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/nicograef/handbook/systematic-debuggingnpx skills add nicograef/handbook --skill systematic-debugginggit clone --depth 1 https://github.com/nicograef/handbookWhat 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 | $0.00056 | $0.01130 |
| Opus 5 | $0.00028 | $0.00565 |
| Sonnet 5 | $0.00011 | $0.00226 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
systematic-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 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Adapted from the MIT-licensed superpowers plugin.
Find the root cause before touching code. An ungrounded fix is a guess. It may hide the symptom or introduce a new bug.
Workflow
-
Read the error completely.
- Full stack trace, exact message, line numbers, file paths, exit codes.
- Don't skim past a warning — it may already tell you the answer.
-
Reproduce it reliably.
- Find the exact steps or command that triggers it every time.
- Examples:
go test ./... -run TestX,pnpm test -- path/to/spec,mvn test -Dtest=ClassName. - Won't reproduce? Gather more evidence before guessing fixes.
- Run with
-v/--verbose, add temporary logging, check whether it's flaky/timing-dependent, or narrow the triggering conditions.
-
Check what changed recently.
- Tools:
git log -p,git diff,git blameon the affected lines. - Check new or bumped dependencies (
go.mod,package.json,pom.xml). - Check config/env var changes and infra changes.
- The bug usually correlates with a recent change, even if the symptom appears elsewhere.
- Tools:
-
When a value crosses a boundary, log what enters and exits.
- Applies to process, service, or layer boundaries: API → service → database, CI → build → deploy, frontend → backend.
- Add temporary logging at each hop.
- Run once to see where good data becomes bad data.
- That pins down which component to investigate.
- Remove the temporary logging once done.
-
Trace a bad value backward to its source.
- Don't fix where a deep call-stack error surfaces.
- Ask "what called this with this value?" and walk up: function → caller → caller's caller.
- Find where the bad value was created or first went wrong.
- Fix there, not where it finally blew up.
-
Find a working example in the same codebase and diff against it.
- Look for something similar that works: another handler, component, or test.
- Read it fully; list every difference from the broken code.
- Differences include configuration, dependencies, assumptions, order of operations.
- Don't assume a difference "can't matter" without checking.
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 · 98 lines · 56 tokens per session scan A 8cc9ec1d532b
systematic-debugging is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 25d ago), licensed MIT. It adds 56 tokens to every session and 1,130 once invoked, about $0.0003 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.