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 agentmods add skills/ao92265/claude-code-playbook/debugnpx skills add ao92265/claude-code-playbook --skill debuggit clone --depth 1 https://github.com/ao92265/claude-code-playbookWhat 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 | $0.00081 | $0.00647 |
| Opus 5 | $0.00041 | $0.00324 |
| Sonnet 5 | $0.00016 | $0.00129 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Debugging
Systematic debugging using the scientific method. No more random changes hoping something works.
Steps
-
Reproduce the bug:
- Get the exact error message, stack trace, or unexpected behavior
- Find the minimal reproduction case
- Confirm it's reproducible (not a flaky test or race condition)
- If it can't be reproduced, gather more data before proceeding
-
Form a hypothesis:
- Based on the error and context, what's the most likely cause?
- List 2-3 possible causes ranked by probability
- State what you'd expect to see if each hypothesis is correct
-
Test the hypothesis:
- Add a targeted log, breakpoint, or assertion to test the top hypothesis
- Run the reproduction case
- Does the evidence support or refute the hypothesis?
-
Narrow down:
- If hypothesis is supported: zoom in on the specific code path
- If hypothesis is refuted: move to the next hypothesis
- Use binary search: add a check at the midpoint of the suspected code path
- Each step should cut the problem space in half
-
Identify the root cause:
- Don't stop at the symptom — find why it's happening
- Check: is this a data issue, logic error, race condition, or configuration problem?
- Verify the root cause explains ALL observed symptoms
-
Fix and verify:
- Make the minimum change that fixes the root cause
- Run the original reproduction case — does it pass?
- Run the full test suite — did the fix introduce regressions?
- Remove any debugging artifacts (extra logs, breakpoints)
-
Prevent recurrence:
- Add a test case that would have caught this bug
- Consider: should this be in
tasks/lessons.md? - Is there a class of similar bugs that should be checked?
Important
- Don't change code randomly. Every change should test a specific hypothesis.
- Don't fix symptoms. A null check at the crash site is a band-aid — find why it's null.
- Keep notes. Write down hypotheses and results so you don't re-test the same thing.
- Time-box. If you're stuck after 3 hypotheses, step back and reconsider assumptions.
- Remove debug artifacts. No console.log, debugger statements, or commented-out code in the final commit.
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.
- 2d ago First seen · 68 lines · 81 tokens per session scan A ac2764c38600
debug is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 15d ago), licensed MIT. It adds 81 tokens to every session and 647 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.