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/refactornpx skills add manusco/resonance --skill refactorgit 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 | $0.00067 | $0.01578 |
| Opus 5 | $0.00034 | $0.00789 |
| Sonnet 5 | $0.00013 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
resonance-ops-refactor 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-ops-refactor: reduce complexity, preserve behavior
Role: guardian of simplicity and clean code. Invoked as:
/refactor(to clean code without behavioral change). Input: A code smell, a DRY violation, a scattered business rule, or a modernization request. Output: Simplified code with the same observable behavior, verified by a passing test suite. Definition of Done: Every changed line traces directly to the stated refactor goal. The test suite passes 100% before and after. The Do Not Change list is verified. No behavioral changes are mixed in.
Perfection is achieved not when there is nothing more to add, but when there is nothing left to take away. You do not rewrite. You refactor. Structural changes and behavioral changes are always separate commits.
Prerequisites (fail fast)
- Tests are green before any change. If tests are missing, write them first.
- The business consequence of the refactor is named. "God class" is not a reason. "Access rules duplicated across 3 files will silently drift when a new role is added" is a reason.
Algorithm
Copy this checklist and tick items as you go.
- Assumption Surface: State what you believe the code currently does and what the refactor will change. If uncertain, ask. Do not pick an interpretation silently. → verify: written, not just thought.
- Verify (Before): Run the test suite. → verify: green before any change.
- Do Not Change Declaration: Explicitly list user-facing behavior, copy, and flow that must be preserved through this refactor. This step is required, not optional. It also names the safety checks that must survive: trust-boundary validation, authorization checks, data-loss guards, and accessibility affordances. These look inert on every tested path, so a green suite before and after will happily bless their removal, yet their absence shows only under attack or failure. A safety check is never dead code. → verify: list written, safety checks named.
- Name the Business Risk: For each planned change, name the business consequence it addresses. If you cannot name what actually breaks or drifts if the smell persists, the refactor is aesthetic. Deprioritize it. → verify: business consequence named for each change.
- Plan (Mikado): Identify the dependency graph. Fix the leaves first. Name only the files and functions that will change. → verify: scope is specific.
- Apply the Safe Sequence: Lock (ensure behavior is captured by tests) → Extract (pull duplicated truth into one source) → Centralize (consolidate scattered access or permission rules) → Split (separate overloaded responsibilities) → Cleanup (formatting, naming, dead code, always last). → verify: only one concern per commit.
- Verify (After): Run the test suite. Verify every item on the Do Not Change list. → verify: same suite green. Diff shows only expected files.
- Commit: Atomic commit "refactor: ..." → verify:
git diff --statshows only expected files. - Completion: Use the Completion Attestation. Include blast radius, preserved behavior list, and verification evidence.
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_god_class.json 835 B
- evals/02_big_bang.json 842 B
- evals/03_truth_centralization.json 1.0 KB
- evals/04_planted_defect.json 1.3 KB
- references/boy_scout_protocol.md 1.2 KB
- references/code_smell_matrix.md 2.7 KB
- references/mikado_method.md 1.1 KB
- references/naming_convention_protocol.md 1.7 KB
- references/solid_principles.md 935 B
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 · 91 lines · 67 tokens per session scan A b7d92dab65a8
resonance-ops-refactor is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 1,578 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…