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 rfxlamia/pocketto --skill bug-huntinggit clone --depth 1 https://github.com/rfxlamia/pockettoWrote 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/rfxlamia/pocketto/bug-hunting)<a href="https://agentmods.dev/skills/rfxlamia/pocketto/bug-hunting"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/bug-hunting/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/rfxlamia/pocketto/bug-hunting"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/bug-hunting.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 | $0.00046 | $0.01686 |
| Opus 5 | $0.00023 | $0.00843 |
| Sonnet 5 | $0.00009 | $0.00337 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
bug-hunting 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 11d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Hunting
Overview
Bugs have root causes. Symptoms have patches. Patches create future bugs.
Core principle: A claim is not evidence. Evidence is not root cause. Root cause is not a fix.
Violating the letter of this process is violating the spirit of bug hunting.
Two Modes
| Mode | Trigger | First Question |
|---|---|---|
| Reactive | "Fix this bug", "test failing", "production error" | What is the confirmed root cause? |
| Proactive | "Review this code", "find bugs in...", "audit this" | What could go wrong? Where are the weakest points? |
Both modes follow the same 5 phases. Entry point differs; discipline does not.
The Three Iron Laws
LAW 1: NO FIX WITHOUT CONFIRMED ROOT CAUSE
LAW 2: NO CLAIM WITHOUT EVIDENCE
LAW 3: FIX THE SOURCE, NOT THE SYMPTOM
The Laws are non-negotiable. All three must hold for every bug.
If you haven't confirmed root cause → you cannot propose a fix. If you have evidence → state it explicitly. Never say "probably" or "almost certainly." If the fix is at the crash site → trace back further. The source is upstream.
The Five Phases
Complete each phase before proceeding. No skipping.
Phase 0: Reconnaissance
BEFORE touching any code or error message:
- What is the expected behavior? (What should it do, not what it does?)
- What type of bug is this?
- Logic error, race condition, data corruption, integration failure, performance, security
- What components are involved?
- What are common bugs in this domain/language/framework?
→ If expected behavior is unclear: stop and clarify before proceeding.
This phase prevents "fixing" intentional behavior and grounds your investigation.
Phase 1: Evidence Hunt
Collect evidence. Do not interpret yet.
- Read ALL error messages and stack traces — every line, every file path
- Reproduce consistently — if you cannot reproduce it, you cannot fix it
- Check recent changes — git diff, recent commits, new dependencies
- Add diagnostic instrumentation at component boundaries
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.
- 11d ago First seen · 164 lines · 46 tokens per session scan A 0fa9cf39bcea
bug-hunting is a skill published in the GitHub repository rfxlamia/pocketto (5 stars, last pushed 18d ago), licensed MIT. It adds 46 tokens to every session and 1,686 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
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
observability-baseline
Scaffold-time observability so a shipped product is not blind in prod from day one — error capture (Sentry), request-id structured logging, and /healthz + /readyz endpoints. stack-baseline pins Sentry but nothing wires it; this is the wiring. Loaded by app-scaffolder (bake into the scaffold), infra-provisioner (prod…
independent-review-loop
Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustiveness — a reviewer…
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.