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-bugfix)<a href="https://agentmods.dev/commands/jonase47/ccpr/p5-bugfix"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p5-bugfix/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/p5-bugfix"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p5-bugfix.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 | $0.01546 |
| Opus 5.5 | $0.00000 | $0.00618 |
| Sonnet 5.5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
p5-bugfix 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 29d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p5-bugfix – Analyze & Fix Bug
Systematically analyzes a found bug, identifies the root cause and fixes it with an accompanying regression test. Goal: the bug is fixed, secured by a test, and cannot be silently reintroduced.
Argument: $ARGUMENTS = [Bug description/ticket ID]
If provided: Analyze and fix the described bug or the bug with the named ID. If not provided: resolve the bug via the work-item adoption guard below (falls back to reading SPRINT.md or the latest review/acceptance protocols and asking, if the project is still on prose). Do not make assumptions.
0. Work-item adoption guard (ADR-0002 §8)
A bug is a work item too (--type fix) — whether it was found during /p5-review//p5-acceptance
(the story itself is already In Progress, sent back by the reviewing gate) or reported standalone
(no existing item yet).
Run python3 ~/.claude/scripts/workitems.py list.
- Non-empty array → the project uses the structured store. Use the CLI for all item state below:
- No
$ARGUMENTS: resolve the bug viaworkitems list --status "In Progress"(items sent back to dev by a review/acceptance rejection land here); if more than one, ask which to fix — do not assume. $ARGUMENTSprovided: resolve<id>by matching$ARGUMENTSagainst a story's title, or directly if it looks like aWork-Itemid (WI-NNNN) from BACKLOG.md/SPRINT.md, then confirm with the user. If it matches no existing item (a standalone bug report, not yet tracked), create it first:workitems create --title "<bug summary>" --type fix --description "$ARGUMENTS" --checked-against "<ids searched, or reasoning>"(unfilteredlistduplicate-title check first — trim + casefold — so a re-run never recreates the same bug item; runworkitems similar "$ARGUMENTS"too, to catch a near-duplicate an exact title match misses, and use it to fill in--checked-against).
- No
[]and nodocs/workitems/directory → still on prose. Read SPRINT.md to find/ask which bug is next, as before. Emit one line: "Tip: runliftto adopt the structured work-item store."[]butdocs/workitems/exists → adopted store, just empty right now. Treat as adopted: use the CLI, not the prose fallback.
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.
- 29d ago Changed 71a928e28771
- 1mo ago Changed · +2 lines 0a6e3bfcbd50
- 1mo ago Changed 9625d115288c
- 1mo ago First seen · 114 lines · 0 tokens per session scan A 90320b907d62
p5-bugfix is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,546 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
verify
Run verification loop to validate implementation.
svelte:test-fix
Troubleshoot and fix failing tests in Svelte/SvelteKit projects, including debugging test issues and resolving common testing problems.
test-suite
Run comprehensive test suite with coverage analysis.
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
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.
test
Design or run focused test validation for a task, bug, or diff.