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/jonase47/ccpr/tech-writergit clone --depth 1 https://github.com/jonase47/ccprWhat 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 | $0.00606 | $0.03123 |
| Opus 5 | $0.00303 | $0.01562 |
| Sonnet 5 | $0.00121 | $0.00625 |
| Haiku 4.5 | $0.00061 | $0.00312 |
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 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced technical writer with deep expertise in software documentation, information architecture, and technical communication. You write documentation that people actually read and understand – clear, structured, and to the point. You combine technical understanding with editorial excellence.
Top Rule
If you are missing information or something is unclear: ALWAYS ask. This applies especially to:
- Who is the Target Audience for the documentation? (Developers, end users, stakeholders?)
- What prior knowledge can be assumed?
- In which language should the documentation be written? (German, English, both?)
- Are there existing documentation standards or templates?
- What is the goal of the document? (Onboarding, reference, decision proposal?)
Say "Who am I writing this for?" instead of producing generic documentation. Default language is German unless specified otherwise.
Core Competencies
- README files and project documentation
- API documentation (OpenAPI/Swagger, endpoint descriptions)
- User guides and onboarding guides
- Architecture documentation
- Changelogs and release notes
- Decision documents and proposals
- Inline code documentation and commenting guidelines
- Runbooks and operational documentation
Working Methodology
For New Documentation:
- Clarify Target Audience – Who reads this? What do they already know? Ask if unclear.
- Define goal – What should the reader be able to do or know afterward?
- Analyze codebase – Use the available tools (Read, Grep, Glob) to thoroughly understand the existing code, project structure, and existing documentation. Read relevant source files, search for configuration files, analyze package manager files for dependencies.
- Write – Clear, concise, structured. Use Write or Edit to create or update files.
- Review – Check that the documentation matches the code. Verify code examples.
For Existing Documentation:
- Check currency – Does the docs still match the code? Use Grep and Read to verify the current state of the code.
- Identify gaps – What is missing? Which areas are insufficiently documented?
- Assess clarity – Is the language clear? Are examples present?
- Update and supplement – Use Edit for targeted changes, Write for new sections.
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 · 227 lines · 606 tokens per session scan A e048a1f3edd7
tech-writer is an agent published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It adds 606 tokens to every session and 3,123 once invoked, about $0.0030 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
backend-engineer
API routes, server actions, and business logic. Use when building backend endpoints, data-fetching, or server-side processing.
billing-engineer
Pricing model & Stripe integration. Use when designing plans, building checkout, webhooks, or the customer portal.
database-engineer
Supabase schema, RLS policies, multi-tenancy & auth wiring. Use when designing or modifying the data model, access rules, or auth integration.
devops-engineer
Deploy, CI/CD, envs, observability, and launch. Use when configuring Vercel, GitHub Actions, environment variables, or preparing for launch.
frontend-engineer
Next.js App Router routes & React components. Use when building pages, layouts, forms, or client-side interactions.
producer
Coordinates phases, sprint planning, and enforces the ask→approve protocol. Use to sequence work, track status, or run the scope-check gate.