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/p6-func-regression)<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-func-regression"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-func-regression/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/p6-func-regression"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-func-regression.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 | $0.01139 |
| Opus 5.5 | $0.00000 | $0.00456 |
| Sonnet 5.5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
p6-func-regression 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 27d 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.
/p6-func-regression – Run Regression Tests
Ensures that existing functionality has not been broken by new changes.
Argument: $ARGUMENTS = [area/sprint]
If provided: Focus regression on the specified area. If not provided: Test all areas affected by the latest changes.
Prerequisites
- Existing automated tests present
- SPRINT.md with latest changes
Agent
- Type: qa-tester
- Model: sonnet
Context (Orchestrator prepares)
The qa-tester agent has no Bash (agents/qa-tester.md) — it cannot run the suite itself. The
orchestrator runs it first and hands the agent the result to analyze:
- From SPRINT.md: Which features/modules were changed most recently
- From tests/: Existing test files (file names + test case overview only)
- Test-run output: run
~/.claude/scripts/run-tests.sh [area] [projectdir]scoped to the areas affected by recent changes (or the full suite if$ARGUMENTSwas not given) and capture its JSON output — this is the agent's sole source for pass/fail counts below
Prompt Template
Goal: Analyze the results below – identify whether recent changes have broken existing functionality. Every number in your report must be transcribed from the provided results, never invented or estimated.
Recent Changes: [inline from SPRINT.md]
Results (already produced by the orchestrator, via
scripts/run-tests.sh): [inline JSON: framework, summary.total/passed/failed, failures[]]No-summary fallback: if the results carry no
summaryfield (run-tests.sh'snpm testpath returns{"framework":"npm-test","raw_output":…}, and an undetected framework returns{"framework":"unknown","error":…}) — do not produce any pass/fail count. Mark every row "Manually Verified" / "No parseable automated result" instead, and say so explicitly in the summary.Output Format:
# Test Area Total Tests Passed Failed Regressions (Total/Passed/Failed transcribed from the results' summary— never estimated. Nosummarypresent → "Manually Verified" / "No parseable automated result" per the fallback above, not a number) New regressions (if any, derived from the
failures[]entries):
# Regression Affected Feature Suspected Cause Constraints:
- Analyze the provided results ONLY — no new test files, no independent suite execution
- Focus on areas affected by recent changes
- Assign each regression clearly to a change
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.
- 27d ago Changed · +18 lines 65e27dcd8e0e
- 1mo ago Changed c27c549c69e2
- 1mo ago First seen · 88 lines · 0 tokens per session scan A 373ca260dd23
p6-func-regression is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,139 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.
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.