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 instructions/jonase47/ccpr/claude-mdgit 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 | $0.06410 | $0.06410 |
| Opus 5 | $0.03205 | $0.03205 |
| Sonnet 5 | $0.01282 | $0.01282 |
| Haiku 4.5 | $0.00641 | $0.00641 |
Grade A, and why
ccpr CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Prerequisite:** Ollama server must be running (`curl -s http://localhost:11434/api/tags`). How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Preferences (local, interactive mode)
This is the shipped CCPR default. Personalise the sections below (especially Personal Context and Infrastructure) for your own setup — see README step 4. Everything from "Agent Team" onward is framework behaviour you normally keep as-is.
Language & Communication
- Communication language: English (default for CCPR distribution; adjust to your preferred language locally). Code, comments, variable names: English.
- Direct, technically precise. Explain the "why" behind decisions in logs and commit messages.
- No praise, no filler phrases ("Perfect!", "Great question!", "Excellent!"). Just do it.
- Ask when unclear instead of assuming. Interactive mode: ask one question too many rather than hallucinate.
Personal Context
Replace with your own role, background, and working preferences — the agents use this to tailor their output. The accessibility and Dark Mode lines are CCPR defaults; keep or adjust them.
- Your role and background (e.g. Product Owner, developer, founder; years of experience)
- How hands-on you are with code
- Accessibility is a high priority: use color-blind-friendly palettes (blue/orange instead of red/green) and always pair status with icon/text, never color alone
- Dark Mode is always considered
Infrastructure
Adjust to your own hosting and jurisdiction. The values below are examples reflecting a self-hosted setup.
- Pipeline runs as a Docker container (locally or on a cloud server via Coolify)
- Example target infrastructure: a self-hosted server with Gitea, Traefik, Coolify (e.g. Hetzner Cloud)
- Self-hosted is the default — managed services only when operational overhead clearly outweighs benefits
- DSGVO (GDPR) is CCPR's default compliance assumption — opt out per project with documented justification
Code Standards
- Test-Driven Development: Red → Green → Refactor
- No production code without tests
- 1 TDD cycle = 1 commit (Conventional Commits: feat/fix/refactor/docs/chore) → Details:
~/.claude/docs/PROJECT_PHASES.md - Commits in skills are authorized: When a skill prompt instructs "Commit after Fix/GREEN/REFACTOR", the commit is executed as part of the skill workflow – without a separate user prompt. The skill instruction takes precedence over the system default.
- Clean Code, SOLID where sensible, YAGNI
- Simplest solution that works
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 · 357 lines · 6,410 tokens per session scan A 0368de889f41
ccpr CLAUDE.md is an instructions file published in the GitHub repository jonase47/ccpr (1 stars, last pushed 2d ago), licensed MIT. It adds 6,410 tokens to every session, about $0.0321 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
dotskills AGENTS.md
Instructions for vincentkoc/dotskills, covering agents.md, repository purpose, mandatory contribution flow, skill standards and openai metadata defaults.
FMT-exocortex-template CLAUDE.md
Claude Code instructions for TserenTserenov/FMT-exocortex-template, covering инструкции для всех репозиториев, 1. архитектура репозиториев, 2. орз-фрактал (открытие → работа → закрытие), блокирующие правила and протокол работы (полный → memory/protocol-work.md).
asap-protocol AGENTS.md
AGENTS.md instructions for asap-protocol/asap-protocol, covering agents.md, project context, quick start, agent guidance (rules vs skills) and knowledge map.
slipway AGENTS.md
Instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.
ai-marketplace AGENTS.md
Instructions for Kong/ai-marketplace, covering skill authoring guide, what belongs here, before you create a skill, what a good skill does and layered skill design.
Agent-Harness-Kit AGENTS.md
Instructions for Eduardo-Salvador/Agent-Harness-Kit, covering agent harness kit — operational map, request-routing gate — before all harness ceremony, direct-trivial fast path, vibe fast path and context pressure and graph-only tasks.