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 KunanonJ/ai-skills-hub --skill bug-huntergit clone --depth 1 https://github.com/KunanonJ/ai-skills-hubWrote 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/kunanonj/ai-skills-hub/bug-hunter)<a href="https://agentmods.dev/skills/kunanonj/ai-skills-hub/bug-hunter"><img src="https://agentmods.dev/badge/skills/kunanonj/ai-skills-hub/bug-hunter/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/kunanonj/ai-skills-hub/bug-hunter"><img src="https://agentmods.dev/badge/skills/kunanonj/ai-skills-hub/bug-hunter.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 | $0.00030 | $0.01926 |
| Opus 5 | $0.00015 | $0.00963 |
| Sonnet 5 | $0.00006 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
bug-hunter 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 12d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Hunter
Systematically hunt down and fix bugs using proven debugging techniques. No guessing—follow the evidence.
When to Use This Skill
- User reports a bug or error
- Something isn't working as expected
- User says "fix the bug" or "debug this"
- Intermittent failures or weird behavior
- Production issues need investigation
The Debugging Process
1. Reproduce the Bug
First, make it happen consistently:
1. Get exact steps to reproduce
2. Try to reproduce locally
3. Note what triggers it
4. Document the error message/behavior
5. Check if it happens every time or randomly
If you can't reproduce it, gather more info:
- What environment? (dev, staging, prod)
- What browser/device?
- What user actions preceded it?
- Any error logs?
2. Gather Evidence
Collect all available information:
Check logs:
# Application logs
tail -f logs/app.log
# System logs
journalctl -u myapp -f
# Browser console
# Open DevTools → Console tab
Check error messages:
- Full stack trace
- Error type and message
- Line numbers
- Timestamp
Check state:
- What data was being processed?
- What was the user trying to do?
- What's in the database?
- What's in local storage/cookies?
3. Form a Hypothesis
Based on evidence, guess what's wrong:
"The login times out because the session cookie
expires before the auth check completes"
"The form fails because email validation regex
doesn't handle plus signs"
"The API returns 500 because the database query
has a syntax error with special characters"
4. Test the Hypothesis
Prove or disprove your guess:
Add logging:
console.log('Before API call:', userData);
const response = await api.login(userData);
console.log('After API call:', response);
Use debugger:
debugger; // Execution pauses here
const result = processData(input);
Isolate the problem:
// Comment out code to narrow down
// const result = complexFunction();
const result = { mock: 'data' }; // Use mock data
What ships with it
1 file 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.
- 12d ago First seen · 385 lines · 30 tokens per session scan A b3e9b84416d0
bug-hunter is a skill published in the GitHub repository KunanonJ/ai-skills-hub (5 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,926 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.
ijfw-debug
Root-cause analysis with hypothesis tracking. Trigger: 'debug', 'broken', 'not working', 'fix this bug', /debug.
ijfw-doctor
Diagnose IJFW integration health per platform. Trigger: 'doctor', 'check setup', /doctor.
debugger
Finds the root cause of a defect hypothesis-first: reproduce it, form competing hypotheses, gather evidence that discriminates between them, then fix the cause and prove the fix. Use when a test fails for unclear reasons, a failure is flaky or happens only in CI, behaviour differs from what was expected, or a…