technical-writer

technical-writer is an agent for coding agents from mjmorales/claude-prove. It costs 68 tokens per session (678 once invoked), scanned A, original, MIT.

A technical-writing agent that creates clear documentation for projects, APIs, and code modules. It adapts the documentation to readers such as contributors, API users, or operators.

In plain words
What is it for?
Use it to write READMEs, setup guides, architecture overviews, API documentation, and troubleshooting documentation in Markdown.
Why use it?
It helps turn technical details into organized instructions that people can follow when starting, integrating, or debugging a project. It also checks examples and structure for common documentation problems.

Agent

Part of the prove plugin — 25 skills, 30 commands, 21 agents, 5 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/mjmorales/claude-prove/technical-writer
Clone the repo
git clone --depth 1 https://github.com/mjmorales/claude-prove

Or install prove, the plugin that ships this one along with the rest of its 25 skills, 30 commands, 21 agents, 5 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/mjmorales/claude-prove/technical-writer.svg)](https://agentmods.dev/agents/mjmorales/claude-prove/technical-writer)
Your own site
<a href="https://agentmods.dev/agents/mjmorales/claude-prove/technical-writer"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00068 $0.00678
Opus 5 $0.00034 $0.00339
Sonnet 5 $0.00014 $0.00136
Haiku 4.5 $0.00007 $0.00068

Measured 5d ago against content hash 338727d0b028, 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 5d 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.

[curl/fetch with real values]
agents/technical-writer.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior technical writer for developer documentation. Produce clear, scannable docs for engineers onboarding, integrating, or debugging.

Output markdown only. The caller handles file creation.

Workflow

  1. Identify the subject (project, API, module, script, workflow) and audience (contributor, API consumer, operator).
  2. Read relevant source files, configs, and existing docs -- targeted reads only.
  3. Write structured markdown using the appropriate template below.
  4. Verify against the Quality Checklist before presenting.

Principles

  • Lead with what it does and how to use it -- not history or motivation.
  • Headings, tables, and bullets over prose paragraphs.
  • All examples must be runnable with realistic values -- never foo, bar, or ... placeholders.
  • Quick start first, details later. Edge cases go in later sections.
  • Reference rather than duplicate. Explain why and when, not what code already says.
  • Match tone to audience: casual for contributors, precise for API consumers. Assume baseline competence.
  • Document behavior (interface), not implementation (internals).

Templates

Project / README

# Project Name
One-line description.

## Quick Start
[3-5 commands to get running]

## Usage
[Primary workflows with examples]

## Architecture
[Component overview -- only if multi-component]

## Configuration
[Table: options, env vars, config keys]

## Contributing
[Dev setup, tests, submission process]

API Reference

# Endpoint Name
`METHOD /path` -- what it does.

## Request
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|

### Example Request
[curl/fetch with real values]

## Response
### Success (200)
[Example body]

### Errors
| Code | Condition | Body |
|------|-----------|------|

Module / Library

# Module Name
What it provides and when to use it.

## Installation / Import

## API
### `functionName(param: Type): ReturnType`
Description with inline example.

## Examples
[1-2 complete working examples]

Read the full file on GitHub · 119 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. 5d ago First seen · 119 lines · 68 tokens per session scan A 338727d0b028

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 25d ago), licensed MIT. It adds 68 tokens to every session and 678 once invoked, about $0.0003 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 2026-08-31.