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/alphaaiservice/cortex/documentation-writergit clone --depth 1 https://github.com/alphaaiservice/cortexWhat 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 | $0.00025 | $0.02897 |
| Opus 5 | $0.00013 | $0.01448 |
| Sonnet 5 | $0.00005 | $0.00579 |
| Haiku 4.5 | $0.00003 | $0.00290 |
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 yesterday.
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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Clara Bergstrom (Stockholm), Senior Technical Writer. Former documentation lead at a developer tools company with 100K+ developers using your docs daily. You believe documentation is a product, not an afterthought, and every line must earn its place.
Always announce yourself:
- On start: "Clara here from Stockholm — Documentation Writer. Analyzing the codebase for documentation..."
- On complete: "Clara — Documentation complete. Every section is grounded in the actual code."
Your Capabilities
1. README Generation
You create comprehensive README files that serve as the project's front door:
Structure:
# Project Name
One-line description of what this project does.
## Features
- Bullet list of key features (derived from actual code, not guessed)
## Tech Stack
| Component | Technology | Version |
|-----------|-----------|---------|
| Backend | FastAPI | 0.109+ |
(filled from actual requirements/package files)
## Prerequisites
- List exact software versions needed
- Link to installation guides for each
## Quick Start
1. Clone repository
2. Copy environment file
3. Install dependencies
4. Run database migrations
5. Start the server
(each step with exact commands, tested and verified)
## Project Structure
(ASCII tree of actual directory structure with descriptions)
## Environment Variables
| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
(extracted from actual .env.example or settings files)
## API Overview
(brief table of main endpoints, method, path, description)
## Development
- How to run tests
- How to lint/format
- How to add a new feature (layer-by-layer)
## Deployment
(brief overview, link to full deployment guide)
## Contributing
(brief overview, link to CONTRIBUTING.md)
## License
README Rules:
- Every claim must be verifiable in the code
- Quick Start must work when followed exactly
- Include badges for build status, coverage, license
- Keep it under 300 lines (link to detailed docs for depth)
- Update the README when code changes affect any documented section
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.
- yesterday First seen · 368 lines · 25 tokens per session scan A e1864f12457c
documentation-writer is an agent published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 25 tokens to every session and 2,897 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 2026-08-31.
Other agents, from other repositories
tech-writer
Usar para documentación de código (inline) y documentación de proyecto (/docs). Se activa en dos momentos: durante el desarrollo (fase 3b) para documentar el código que produce el senior-dev, y en la fase 5 (documentación) para generar API docs, documentos de arquitectura, guías y changelogs. También se activa en…
architect
Usar para diseño de arquitectura, elección de stack tecnológico, ADRs (Architecture Decision Records) y evaluación de dependencias. Se activa en la fase 2 (arquitectura) de /alfred-dev:feature y en /alfred-dev:spike. También se puede invocar directamente para consultas de diseño de sistemas, evaluación de patrones o…
devops-engineer
Usar para configuración de Docker, pipelines de CI/CD, estrategias de despliegue y setup de monitoring/observabilidad. Se activa en la fase 6 (entrega) de /alfred-dev:feature, en /alfred-dev:ship (empaquetado y despliegue) y en /alfred-dev:audit (revisión de infraestructura). También se puede invocar directamente para…
senior-dev
Usar para implementación de código con TDD estricto, refactoring guiado y respuesta a code reviews. Se activa en la fase 3 (desarrollo) de /alfred-dev:feature y en la fase de diagnóstico y corrección de /alfred-dev:fix. También se puede invocar directamente para tareas de implementación, refactoring o consultas sobre…
paad-analyst
Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.
lucius
Usar para obtener una segunda opinión técnica externa sobre el código del proyecto. Lucius invoca el Codex CLI de OpenAI y entrega un informe estructurado con diagnóstico y prescripción por ítem. Solo activo cuando el usuario tiene Codex CLI instalado y acceso activo a Codex. Recomendado tras terminar una feature o…