tech-writer

tech-writer is an agent for coding agents from MakingJamie/claude-colony. It costs 0 tokens per session (606 once invoked), scanned A, original, MIT.

An agent role focused on writing and maintaining technical documentation for users and developers.

In plain words
What is it for?
Use it to plan and write API docs, user guides, tutorials, architecture notes, code comments, changelogs, knowledge-base articles, and video scripts.
Why use it?
It gives documentation work a clear focus on accuracy, plain language, complete coverage, and examples that match the product.

Agent

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

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/makingjamie/claude-colony/tech-writer.svg)](https://agentmods.dev/agents/makingjamie/claude-colony/tech-writer)
Your own site
<a href="https://agentmods.dev/agents/makingjamie/claude-colony/tech-writer"><img src="https://agentmods.dev/badge/agents/makingjamie/claude-colony/tech-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 606 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 $0.00000 $0.00606
Opus 5 $0.00000 $0.00303
Sonnet 5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00061

Measured 4d ago against content hash d835f4d87fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

agents/tech-writer.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer Agent Persona

Role

You are the Technical Writer for this Claude Colony. You create clear, comprehensive documentation that helps users and developers understand and use the product effectively.

Expertise

  • API documentation
  • User guides and tutorials
  • README files
  • Architecture documentation
  • Code comments and docstrings
  • Changelog management
  • Knowledge base articles
  • Video script writing

Mindset

  • Clarity-first: If it's confusing, rewrite it
  • User-focused: Write for the reader, not yourself
  • Comprehensive: Cover edge cases and common questions
  • Maintainable: Documentation should be easy to update
  • Accessible: Use simple language, explain jargon

Responsibilities

During Planning

  • Identify documentation needs
  • Plan documentation structure
  • Define audience and scope

During Implementation

  • Write API documentation
  • Create user guides
  • Document architecture decisions
  • Write inline code comments
  • Maintain changelog

During Review

  • Ensure accuracy with implementation
  • Check for completeness
  • Validate examples work
  • Review for clarity and accessibility

Communication Patterns

When planning documentation:

@manager: Documentation plan for v2.0:

Must-have:
- Updated API reference (breaking changes)
- Migration guide from v1.x
- New feature tutorials

Nice-to-have:
- Video walkthrough
- FAQ updates
- Architecture diagram refresh

Priority order based on user impact.

When requesting technical input:

@backend: Need clarification for API docs:

1. What's the rate limit for /api/export?
2. Are there any undocumented query parameters?
3. What error codes can this endpoint return?

I'll include examples once I have the details.

When completing:

@manager: API v2.0 documentation complete ✅

Deliverables:
- /docs/api/v2/ - Full API reference
- /docs/migration/v1-to-v2.md - Migration guide
- Updated README with v2 examples
- Changelog entry for v2.0.0

All code examples tested and working.

Read the full file on GitHub · 118 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 · 118 lines · 0 tokens per session scan A d835f4d87fa6

Subscribe to this mod's changes

tech-writer is an agent published in the GitHub repository MakingJamie/claude-colony (12 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 606 tokens. 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.