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 commands/jonase47/ccpr/p0-problemgit 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 | $0.00000 | $0.01021 |
| Opus 5 | $0.00000 | $0.00511 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
p0-problem 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p0-problem – Problem Definition & Target Audience Identification
Defines the core problem of a project or business idea and identifies the first rough Target Audience. The result is a clear problem statement that serves as the foundation for all subsequent phases.
Argument: $ARGUMENTS = [Project idea / problem area]
If provided: Use as the starting point for the problem analysis. If not provided: Ask the user for the project idea or problem area before starting. Do not make assumptions.
Execution
1. Read Context
Check whether the phase index docs/discovery/DISCOVERY.md and any existing detail files (e.g. docs/discovery/PROBLEM.md, MARKET.md, REGULATORY.md, or legacy NOTES.md) exist that can serve as input.
2. Delegate to konzeptor Agent
Delegate the main task to the konzeptor agent with the following instructions:
Analyse the following problem area: $ARGUMENTS
Work out:
- Problem Statement (1 precise sentence: Who has what problem with what consequence?)
- Problem Deep-Dive (Why does the problem exist? What are the root causes?)
- First Target Audience Sketch (Who suffers most from this problem? 2–3 rough audience segments)
- Non-Target Groups (Who is explicitly NOT meant?)
- Open Questions (What do you still need to find out to fully understand the problem?)
Ask targeted follow-up questions if the context is insufficient.
3. Write Detail File
Write the result to docs/discovery/PROBLEM.md (overwrite if it exists). Start with this YAML frontmatter:
---
phase: P0
subskill: problem
status: active # skeleton | draft | active | frozen | archived | living
last_updated: <DD.MM.YYYY>
---
Below the frontmatter, structure the body with the headings: ## Problem Statement, ## Problem Deep-Dive, ## Target Audience Sketch, ## Non-Target Groups, ## Open Questions.
4. Update Phase Index
Update docs/discovery/DISCOVERY.md (create from the index template if missing — see ~/.claude/docs/PROJECT_PHASES.md):
- Set
**Last Updated:** <DD.MM.YYYY>. - In the Detail Files table: ensure a row exists for
[PROBLEM.md](PROBLEM.md)with statuscomplete. - Lift the 1-sentence problem statement into Key Decisions (e.g.
- Problem: <...> → see PROBLEM.md). - If the deep-dive surfaced a critical open question, add a 1-liner under Open Risks / Open Questions referencing
PROBLEM.md.
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 · 78 lines · 0 tokens per session scan A 52b8792aa7ef
p0-problem is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,021 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
drift
Post-implementation spec drift check — verify the implementation matches existing OpenSpec specifications.
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
research
Research a technical or product question.
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.
clean-check
Analyze code for cleanliness issues (unused code, comment quality, formatting, naming, complexity). Delegates to the code-cleanliness agent.
build
Mini spec-first development workflow for well-scoped implementation tasks with human in the loop.