Resonance Ops System Health

/resonance-ops-system-health: measure the pulse, diagnose the drift

> Role: the Doctor and benchmark engine. > Invoked as: /system-health (to run a full health check). > Input: Codebase State. > Output: Health Score (0-100) + Qualitative Flags. > Definition of Done: A final score is calculated using Test/Lint/Build weights. Qualitative flags for Auth Inconsistency, Env Fragility, Shallow Tests, and State Drift are explicitly marked.

You need to measure the system's pulse. A "Healthy" system has high confidence (tests pass), low entropy (clean lint), synced state (Map == Territory), consistent authorization, and environmental safety.

Prerequisites (fail fast)

• [ ] Project is initialized (has a .resonance/ directory).

Algorithm (Execution)

Copy this checklist and tick items as you go.

1. Automated Vitals: Detect the project's toolchain first (see Toolchain Detection); do not assume npm. Run the project's own commands:

• Tests: the project's test command, with coverage if available. (Weight: 40%)
• Lint: the project's lint command. (Weight: 30%)
• Build: the project's build command. (Weight: 30%)

1. Manual Vitals (The Qualitative Flags):

• Drift Check: Read 01_state.md. Does it match git log -10? (Flag: DRIFT_DETECTED)
• Auth Model Consistency: Do routes, policies, and UI templates agree on access rules? Delegate to resonance-ops-security. (Flag: AUTH_INCONSISTENT)
• Environment Assumption Check: Are there hardcoded paths or missing fallbacks? Would the app survive deploying to a fresh environment? (Flag: ENV_FRAGILE)
• Test Depth Check: Do tests cover failure paths and unauthorized paths? Quick scan against the 8-Path Matrix. Delegate to resonance-ops-qa. (Flag: TEST_SHALLOW)
• Stale Tests Check: Do tests encode product decisions that have since changed? (Flag: STALE_TESTS)

1. Calculation:

• Score = (Test% * 0.4) + (LintClean * 0.3) + (BuildPass * 0.3)
• Compile the qualitative flags.

1. Synthesis: Output the Health Report.

Recovery

• Score Model note (Claude): Strong native reasoning. Do not narrate "let me think step by step" or pad with chain-of-thought; think, then act. Prefer the dedicated file and search tools over shell. State assumptions briefly, then proceed.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: manusco
• Source: manusco/resonance
• License: MIT

Install and usage instructions live in the source repository linked above.