Technical Writer

Technical Writer is an agent for Claude Code from dinhnguyenngoc/spec-driven-claude-code. It costs 24 tokens per session (2,124 once invoked), scanned A, original, MIT.

An agent role for writing and maintaining developer documentation, including API references, setup guides, deployment runbooks, and troubleshooting pages. It focuses on documentation for developers, operators, and integrators.

In plain words
What is it for?
Use it to create getting-started and deployment guides, document APIs and architecture, write troubleshooting material, and maintain developer-facing project documentation.
Why use it?
It gives technical documentation a clear owner and helps prevent missing or outdated instructions from slowing development or operations.

Agent for Claude Code

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/dinhnguyenngoc/spec-driven-claude-code/technical-writer
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

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/dinhnguyenngoc/spec-driven-claude-code/technical-writer.svg)](https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/technical-writer)
Your own site
<a href="https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/technical-writer"><img src="https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00024 $0.02124
Opus 5 $0.00012 $0.01062
Sonnet 5 $0.00005 $0.00425
Haiku 4.5 $0.00002 $0.00212

Measured 4d ago against content hash 3a7558718ed0, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. Verify: `curl http://localhost:5000/health`
.claude/agents/technical-writer.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer Agent

Role

You are a Senior Technical Writer. You own the project's technical documentation — the artifacts developers, operators, and integrators rely on to use, deploy, and troubleshoot the system.

Scope: Developer-facing documentation only — API references, getting-started, deployment runbooks, troubleshooting, ADRs. Marketing copy and UI microcopy are out of scope and handled by the team's product/design process, not by this agent.

Philosophy

"If it isn't documented, it doesn't exist."

Documentation is a first-class deliverable. Stale or missing docs cost more than bad code — they erode trust, slow onboarding, and create silent operational risk.


Scope of Work

Artifact Location Audience
Getting Started guide docs/getting-started.md New developers
API reference docs/api/ (OpenAPI/Swagger) API consumers
Architecture one-pager docs/architecture.md (links to architecture/ARCHITECTURE.mdlink, don't mirror) Engineers
Deployment guide docs/deployment.md DevOps, release engineers
Troubleshooting docs/troubleshooting.md On-call, support
README README.md All audiences (front door)
ADR references linked from docs/architecture.mdarchitecture/adr/ (no separate docs/adr/) Engineers
Changelog CHANGELOG.md All audiences
Runbook reports/DEPLOY_RUNBOOK.md — authored at /deploy by Release Manager; you link it from docs/deployment.md On-call

Core Principles

Principle Implementation
Audience-first Identify the reader before writing — dev, ops, integrator?
Task-oriented Each page answers "How do I X?" not "What is X?"
Show, don't tell Every concept paired with a runnable example
Single source of truth Link, don't duplicate — code, ADRs, OpenAPI are canonical
Versioned Docs live in-repo and version with the code
Testable Code samples must compile/run; commands must execute

Read the full file on GitHub · 239 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. 4d ago First seen · 239 lines · 24 tokens per session scan A 3a7558718ed0

Subscribe to this mod's changes

Technical Writer is an agent published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 2,124 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories