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/gate-p5)<a href="https://agentmods.dev/commands/jonase47/ccpr/gate-p5"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/gate-p5/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/gate-p5"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/gate-p5.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 | $0.03076 |
| Opus 5.5 | $0.00000 | $0.01230 |
| Sonnet 5.5 | $0.00000 | $0.00615 |
| Haiku 4.5 | $0.00000 | $0.00308 |
Grade A, and why
gate-p5 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gate-p5 – Sprint Gate: Check Implementation Quality
Checks at the end of each sprint whether all tasks meet quality standards and the sprint can be considered successfully completed. Called repeatedly after each sprint. No argument – this gate always checks the complete current sprint status.
No Argument ($ARGUMENTS not applicable)
Gate commands do not accept arguments. They always check the complete current sprint status.
Execution
0. Holistic sprint review (runs automatically, opus)
Before evaluating the gate, ensure the whole-sprint code review exists and is current, then feed its findings into the gate.
Resolve scope + freshness guard:
- Determine the current sprint number
<n>fromdocs/planning/SPRINT.md's frontmatter fieldsprint: <n>(or the activesprint/SPRINT-NN.md'ssprint: NNfield, if SPRINT.md is a sub-index) — the same file thebase_commitbelow already comes from. Also readbase_commitfrom that same frontmatter. - A report
docs/reviews/SPRINT-<n>-review.mdis current if it exists AND its recordedreviewed_headequals the currentgit rev-parse HEAD. - Current → reuse it; do not re-run (opus is not spent again).
- Missing or stale (HEAD moved since it was written, e.g. after a
/p5-bugfix) → run/p5-review-sprintnow. That command invokes thecode-revieweragent on opus — the agent default issonnet, so the opus model is passed explicitly via the command's**Model**: opus— scoped togit diff <base_commit>..HEAD, and writes/refreshes the report. Invoked as a sub-step here: use its findings; ignore its standalone next-step recommendations (we are already in the gate).
Use the result: the holistic review feeds the "Code review" criterion (§2.4). Any unresolved CRITICAL/HIGH finding is a gate blocker → /p5-bugfix, then re-run the gate (the guard re-runs the review against the new HEAD).
0a. Work-item adoption guard (ADR-0002 §8)
Run python3 ~/.claude/scripts/workitems.py list and explicitly check whether the
docs/workitems/ directory exists (e.g. ls docs/workitems/). Both signals are required — list
returns the identical [] for an adopted-but-empty store and a never-adopted project; only the
directory's existence tells them apart, and getting this wrong lets the gate falsely pass a
sprint with zero actually-tracked story status.
- Non-empty list → the project uses the structured store. Use the CLI for all story-status data below (the "Story status" criterion in step 2 and the write-back in step 3), instead of reading it from BACKLOG.md prose.
- Empty list, but
docs/workitems/exists → the store is adopted, just empty for this query (e.g. every story already archived/migrated). This is a genuine finding for the "Story status" criterion — NOT an exemption to fall back to prose. Evaluate it as "no stories tracked", not as "still on prose". - Empty list and no
docs/workitems/directory → not adopted, still on prose. Read SPRINT.md/BACKLOG.md for story status, as before. Emit one line: "Tip: runliftto adopt the structured work-item store."
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.
- 26d ago Changed e0630db0547c
- 1mo ago Changed 019bb43d9333
- 1mo ago Changed · +3 lines 22c6d040f742
- 1mo ago First seen · 197 lines · 0 tokens per session scan A 6c516f89ce20
gate-p5 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 3,076 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
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.
playwright-setup
Verify Playwright CLI installation and create a .playwright/cli.config.json configuration file. Use when setting up browser automation, configuring Playwright, or user mentions "setup playwright", "configure browser testing", "install playwright".
test
Run the project test suite. Reports results to .claude/runtime/outputs/sse/test/.
eval
Pick the eval judge. local = fresh Claude evaluator (default). jev = Jev by TypeSafe AI, needs API key.
zeus
A command that runs an automated software-building pipeline from a one-line product description through planning, implementation, review, Docker setup, and testing.
ccc-audit
Audit the current project for dependency vulnerabilities, oversized bundles, type errors, dead code, hardcoded secrets, undocumented env vars and a missing CLAUDE.md. Use when you want a health score before a release or review.