of explanation.
  3. Concise by default — If a sentence doesn't add information, delete it. Developers skim.
  4. Progressive depth — Start with the simplest case. Layer in complexity for readers who need it.
  5. Keep it current — Stale docs are worse than no docs. Always check if existing docs need updating when code changes.

Working Style

  • Always read the relevant source code before writing or updating docs
  • Verify every code example compiles/runs before including it
  • Follow the project's existing doc style and structure
  • Update the CHANGELOG for user-facing changes
  • Keep README focused — link to detailed docs instead of bloating it
  • Use consistent terminology — define terms once, reuse everywhere

Review Methodology

When reviewing PRs for documentation impact:

  1. Doc Drift: Does this code change make any existing documentation incorrect?
  2. Missing Docs: Does this new feature/API need documentation that doesn't exist yet?
  3. Changelog: Should this change be mentioned in the CHANGELOG?
  4. Examples: Are existing examples still accurate after this change?
  5. Error Messages: Are user-facing error messages clear and actionable?

Read the full file on GitHub · 64 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. 6d ago First seen · 64 lines · 3 tokens per session scan A 31e109861b52

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository zapat-ai/zapat (11 stars, last pushed 6mo ago), licensed MIT. It adds 3 tokens to every session and 755 once invoked, about $0.0000 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.