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 ApexIQ/skillsmith --skill debugginggit clone --depth 1 https://github.com/ApexIQ/skillsmithWrote 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/apexiq/skillsmith/debugging)<a href="https://agentmods.dev/skills/apexiq/skillsmith/debugging"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/debugging/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/apexiq/skillsmith/debugging"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/debugging.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 | $0.00025 | $0.00518 |
| Opus 5.5 | $0.00010 | $0.00207 |
| Sonnet 5.5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
debugging 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 1mo 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
🐛 Debugging
Philosophy: A bug is a gift. It reveals a gap in your tests or understanding.
Workflow
1. Reproduce
- First, reproduce the bug reliably. If you can't reproduce it, you can't fix it.
- Get exact steps, input, and environment.
- Create a minimal test case that fails.
2. Isolate
- Narrow down the scope: Frontend or Backend? Which function?
- Use logging or debugger to inspect state at key points.
- Binary Search: Comment out half the code. Does bug persist? Narrow down.
3. Diagnose
- Ask: "What did I expect? What actually happened?"
- Check recent changes (
git log,git blame). - Inspect data entering and leaving suspect functions.
4. Fix & Verify
- Write a test that fails due to the bug. (TDD for bugs!)
- Implement the fix.
- Run the test. It MUST pass.
- Run full test suite to check for regressions.
5. Document
- Add a comment explaining why the bug occurred.
- If subtle, add to "Known Gotchas" in documentation.
Common Bug Patterns
| Symptom | Likely Cause |
|---|---|
| Works locally, fails in CI | Environment differences, missing env vars |
| Works sometimes | Race condition, timing issue |
| Returns null/undefined | Missing null check, async timing |
| Wrong data displayed | API mismatch, caching issue |
Examples
1. Bug: "Submit button does nothing."
2. Isolate: Is onClick firing? -> Add console.log.
3. Diagnose: Handler fires, but API returns 500.
4. Root Cause: Endpoint expects different payload format.
5. Fix: Update request payload. Add test.
Guidelines
- Never guess. Always verify with logs or debugger.
- Don't just patch symptoms. Find the root cause.
- If bug took >30 mins to find, add a test to prevent recurrence.
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.
- 1mo ago First seen · 65 lines · 25 tokens per session scan A cd4311eab203
debugging is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 518 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 2026-08-31.
Other skills, from other repositories
graph-query
Query the code graph for callers, dependencies and the blast radius of a change. Use before changing the signature or behaviour of a function, class or module that other code uses, when the user asks "find callers", "what uses this" or "check dependencies", and when exploring an unfamiliar codebase.
dev-debug
Systematic debugging - reproduce, isolate the root cause, fix, pin it with a regression test. Use it first whenever the user reports a bug, a crash, an error message, a wrong result or a failing test (a failing CI pipeline is ops-ci-fix), before reading code to guess at the cause.
debug-device-over-vusb
Debug the user's app on a real Kobiton device attached to this machine over virtualUSB, driven by natural language. Installs the pinned virtualUSB client on first use (macOS: cached bundle; Windows: verified installer handed to the user), finds vUSB-ready private devices with listDevices({virtualUsb: true}), connects…
dev-error-handling
Error handling strategy. Trigger when the user wants to implement error handling, exceptions, or error boundaries.
learner
Post-debugging knowledge extraction — captures non-obvious, codebase-specific learnings that pass quality gates. Invoke after resolving tricky bugs or discovering surprising behavior.
ops-ci-fix
Autonomous diagnosis and repair of failing CI/CD pipelines. Scan GitHub Actions workflows, identify failure causes, and apply fixes. Trigger when CI is broken, tests fail in CI, or workflows are stuck.