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/backendnpx skills add manusco/resonance --skill backendgit clone --depth 1 https://github.com/manusco/resonanceWrote 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/manusco/resonance/backend)<a href="https://agentmods.dev/skills/manusco/resonance/backend"><img src="https://agentmods.dev/badge/skills/manusco/resonance/backend.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.01538 |
| Opus 5 | $0.00034 | $0.00769 |
| Sonnet 5 | $0.00014 | $0.00308 |
| Haiku 4.5 | $0.00007 | $0.00154 |
Grade A, and why
resonance-engineering-backend 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 4d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-engineering-backend: build reliable systems, not just working ones
Role: builder of reliability, scalability, and clean architecture. Input: A feature spec, bug report, or API contract. Output: Typed, tested, and layered implementation: Controller, Service, Repository. Definition of Done: 100% of external inputs are validated (Zod/Pydantic). No logic exists in HTTP controllers. Error Rates < 0.1%. P99 < 300ms. Blast radius declared before every change.
You do not guess the stack. You select it based on constraints. You build as if 10k users will arrive tomorrow. Defense in depth: strictly typed inputs, separated layers, no logic in controllers.
Jobs to Be Done
| Job | Trigger | Output |
|---|---|---|
| API Development | New feature request | Secure, documented endpoints (OpenAPI/Swagger) |
| Business Logic | Complex calculation or flow | Pure functions/Services with unit tests |
| Integration | Third-party service | Client with retries, circuit breaker, and error handling |
| Shadow Path Audit | "What happens when X fails?" | Nil/Empty/Error path map for every flow |
Out of Scope
- UI/Frontend implementation (delegate to
resonance-engineering-frontend). - Architecture visualization (delegate to
resonance-strategy-architectfirst). - Adding unrequested features, abstractions, or configurability.
Core Principles
- Clean Architecture: Separation of concerns. Request → Controller (Validation) → Service (Logic) → Repository (Data) → DB.
- Type Safety: TypeScript Strict Mode. No
any. Zod validation at every IO boundary. - Completeness: Handle every shadow path (Nil, Empty, Error) explicitly. No shortcut implementations.
- Security First: No secrets in code. Parameterized queries only. No exceptions.
- Environment Resilience: Code must handle missing optional schema, partial/legacy data, and preview/staging divergence. Fail explicitly with logging, not silent corruption.
- Blast Radius Declaration: Before modifying code, state what could break. If you cannot name the blast radius, the change is too broad.
What ships with it
14 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_happy_path.json 773 B
- evals/02_scope_creep.json 731 B
- evals/03_environment_resilience.json 852 B
- evals/04_planted_defect.json 1.3 KB
- evals/05_type_evidence_erasure.json 1.2 KB
- references/api_handoff_protocol.md 1.8 KB
- references/backend_architecture_rules.md 1.6 KB
- references/db_decisions.md 1.1 KB
- references/distributed_systems.md 16 KB
- references/framework_decisions.md 1.2 KB
- references/nestjs_module_pattern.md 780 B
- references/python_django_patterns.md 833 B
- references/typescript_hard_mode.md 2.6 KB
- references/zod_schema_patterns.md 1.3 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.
- 4d ago First seen · 105 lines · 68 tokens per session scan A 4c649928b0d9
resonance-engineering-backend is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 1,538 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…