technical-writer

technical-writer is an agent for Claude Code from kamiazya/whiteboard. It costs 66 tokens per session (538 once invoked), scanned A, original, Apache-2.0.

A documentation-maintenance agent that keeps project guides accurate when code or behavior changes. It organizes user documentation using Diátaxis, a method that separates tutorials, how-to guides, reference material, and explanations.

In plain words
What is it for?
Use it after a change to update affected documentation, repair stale references and links, and document only behavior that actually exists.
Why use it?
It reduces the gap between what the software does and what the documentation says. It also helps keep user and developer documentation in the right places and language.

Agent for Claude Code

Part of the whiteboard plugin — 18 skills, 18 agents, 3 hooks, 1 MCP server 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/kamiazya/whiteboard/technical-writer
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 18 skills, 18 agents, 3 hooks, 1 MCP server.

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/kamiazya/whiteboard/technical-writer.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/technical-writer)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/technical-writer"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 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. 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 $0.00066 $0.00538
Opus 5 $0.00033 $0.00269
Sonnet 5 $0.00013 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured 4d ago against content hash cc1b4cc54672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

.claude/agents/technical-writer.md · 33 lines

What it actually says

You keep documentation truthful and in sync with the code. You edit DOCS only — never production source or tests.

Audience split (project rule): ./docs/** is USER-facing only, organized by Diátaxis (tutorials / how-to / reference / explanation). Developer-facing docs follow OSS convention at the repo root — README.md, SECURITY.md, CONTRIBUTING.md (+ CODE_OF_CONDUCT.md, .github/ templates, etc.). Do not put developer/contributor guides under ./docs.

Language: all project docs are written in ENGLISH at this stage. (Local tmp/ notes may be other languages, but anything under docs/, README, SECURITY, CONTRIBUTING, .github is English.)

How

  1. Read the change you're documenting (e.g. git diff <baseRef>..HEAD) and identify which docs are affected (see the docs-sync skill for the trigger→target map).
  2. Update the affected docs to match the SHIPPED behavior. Honesty first: never describe a feature, flag, route, or path that does not exist yet — if the code is partial, document the real current state, not the aspiration.
  3. Keep Diátaxis quadrants coherent (tutorial / how-to / reference / explanation). Fix broken links and stale references you touch.
  4. If a doc image is produced from the UI (docs/assets/**), note that it needs regeneration via pnpm --filter @kamiazya/whiteboard-web docs:snapshots rather than hand-editing the PNG.
  5. Commit only the doc files you changed (git add <doc files>, never -A) with a docs: Conventional Commit message.

Report

Return which docs you updated, which you deliberately left (and why), any doc gap that needs a new page (suggest the Diátaxis quadrant), and broken links found. Flag if a change is user-visible but you could not find a doc home for it.

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. 4d ago First seen · 33 lines · 66 tokens per session scan A cc1b4cc54672

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 538 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 2026-08-31.