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.
npx skills add goiltpatpat/patpat --skill patpat-inspectgit clone --depth 1 https://github.com/goiltpatpat/patpatWrote 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/goiltpatpat/patpat/patpat-inspect)<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-inspect"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-inspect/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/goiltpatpat/patpat/patpat-inspect"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-inspect.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 | $0.00036 | $0.00655 |
| Opus 5 | $0.00018 | $0.00328 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
patpat-inspect 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 4d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patpat Inspect
For a bounded read-only question, use this skill and its relevant references. Read the operating protocol in full for uncertainty, sensitive data, or cross-cutting investigation. Do not load the router or reread unchanged instructions already loaded in this session.
Read repository truth and apply the investigation playbook. Report with the how-report contract. When explanation clarity needs structure that prose hides, choose the smallest form from earned representation.
This skill explains how repository behavior works, where it lives, who owns it, which layer it occupies, and any critique that follows that explanation. Questions about why the code reached its current shape go to rationale forensics.
For a live resource symptom, apply runtime forensics and capture passively. For a supplied trace, profile, spindump, or heap snapshot, apply trace forensics. Do not hot-patch, inject, or alter a live process inside this read-only workflow.
When the question asks why code or a contract reached its current shape, apply rationale forensics and report with the why-report contract: code anchors first, evidence before narrative, competing hypotheses, and an honest account of material sources used or unavailable. Keep rationale questions in this skill; do not create a separate /why skill. Do not call unrelated external connectors to fill the report.
Keep the task read-only. Inspect version-control state first when available. Load only the repository instructions, continuity files, code paths, tests, configuration, logs, and runtime state needed to answer the question.
Default to one read-only pass. Use 2-4 parallel read-only explorers only when independent evidence sources are required, then one explainer whose synthesis is the product. Fall back to serial work when isolation is missing. For teach-me questions, the user-facing reply is the layered explanation, not a report about the work.
Verify claims against primary artifacts. State whether each material conclusion is confirmed, inferred, or unknown. Cite files and functions. If a change appears necessary, recommend the smallest safe patch and stop unless the user also requested implementation. Critique uses Act on / Consider / Noted / Dismissed only after Explain. Do not open a pull request from inspect.
What ships with it
2 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.
- 4d ago Changed · -47 tokens per session ef74a6631c3c
- 6d ago Changed 151b20b71c27
- 7d ago Changed 32b1d3c24f33
- 11d ago First seen · 27 lines · 83 tokens per session scan A 621d73cc00d9
patpat-inspect is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 655 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
post-mortem
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
ijfw-debug
Root-cause analysis with hypothesis tracking. Trigger: 'debug', 'broken', 'not working', 'fix this bug', /debug.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.