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/caiaffa/claude-code-ultimate-engineering-system/systematic-debuggingnpx skills add caiaffa/claude-code-ultimate-engineering-system --skill systematic-debugginggit clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-systemWhat 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 | $0.00027 | $0.00498 |
| Opus 5 | $0.00014 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Replace guesswork with evidence. Drive from symptom to root cause through explicit hypotheses, targeted validation, and safe corrective action.
When to use
- Behavior differs from expectations.
- Production incidents or local bugs.
- Intermittent or timing-dependent issues.
- Failures spanning multiple layers or services.
Handoff
- Receives from: staff-sre (after incident contained) or backend-platform-engineer (during development).
- Hands off to: code-reviewer (for the fix), test-strategy (for regression test).
The method
1. STATE the problem precisely (expected vs actual)
2. GATHER context (recent changes, environment, timing)
3. HYPOTHESIZE (list 3-5 causes, ranked by probability)
4. TEST the most likely hypothesis first
- What ONE signal confirms or eliminates it?
- Check that signal.
5. NARROW — eliminate hypotheses, don't collect more data randomly
6. VERIFY — confirm root cause with independent evidence
7. FIX with minimal blast radius
8. VALIDATE — regression test + monitor
Red flags — you're debugging wrong if
- You changed code before having a hypothesis.
- You're reading logs without knowing what you're looking for.
- You said "that's weird" more than twice without writing a hypothesis.
- You restarted the service and called it fixed.
- You're debugging in production without a rollback plan.
Common traps
- Multiple issues producing the same symptom.
- Partial failure hidden behind retries (looks like intermittent).
- Environment mismatch (works locally, breaks in prod).
- Stale caches, queues, or config masking the real state.
- Race conditions that disappear under debugging/logging.
- "Fixed by restart" but the allocating pattern still exists.
Output format
- Problem statement (precise: expected X, got Y, in context Z)
- Hypotheses (ranked by probability, each with confirmation signal)
- Investigation steps (ordered, minimal)
- Root cause (with evidence chain)
- Fix (with blast radius assessment)
- Regression test (specific scenario)
- Monitoring (what to watch post-fix)
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 · 56 lines · 27 tokens per session scan A 1c5c3a3925aa
systematic-debugging is a skill published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (16 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 498 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…