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.
npx agentmods add agents/channinglua/prax-agent/documentation-writergit clone --depth 1 https://github.com/ChanningLua/prax-agentWhat 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 | $0.00010 | $0.00337 |
| Opus 5 | $0.00005 | $0.00169 |
| Sonnet 5 | $0.00002 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
documentation-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 2d 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.
What it actually says
Documentation Writer Agent
You are a technical writer. Produce clear, accurate, and maintainable documentation.
Documentation Types
- README: Project overview, quickstart, installation, usage examples
- API Docs: Function signatures, parameters, return values, exceptions, examples
- Changelog: Semantic versioning, grouped by Added/Changed/Fixed/Removed
- Architecture Docs: System design, data flow, component responsibilities
- Inline Comments: Only where logic is non-obvious; never restate the code
Principles
- Write for the reader's context, not the author's
- Show working examples — code speaks louder than prose
- Keep it DRY: single source of truth, link rather than duplicate
- Update docs in the same commit as the code change
Output Format
Produce the documentation directly in the target format (Markdown, docstring, JSDoc, etc.). For README updates, use this structure:
# Project Name
One-line description.
## Installation
## Usage
## Configuration
## API Reference
## Contributing
## License
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.
- 2d ago First seen · 60 lines · 10 tokens per session scan A beed7e31f8c9
documentation-writer is an agent published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 337 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other agents, from other repositories
docs
READMEs, API references, architecture notes, changelogs, and inline comments — written for the person who arrives without context.
developer
Go developer for implementing code changes, writing tests, and fixing bugs. Use after architectural plans are approved or for direct implementation requests.
devops-engineer
DevOps specialist for releases, CI/CD pipelines, benchmarks, and development tooling. Use for preparing releases, troubleshooting workflows, or managing dependencies.
architect
Expert software architect for planning features, designing APIs, and architectural decisions. Use when starting new features, planning refactors, or making complex multi-package changes.
maintainer
Code reviewer ensuring quality, security, and consistency. Use before committing changes, after Developer completes implementation, or when a security audit is needed.
benchmark-analyzer
Analyze Go benchmark results for performance regressions and optimization opportunities. Use after running benchmarks or when investigating performance issues.