Borrowing it
Nothing to install: this file belongs to IgorWarzocha/howaboua-pi-stuff. 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/IgorWarzocha/howaboua-pi-stuff/main/.cursor/skills/pi-stuff-tool-error-audit/SKILL.mdgit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/skills/igorwarzocha/howaboua-pi-stuff/pi-stuff-tool-error-audit)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/pi-stuff-tool-error-audit"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/pi-stuff-tool-error-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/skills/igorwarzocha/howaboua-pi-stuff/pi-stuff-tool-error-audit"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/pi-stuff-tool-error-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.00311 |
| Opus 5.5 | $0.00012 | $0.00124 |
| Sonnet 5.5 | $0.00006 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
pi-stuff-tool-error-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 2mo 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
Discover and load an applicable agent-session diagnostics skill before attributing recurring failures.
Run the bundled script instead of grepping session JSONL:
deno run --no-config --allow-read --allow-env=HOME,PI_CODING_AGENT_DIR .pi/skills/pi-stuff-tool-error-audit/scripts/audit-tool-errors.ts
It treats a persisted isError result or failed nested Notebook trace as a marked failure, keeps unmarked nonzero subprocess exits separate, reports signatures for mechanism-level review, and records later tool results only as chronology. A later green call never makes the failed call successful.
Use the cursor in state.json for the normal audit. Override it with --since 14d only for an explicit retrospective. Read references/interpretation.md before judging the report.
Do not print tool inputs, user messages, or raw session content in a broad audit. Use the reported session path and line numbers to inspect only a selected incident after the aggregate identifies it.
Advance the cursor with --mark-checked only after reviewing the complete unfiltered window with no malformed JSONL lines. Add --allow-write=.pi/skills/pi-stuff-tool-error-audit/state.json to that run. The script records the audit start as the next lower bound, so calls arriving during the scan remain eligible.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago Changed 1f67bf54b884
- 2mo ago First seen · 21 lines · 29 tokens per session scan A 1b2f8a46d404
pi-stuff-tool-error-audit is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (413 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 311 once invoked, about $0.0001 per session on Opus 5.5. 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.
pi-stuff-tool-error-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pi-stuff-tool-error-auditIgorWarzocha/howaboua-pi-stuff | Skill | 413 | yesterday | MIT | A | 29 | Cursor |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |