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/klh/speedy-claude/systematic-debuggingnpx skills add klh/speedy-claude --skill systematic-debugginggit clone --depth 1 https://github.com/klh/speedy-claudeWhat 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 | $0.00040 | $0.01093 |
| Opus 5 | $0.00020 | $0.00547 |
| Sonnet 5 | $0.00008 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00109 |
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 3d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Core Principle
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.
Never apply symptom-focused patches that mask underlying problems. Understand WHY something fails before attempting to fix it.
The Four-Phase Framework
Phase 1: Root Cause Investigation
Before touching any code:
- Read error messages thoroughly - Every word matters
- Reproduce the issue consistently - If you can't reproduce it, you can't verify a fix
- Examine recent changes - What changed before this started failing?
- Gather diagnostic evidence - Logs, stack traces, state dumps
- Trace data flow - Follow the call chain to find where bad values originate
Root Cause Tracing Technique:
1. Observe the symptom - Where does the error manifest?
2. Find immediate cause - Which code directly produces the error?
3. Ask "What called this?" - Map the call chain upward
4. Keep tracing up - Follow invalid data backward through the stack
5. Find original trigger - Where did the problem actually start?
Key principle: Never fix problems solely where errors appear—always trace to the original trigger.
Phase 2: Pattern Analysis
- Locate working examples - Find similar code that works correctly
- Compare implementations completely - Don't just skim
- Identify differences - What's different between working and broken?
- Understand dependencies - What does this code depend on?
Phase 3: Hypothesis and Testing
Apply the scientific method:
- Formulate ONE clear hypothesis - "The error occurs because X"
- Design minimal test - Change ONE variable at a time
- Predict the outcome - What should happen if hypothesis is correct?
- Run the test - Execute and observe
- Verify results - Did it behave as predicted?
- Iterate or proceed - Refine hypothesis if wrong, implement if right
Phase 4: Implementation
- Create failing test case - Captures the bug behavior
- Implement single fix - Address root cause, not symptoms
- Verify test passes - Confirms fix works
- Run full test suite - Ensure no regressions
- If fix fails, STOP - Re-evaluate hypothesis
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.
- 3d ago First seen · 151 lines · 40 tokens per session scan A d9e852d2e118
systematic-debugging is a skill published in the GitHub repository klh/speedy-claude (11 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,093 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 2026-08-30.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…