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/freepeak/ktme/systematic-debuggingnpx skills add FreePeak/ktme --skill systematic-debugginggit clone --depth 1 https://github.com/FreePeak/ktmeWhat 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 | $0.00023 | $0.01751 |
| Opus 5 | $0.00012 | $0.00875 |
| Sonnet 5 | $0.00005 | $0.00350 |
| Haiku 4.5 | $0.00002 | $0.00175 |
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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
A structured approach to debugging that ensures consistent, reliable bug fixes with verification.
When to Use
Use this skill when:
- Encountering unexpected behavior or errors
- Investigating failing tests
- Debugging production issues
- Analyzing performance problems
The 4-Phase Framework
Phase 1: Reproduce the Issue
Goal: Create a minimal, reliable reproduction
Steps:
- Identify the exact conditions that trigger the issue
- Create a minimal test case or script
- Verify you can reproduce it consistently
- Document the reproduction steps
Evidence Format:
REPRODUCTION:
Environment: [OS, runtime version, dependencies]
Steps:
1. [step 1]
2. [step 2]
3. [step 3]
Expected: [what should happen]
Actual: [what actually happens]
Best Practices:
- Isolate the problem - remove unrelated code
- Use logging/debugging to narrow scope
- Check if issue is deterministic or intermittent
- Note any error messages, stack traces, or logs
Phase 2: Analyze Root Cause
Goal: Identify why the issue occurs
Steps:
- Trace execution flow from reproduction
- Examine relevant code with
file:linereferences - Identify the specific line/condition causing the issue
- Determine the underlying cause
Analysis Template:
ANALYSIS:
file:line - [description of problematic code]
ACTUAL: [what the code does]
EXPECTED: [what it should do]
ROOT CAUSE: [wrong input | wrong order | missing dep | config | logic | external]
EVIDENCE:
- [evidence point 1 with file:line]
- [evidence point 2 with file:line]
- [evidence point 3 with file:line]
Investigation Techniques:
- Binary search (comment out code to isolate)
- Check recent changes (git blame, git log)
- Compare with working version
- Review documentation/API specs
- Check for race conditions/timing issues
- Verify assumptions with assertions
Phase 3: Implement Fix
Goal: Apply minimal, targeted fix
Steps:
- Design the simplest possible fix
- Implement the fix with minimal changes
- Consider edge cases
- Add/update tests if applicable
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 · 320 lines · 23 tokens per session scan A f36c77e03602
systematic-debugging is a skill published in the GitHub repository FreePeak/ktme (15 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 1,751 once invoked, about $0.0001 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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.