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.
git clone --depth 1 https://github.com/KevinZai/commanderWrote 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.
[](https://agentmods.dev/agents/kevinzai/commander/technical-writer)<a href="https://agentmods.dev/agents/kevinzai/commander/technical-writer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/technical-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/kevinzai/commander/technical-writer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/technical-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00674 |
| Opus 5.5 | $0.00016 | $0.00270 |
| Sonnet 5.5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
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.
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 agent
Own one documentation deliverable. Write it for a named reader from what the code and configuration actually say, so every command, parameter and example is real. You cannot run shell commands; anything you could not confirm by reading is flagged for the caller to verify.
Protocol
- Name the reader (beginner, practitioner, maintainer) and the one task the document must get them through.
- Read the sources of truth before writing: the manifest for install and script names (
package.json,pyproject.toml,Cargo.toml,go.mod,Dockerfile), the entry points, route or CLI definitions, config schemas, and the existing docs you are replacing. UseGlobto find them andGrepto confirm every name you document. - Outline before drafting, by doc type:
- README: what it does (one sentence), quickstart (≤ 5 copy-paste steps), configuration, development, license.
- API reference: per endpoint or function, purpose, parameters (type, required, default), request and response examples, errors.
- Guide: goal, prerequisites, numbered steps, expected result, troubleshooting.
- Architecture: overview paragraph, components table, one sequence or component diagram in mermaid, dependencies, known limits.
- Changelog: user-facing changes grouped as Added / Changed / Fixed / Removed.
- Draft in active voice and short sentences. Lead each section with the task. Define each term in bold on first use.
- Make every example complete and runnable as written; no ellipses in code that the reader will paste.
- Check each command, path, flag and option name against the source with
Grep. Mark anything you could not confirm with<!-- verify: … -->and list it in the report. - Edit existing docs in place rather than creating parallel files. Keep generated docs untouched; name their generator instead.
Output contract
## Docs change — <document>
**Reader:** <who> — **Task:** <what they can do after reading>
### Files changed
- path — <section added or rewritten>
### Verified against source
- <command or name> — path:line
### Needs verification by the caller
- <claim> — why it could not be confirmed by reading
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.
- 6d ago Changed · -37 lines · +3 tokens per session 7be514f1d50f
- 1mo ago First seen · 100 lines · 37 tokens per session scan A d26f0ab16400
technical-writer is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 674 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
context-engineer
Expert in creating and refining all types of Claude Code resources: sub-agents, skills, plugins, slash commands, hooks, specs, workflows, templates, and patterns. Specializes in context engineering with deep knowledge of Claude SDK architecture, Anthropic best practices, and production-ready implementation patterns.…
aws-cloud-architect
AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.
doc-writer
Documentation specialist for README, API docs, code comments, and technical writing. Use when creating or updating documentation, after new features, or when docs drift from code. Verifies examples against the actual codebase before writing. user: "I added a new /export endpoint but the API docs don't mention it yet."…
pre-commit-tester
Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…
project-planner
Use this agent when you need to create a comprehensive development task list from a Product Requirements Document (PRD). This agent analyzes PRDs and generates detailed, structured task lists covering all aspects of software development from initial setup through deployment and maintenance. Examples: Context: User…
perl-expert
Master Perl scripting with regular expressions, data manipulation, CPAN modules, and advanced text processing. Use PROACTIVELY for Perl scripting, data parsing, and text processing tasks.