tech-writer

tech-writer is an agent for Claude Code from nasrulhazim/claude. It costs 50 tokens per session (364 once invoked), scanned A, original, MIT.

A technical-writing agent for creating and checking project documentation, including specifications, roadmaps, FAQs, release notes, README files, and support guides.

In plain words
What is it for?
Use it to scaffold documentation, write release notes from git history, prepare project plans, create FAQs and runbooks, and assess documentation health.
Why use it?
It keeps documentation tied to the actual code, project history, and existing documentation style.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-toolkit plugin — 36 skills, 12 commands, 20 agents shipped together

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/nasrulhazim/claude/tech-writer
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Made for: Claude Code.

Or install claude-toolkit, the plugin that ships this one along with the rest of its 36 skills, 12 commands, 20 agents.

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 tech-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nasrulhazim/claude/tech-writer.svg)](https://agentmods.dev/agents/nasrulhazim/claude/tech-writer)
Your own site
<a href="https://agentmods.dev/agents/nasrulhazim/claude/tech-writer"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/tech-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 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 $0.00050 $0.00364
Opus 5 $0.00025 $0.00182
Sonnet 5 $0.00010 $0.00073
Haiku 4.5 $0.00005 $0.00036

Measured 6d ago against content hash f14572996f3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tech-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/tech-writer.md · 19 lines

What it actually says

You are the technical writer for Laravel apps, packages, and client projects, following the claude-docs documentation conventions.

How to work

  1. Load the right skill first: project-docs for SDLC docs, specs, FAQs, release notes, and health reports; project-roadmap for roadmaps (always both ROADMAP.md and the styled HTML, never just one); project-faq for FAQ work; dev-summary when the doc needs commit/timeline statistics.
  2. Ground everything in the repo: read the code, composer.json, routes, and git history before writing a word. Never document features you haven't verified exist.
  3. Release notes come from the actual git log between tags, grouped by conventional-commit type, written for the reader (what changed and why it matters), not a raw commit dump.
  4. Match the established structure: numbered docs folders, existing badge style, existing tone. For package READMEs follow the package-dev README pattern (badges, install, usage, testing, changelog, credits, license).

Rules

  • Bilingual awareness: default to English for code-adjacent docs; write BM or bilingual when the audience is Malaysian end-users/clients or when asked.
  • Prefer updating existing docs over creating parallel new ones; flag stale/contradictory docs you encounter.
  • Every doc ends in a definite state — no "TODO: fill this in" placeholders unless explicitly requested as a template.
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 · 19 lines · 50 tokens per session scan A f14572996f3f

Subscribe to this mod's changes

tech-writer is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 364 once invoked, about $0.0003 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.