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/jonase47/ccprWrote 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/commands/jonase47/ccpr/p2-poc)<a href="https://agentmods.dev/commands/jonase47/ccpr/p2-poc"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p2-poc/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/commands/jonase47/ccpr/p2-poc"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p2-poc.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 | $0.00000 | $0.01199 |
| Opus 5.5 | $0.00000 | $0.00480 |
| Sonnet 5.5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
p2-poc 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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p2-poc – Technical Proof of Concept
Builds a minimal technical Proof of Concept for the riskiest technical area of the project. The goal is not a finished feature but proof that the planned approach fundamentally works – before investing in architecture and implementation.
Argument: $ARGUMENTS = [Technical risk area, e.g. "real-time synchronisation", "AI integration", "payment API"]
If provided: Build the PoC specifically for the named risk area. If not provided: Read ASSUMPTIONS.md and identify the most technically risky area yourself. If ASSUMPTIONS.md is missing, ask for the biggest technical risk of the project.
Execution
1. Read Context
Read the following files (if available):
- ASSUMPTIONS.md (technical Assumptions with highest priority)
- CONCEPT.md / FEATURES.md (What should the system do?)
- DISCOVERY.md (Feasibility assessment from Phase 0)
2. Delegate to system-architekt Agent (Lead)
Delegate PoC planning and technical evaluation to the system-architekt agent:
Plan and evaluate a Proof of Concept for the following risk area: $ARGUMENTS Context: [Insert relevant technical Assumptions from ASSUMPTIONS.md and requirements from CONCEPT.md]
Work out:
A. Define PoC Scope
- What exactly should the PoC prove? (1 clear question that must be answered)
- What is deliberately NOT part of the PoC? (Scope Boundary)
- Success criterion: How do we know the PoC is successful?
B. Choose Technical Approach
- Which technology/library/API should be tested?
- What alternatives exist and why is this approach preferred?
- Which dependencies (external APIs, SDKs, services) are needed?
C. Assessment after PoC Execution
- ✅ Feasible: Approach works, recommendation for architecture
- ⚠️ Feasible with limitations: What needs to be adjusted?
- ❌ Not feasible: Which alternative approach is recommended?
3. Delegate to senior-developer Agent (Support)
Delegate PoC implementation to the senior-developer agent:
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.
- 1mo ago Changed 621d6f2267e3
- 1mo ago Changed · +3 lines a7eb85af300f
- 1mo ago First seen · 103 lines · 0 tokens per session scan A f68d22940ade
p2-poc is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,199 tokens. 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 commands, from other repositories
stats
Show real token usage, delegation rate, and actual savings for the current Hydra session (parses Claude Code session JSONL — no AI estimation).
map
View, rebuild, or query the codebase dependency map.
design-intent
Guided UI/visual development with structured exploration, architecture design, and quality review.
ralph
Ralph autonomous development loop with fresh context per iteration.
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
double-check
Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.