Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/muyen/vibe-to-prodnpx agentmods add skills/muyen/vibe-to-prod/systematic-debuggingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/muyen/vibe-to-prod/systematic-debugging)<a href="https://agentmods.dev/skills/muyen/vibe-to-prod/systematic-debugging"><img src="https://agentmods.dev/badge/skills/muyen/vibe-to-prod/systematic-debugging/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/muyen/vibe-to-prod/systematic-debugging"><img src="https://agentmods.dev/badge/skills/muyen/vibe-to-prod/systematic-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00031 | $0.00775 |
| Opus 5.5 | $0.00012 | $0.00310 |
| Sonnet 5.5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
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 12d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging Skill
Apply structured 4-phase debugging to find root causes, not just symptoms.
When to Activate
This skill should activate when:
- User reports a bug or unexpected behavior
- Error messages or stack traces appear
- Tests are failing
- User says "fix", "debug", "broken", "not working", "issue"
- Behavior differs from expected
4-Phase Debugging Process
Phase 1: REPRODUCE
Before fixing anything:
1. Understand the expected behavior
2. Understand the actual behavior
3. Find reliable reproduction steps
4. Identify the exact error/symptom
Questions to answer:
- What should happen?
- What actually happens?
- Can I reproduce it consistently?
- What are the exact steps?
Phase 2: ISOLATE
Narrow down the problem:
1. Find the smallest reproduction case
2. Identify which component/layer fails
3. Check recent changes (git log, git diff)
4. Add logging/debugging to trace execution
Techniques:
- Binary search through code changes
- Add strategic logging
- Comment out code sections
- Test with minimal input
Phase 3: IDENTIFY ROOT CAUSE
Find the actual cause, not symptoms:
1. Follow the data flow
2. Check assumptions
3. Verify inputs/outputs at each step
4. Ask "why" 5 times
Common root causes:
| Symptom | Likely Root Cause |
|---|---|
| 404 on API | Route not registered |
| Type mismatch | Wrong type conversion |
| Null pointer | Uninitialized variable |
| Race condition | Missing synchronization |
| Auth failure | Token/session expired |
Phase 4: FIX AND VERIFY
Fix properly:
1. Write a test that reproduces the bug
2. Implement the fix
3. Verify the test passes
4. Check for similar issues elsewhere
5. Prevent regression
Debugging Commands
Backend (Go)
# Run with verbose logging
go run ./cmd/api/main.go
# Run specific test with verbose output
go test -v -run TestName ./...
# Add debug logging
zap.L().Debug("checkpoint", zap.Any("data", data))
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.
- 12d ago First seen · 138 lines · 31 tokens per session scan A 1961fdf1a03d
systematic-debugging is a skill published in the GitHub repository muyen/vibe-to-prod (34 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 775 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
test-flakiness
Find flaky tests from CI logs — aggregates pass rates, spots intermittent failures, recommends quarantine. After multiple runs.
bugfix-quick
Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
bug-report
Structured bug report from a description, or analyze code for potential bugs. Reproduction steps, severity.
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.