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/p5-impl-redgit 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/p5-impl-red)<a href="https://agentmods.dev/commands/jonase47/ccpr/p5-impl-red"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p5-impl-red.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00520 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
p5-impl-red 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 today.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p5-impl-red – Write Failing Tests (RED)
Writes unit tests for a feature BEFORE production code exists. Tests must fail.
Argument: $ARGUMENTS = [Feature name/Story ID]
If provided: Write tests for the named feature. If not provided: Ask which feature should be tested.
Prerequisites
- Story identified in SPRINT.md
- Acceptance criteria from BACKLOG.md known
Agent
- Type: senior-developer
- Model: sonnet
Context (Orchestrator prepares)
Orchestrator reads beforehand and provides inline:
- From BACKLOG.md: acceptance criteria of the story (exact lines)
- From ARCHITECTURE.md: affected modules/files (relevant section only)
- From TEST_STRATEGY.md: test naming convention and framework
Prompt Template
Goal: Write failing unit tests for Story [ID]: [Title]
Acceptance Criteria: [inline from BACKLOG.md]
Affected Modules: [inline from ARCHITECTURE.md]
Output Format:
- Test file(s) in the tests/ directory
- Naming scheme: "should [behavior] when [condition]"
- 1 test per acceptance criterion + most important edge cases
Constraints:
- Write ONLY tests, NO production code
- Tests MUST fail (assert against not-yet-existing code)
- Max. 15 test cases
Orchestrator Checkpoint
- Tests cover all acceptance criteria?
- Tests actually fail (not due to syntax errors)?
- Test file is in the correct directory?
Output
- Test file(s) in tests/
Handover Epilog
Update docs/HANDOVER.md:
- What was created/changed
- Open decisions → the
## Open Decisionstable; a finding outside this command's scope goes to the## Open Pointsinbox instead - Next Steps (according to
~/.claude/docs/NEXT_STEPS_REFERENCE.md)
Recommend 1-3 sensible next commands to the user:
- Read
docs/HANDOVER.mdfor the current project status - Consult
~/.claude/docs/NEXT_STEPS_REFERENCE.mdfor allowed transitions - Only suggest commands that match the current phase/sub-skill status
- If the current phase appears complete: recommend the gate
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.
- today First seen · 65 lines · 0 tokens per session scan A 1264881be139
p5-impl-red is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 520 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 2026-09-03.
Other commands, from other repositories
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.
wiki-tune
Tune wiki schema and conventions interactively.
listen
Show what a given agent should read before coding, plus briefs/approvals mentioning it.
forge-insights
Analyze past sessions for error patterns, file activity, and recommendations.
forge-context-status
Report on current context window usage, cache health, and compaction recommendation. Read-only — does not compact.
CLAUDE
Each subdirectory is one engine verb dispatched by ../cli/cli.ts: / .ts exports a pure handler that resolves the vault, does its work through ../core/ primitives, and returns its own typed report. Commands stay thin — they compose core checks and builders; they do not reimplement them. The canonical output schema is…