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-debuggit 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-debug)<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-debug"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-debug.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00657 |
| Opus 5 | $0.00020 | $0.00329 |
| Sonnet 5 | $0.00008 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
patpat-debug 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 today.
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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patpat Debug
For clear, bounded, reversible local work without delivery intent, use this skill and its relevant references. Otherwise read the operating protocol and execution graph in full before acting. Escalate on uncertainty, security, auth, billing, secrets, architecture, cross-cutting work, or delivery intent. Define Claim, Surface, Action, Expect, and Cleanup before editing. Do not load the router or reread unchanged instructions already loaded in this session.
Read repository truth, proof over proxy, fix root causes, smallest safe change, and preserve safety. Apply the defect playbook. When the user requests test-first work or a cheap deterministic regression target exists, apply regression first.
Observe the failure before any production edit, or record an explicit why-not; report fail-before and pass-after on the same check.
Reproduce before editing when safe and practical. Otherwise trace the contract or code path, or use an isolated non-harmful surrogate, and state that direct runtime proof is unavailable. Trace the earliest incorrect state instead of patching the last visible symptom.
If the user limited the request to diagnosis, stop after proving or bounding the root cause. Recommend the smallest patch without editing.
Change one causal variable at a time. Preserve only material failed hypotheses through the defect playbook as bounded, redacted evidence; do not retain raw logs or trivial attempts. Re-run the original reproduction when it remains safe and practical; otherwise run the predeclared non-triggering check and state the missing runtime proof. Never label an unobserved fix as verified.
When the defect is a mismatch against a reference image or migrated UI, apply the visual equivalence playbook after reproducing the defect. Preserve the pre-edit reference and comparison harness.
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.
- today Changed · +2 lines 47e03b6a3444
- 3d ago Changed · +2 lines 50da729fb627
- 7d ago First seen · 26 lines · 40 tokens per session scan A 47e6ced02556
patpat-debug is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 657 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.