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/manusco/resonance/debuggernpx skills add manusco/resonance --skill debuggergit clone --depth 1 https://github.com/manusco/resonanceWhat 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 | $0.00057 | $0.01596 |
| Opus 5 | $0.00028 | $0.00798 |
| Sonnet 5 | $0.00011 | $0.00319 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
resonance-engineering-debugger 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-engineering-debugger: find the truth, not just a patch
Role: investigator of root causes. Invoked as:
/debug(to isolate and fix defects). Input: A bug report, error log, or flaky behavior description. Output: A reproduction script, Root Cause Analysis, and a surgical fix. Definition of Done: The reproduction script triggers the bug 100% of the time before the fix. After the fix, the same script passes. The RCA explains the exact logic gap that caused the failure. The fix touches only the lines that caused the bug.
Iron Law: No Fix Without Root Cause.
You do not guess. You hypothesize, test, and prove. Fixing the symptom without understanding the disease is negligence. The next bug like it will be back in 3 months.
Prerequisites (fail fast)
- You can reproduce the bug at least once. If you cannot reproduce it, step 1 is to build the reproduction case. Nothing else.
- You know which environment the bug was observed in. Local, staging, and production may have different data shapes.
Algorithm (The 9-Step Protocol)
Copy this checklist and tick items as you go.
- Search + Learn: Check
02_memory.mdfor similar past bugs or "gotchas" in this project. → verify: checked before proceeding. - Reproduce: Write a script or set of steps that triggers the error 100% of the time. → verify: error is deterministic before continuing.
- Isolate: Narrow the scope using binary search or
git bisect. Comment out half the code. Does it still fail? → verify: the failing surface is minimized. - Hypothesize: Write down your theory about the Smoking Gun in one sentence before running any test. Construct at least one alternative hypothesis that contradicts your primary assumption to defeat Confirmation Bias. → verify: hypothesis is written, not just thought.
- Instrument: Add targeted logging or assertions to confirm or refute the hypothesis. → verify: evidence collected from the instrumentation.
- Verify Cause: If the hypothesis is wrong, discard and return to step 4. Do not apply blind patches. → verify: the exact line, state, or race condition is confirmed.
- Fix: Apply the minimal surgical fix. Match existing style exactly. → verify: run the reproduction script. It must now pass.
- Harden the class: Before closing, trace the layers the bad value crossed and make the whole bug class structurally impossible where it counts, not just the one line that failed. See Defense in Depth. → verify: the illegal state is now guarded or unrepresentable, and the reproduction script is a permanent regression test.
- Self-Improvement: Log the RCA and the Smoking Gun to
02_memory.mdto prevent future re-discovery. - Completion: Use the Completion Attestation. Include reproduction evidence, root cause, environment context, and blast radius of the fix.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/01_flaky_bug.json 823 B
- evals/02_shotgun_fix.json 834 B
- evals/03_environment_bug.json 869 B
- evals/04_planted_defect.json 1.3 KB
- references/agent_debugging_protocol.md 3.3 KB
- references/defense_in_depth.md 2.4 KB
- references/diagnostic_playbook.md 3.5 KB
- references/scientific_engineering_standards.md 2.4 KB
- references/strategic_debugging.md 1.5 KB
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 · 93 lines · 57 tokens per session scan A b9c063171913
resonance-engineering-debugger is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,596 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 2026-08-30.
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…