{"id":17202,"plugin_id":"plugins_6a746bbb64d48191942c65a16a1eb19f","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:14:01.431Z","digest":"30d47c652b3b2d87499ba6a642f5a806edf926050bc01c063a61cb68d36b7bdb","against":null,"payload":{"name":"machine-conformance","description":"Audit, score, or challenge an existing AI harness against Frontier Infra The Machine, determine Machine versus Orchestrator shape, run the canonical kit, gather evidence, design chaos tests, and prevent unsupported conformance claims.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":235}],"skill_md_contents":"---\nname: machine-conformance\ndescription: Audit, score, or challenge an existing AI harness against Frontier Infra The Machine, determine Machine versus Orchestrator shape, run the canonical kit, gather evidence, design chaos tests, and prevent unsupported conformance claims.\n---\n\n# Audit Machine conformance\n\nRead `../../references/conformance.md`, `../../references/system-architecture.md`, and `../../references/threat-model.md`.\n\nAudit an explicitly identified target deployment. Do not automatically score\nthe repository being edited, the builder's process, this plugin, or the SDK's\ndistribution as a condition of using Frontier to build an application.\n\n## Workflow\n\n1. Audit the deployment wiring, not a standard, library, diagram, or README.\n2. Determine shape from executed control flow: zero-token deterministic driver versus model-selected closed transitions with write-ahead decision persistence.\n3. Inventory code/config for every box, governance control, foundation service, operational obligation, critical component, and mutation path.\n4. Treat prose as a claim to test. Cite concrete file/config/runtime evidence.\n5. Run the published conformance CLI — it bundles The Machine's static kit; do not hunt for a checked-out kit or recreate scoring logic:\n\n   ```sh\n   npx -y @frontier-infra/audit run <deployment-repository> --out <dir-outside-that-repo>\n   ```\n\n6. Execute or mark `NOT-RUN` the kill/resume, replay, lying-worker, verifier removal/staleness, duplicate effect, quarantine, budget, override, forged rollback, bypass, and dead-workforce health fixtures.\n7. Verify receipt chains and health timestamps; confirm the audit sink survives operator halt of the deployment scope. If the deployment emits the four-layer runtime health contract, evaluate it with the published reducer (`npm install @frontier-infra/protocol`, then `evaluateRuntimeHealth(record)`) and treat any non-pass aggregate as fail-closed.\n8. Report a deployment as a `structural candidate` when only static architecture/code mapping has been reviewed. Report a shape-stamped conformance level only when the required runtime evidence passes. Otherwise report current evidence, gaps, and the next lowest-cost falsifying test.\n\n## Output\n\nReturn an obligation matrix with `PASS`, `FAIL`, or `NOT-RUN`; evidence locations; executed commands; limitations; spec/kit versions; and a dated claim or explicit `UNSCORED` verdict.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}