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/p5-review-sprint)<a href="https://agentmods.dev/commands/jonase47/ccpr/p5-review-sprint"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p5-review-sprint.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 5.1 | $0.00000 | $0.02156 |
| Opus 5 | $0.00000 | $0.01078 |
| Sonnet 5 | $0.00000 | $0.00431 |
| Haiku 4.5 | $0.00000 | $0.00216 |
Grade A, and why
p5-review-sprint 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 4d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p5-review-sprint – Holistic Sprint Code Review (whole-context)
Runs ONE final code review over the entire sprint at sprint end, with a stronger model, to catch issues that single-story reviews structurally cannot see: cross-story interactions, the schema/data model as a whole, conformance to ADRs and Constitution Inviolables, and consistency with prior lessons/instincts.
This is complementary to /p5-review-code, not a repeat of it. The per-story review runs during the sprint, is narrow and local, and also surfaces "good things". This pass is broad and architectural — it deliberately does not re-do the per-story nitpicking.
Argument: $ARGUMENTS = [optional: sprint number or git base ref]
- Without argument: review the current sprint (stories from
docs/planning/SPRINT.md, diff from the sprint's base commit toHEAD). - With a sprint number (e.g.
6): review that sprint. - With a git ref (e.g. a tag or SHA): use it as the diff base.
Prerequisites
- Template:
~/.claude/templates/REVIEW_REPORT_TEMPLATE.md - Sprint implementation complete (all stories at least through
/p5-reviewper story). - Either run manually before
/gate-p5, or let/gate-p5run it automatically (the gate triggers this review on opus when no current report exists). Mirrors/cross-checkfor docs, but unlike/cross-checkthe sprint gate runs it for you. - Working tree committed, so the diff reflects the committed sprint work.
Agent
- Type: code-reviewer
- Model: opus
Rationale (why opus here, cheaper models elsewhere): this pass reasons across the full sprint diff and the architecture anchors at once. The findings it targets — a constraint anti-pattern repeated across a migration, a job-queue/coalescing semantics gap, drift from an ADR or Inviolable, a lesson applied in one module but not its sibling — require holding the whole sprint in context and the stronger model to connect the dots. That cross-context reasoning is the entire point of the pass, and it runs once per sprint, so the cost is bounded. Per-story reviews stay on the cheaper model.
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.
- 4d ago First seen · 130 lines · 0 tokens per session scan A 685d0f70b0f9
p5-review-sprint 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 2,156 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
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.
clean-check
Analyze code for cleanliness issues (unused code, comment quality, formatting, naming, complexity). Delegates to the code-cleanliness agent.
review
Ejecutá un code review como senior engineer para producción.
pr
Open a Pull Request on GitHub following team conventions. Draft by default.
review
Adversarial staff-level review of a System Design Doc. Interrogates the 10 staff questions, finds cost and failure risks, returns a verdict. Sensors and evals gate.
de-slop
Run post-implementation cleanup pass. Removes debug code, test slop, commented blocks, inconsistent naming, and TODO hacks. Usage - /mindforge:de-slop [path] [--dry-run] [--category debug|test|comments|naming|todos|all].