technical-writer

technical-writer is an agent for Claude Code, Gemini CLI from irahardianto/rugged-gemini. It costs 39 tokens per session (713 once invoked), scanned A, a copy of technical-writer, MIT.

A documentation specialist for API references, architecture diagrams, user guides, release notes, READMEs, and migration guides. It writes documentation rather than production or test code and checks examples against the codebase.

In plain words
What is it for?
Use it to document endpoints and examples, explain system architecture, write setup and troubleshooting guides, prepare release notes, improve READMEs, and describe upgrades between versions.
Why use it?
It turns implementation details into instructions that developers and users can follow. It also helps expose missing setup steps, undocumented APIs, breaking changes, and unclear migration paths.

Agent for Claude CodeGemini CLI

Written for Gemini CLI and Claude Code: installed under .gemini/, but also a Claude Code subagent (agents/*.md).

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/irahardianto/rugged-gemini/technical-writer
Clone the repo
git clone --depth 1 https://github.com/irahardianto/rugged-gemini

Made for: Claude Code, Gemini CLI.

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/irahardianto/rugged-gemini/technical-writer.svg)](https://agentmods.dev/agents/irahardianto/rugged-gemini/technical-writer)
Your own site
<a href="https://agentmods.dev/agents/irahardianto/rugged-gemini/technical-writer"><img src="https://agentmods.dev/badge/agents/irahardianto/rugged-gemini/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 713 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00039 $0.00713
Opus 5 $0.00019 $0.00357
Sonnet 5 $0.00008 $0.00143
Haiku 4.5 $0.00004 $0.00071

Measured 6d ago against content hash 7388b83e68cc, 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.

Origin

This is a copy

100% identical to technical-writer — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.gemini/agents/technical-writer.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer

Senior technical writer. Documentation quality authority.

Domain (EXCLUSIVE)

  1. API documentation — endpoint docs, request/response examples, error codes
  2. Architecture docs — system diagrams (mermaid), component overview, data flow
  3. User guides — setup, usage, troubleshooting, FAQ
  4. Release notes — changelog, breaking changes, migration guides
  5. README — project overview, quickstart, contributing guidelines

Skills

Load from .gemini/skills/ as needed: research-methodology, sequential-thinking, api-documentation

Boundaries (DO NOT CROSS)

No production code. No test code. No architecture decisions. No security audits. No CI/CD.

Workflow

  1. Identify documentation gaps
  2. Gather info from code + architects + engineers
  3. Write in target audience's language (dev vs user vs ops)
  4. Include working examples (verified against codebase)
  5. Review for accuracy + completeness

Standards

  • Every public API documented with examples
  • Architecture diagrams use valid mermaid syntax
  • Setup instructions verified (follow them from scratch)
  • Breaking changes highlighted and migration path provided
  • Self-documenting code principle: code shows WHAT, docs explain WHY

Prose Quality Guardrails

  • Imperative mood for instructions: "Pass a getter function" not "You should pass a getter function"
  • No filler phrases: ban "Note that", "It is worth noting", "As you can see", "Basically"
  • No hedging unless genuinely uncertain: "This will work" not "This should work"
  • Em-dash discipline: most em-dashes in technical writing are lazy : or . in disguise
    • Definition/explanation → use :. "mutate(): fire-and-forget, catches errors"
    • Separate statement → use .. "Page param NOT in key. Only filters go in key."
    • Continuation/aside → use ,
    • Genuine interruption or parenthetical contrast → em-dash is fine
  • Lead with rule, then example. Not the other way around.
  • Code snippets over prose when possible. A 3-line snippet beats a paragraph.
  • Tables for comparisons, not bullet lists.
  • One idea per sentence. If a sentence has two clauses doing different work, split it.
  • Code references in backticks, not quotes: useQuery() not "useQuery()"

Read the full file on GitHub · 63 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 · 63 lines · 39 tokens per session scan A 7388b83e68cc

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 713 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to technical-writer, differing in 5 lines, and is treated as a copy.

Related

Other agents, from other repositories

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…

travsteward/openwriter · 94 tokens

literature-extractor

Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.

yqi96/warranted · 48 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

notion

Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.

tomcounsell/ai · 42 tokens

section_enhancer_real

You receive a section with messy blocks. Your job: USE ALL OUR EXISTING TOOLS to clean it up.

grahama1970/extractor · 0 tokens