Borrowing it
Nothing to install: this file belongs to rygel/AIUsageTracker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rygel/AIUsageTracker/main/.claude/commands/papi-audit.mdgit clone --depth 1 https://github.com/rygel/AIUsageTrackerWrote 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/rygel/aiusagetracker/papi-audit)<a href="https://agentmods.dev/commands/rygel/aiusagetracker/papi-audit"><img src="https://agentmods.dev/badge/commands/rygel/aiusagetracker/papi-audit/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/rygel/aiusagetracker/papi-audit"><img src="https://agentmods.dev/badge/commands/rygel/aiusagetracker/papi-audit.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 | $0.00303 |
| Opus 5.5 | $0.00000 | $0.00121 |
| Sonnet 5.5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
papi-audit 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 1mo 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.
What it actually says
Audit the latest changes in this branch for bugs and compliance with the project's conventions defined in CLAUDE.md.
Steps
-
Identify changed files: Run
git diff main --name-onlyto find all files modified on this branch. -
Read each changed file and review it for:
Bug check
- Logic errors, off-by-one mistakes, incorrect conditions
- Unhandled edge cases (null, undefined, empty inputs)
- Race conditions or state management issues
- Functions that could throw but aren't wrapped in try/catch where needed
- Incorrect type narrowing or unsafe casts
Code style (from CLAUDE.md)
- Check all conventions defined in CLAUDE.md and flag any violations
- Pay special attention to naming, typing, error handling, and import patterns
Documentation check
- For each changed source file, check if any documentation in
docs/describes behaviour that the change modified - If a doc needs updating, report it as a finding with severity "Doc drift"
- Report findings in this format:
For each issue found:
- File: path and line number
- Severity: Bug / Convention violation / Nitpick
- Issue: What's wrong
- Fix: How to fix it
If no issues are found, state that the changes are clean.
- Note pre-existing issues separately — flag them but don't fix them unless they interact with the new changes.
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.
- 1mo ago First seen · 35 lines · 0 tokens per session scan A 1ca7dfef2767
papi-audit is a command published in the GitHub repository rygel/AIUsageTracker (48 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 303 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 2026-08-30.
Other commands, from other repositories
plannotator-review
Open interactive code review for current changes, another directory, or a PR URL; --base / --diff-type pin the session's opening diff (session-only, git-only).
default-ai-review
Extract findings from the provided diff. Rank by severity. Produce a structured review. Emit one recommendation.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
branch-review
Review a branch before merge.
code-simplify
A code-review command that simplifies recently changed code or another chosen scope while preserving its behavior.