d4e72f280e
- Delete .mcp.json + .claude/rules/repo-mem.md; drop .repo-mem from .gitignore - Remove repo-mem / substrate_score / repo_search references from all .md - Move 15 EVOLV skills from .agents/skills/ to .claude/skills/ so they are auto-discovered by the Claude Code harness and invokable via the Skill tool - Retire .agents/skills/evolv-orchestrator (duplicate of the subagent at .claude/agents/evolv-orchestrator.md); orchestrator lives as a subagent only - Drop OpenAI-format agent yaml metadata from each skill (not needed for CC) - Update CLAUDE.md, CONTRACTS.md, AGENTS.md to point at the new locations and disambiguate skills (.claude/skills/) vs subagents (.claude/agents/) - Fix CLAUDE.md tick-loop wording (opt-in per-node, not a fixed 1000ms) - Widen .claude/rules/ paths frontmatter so node-architecture and telemetry rules trigger on more relevant files; add frontmatter to flow-layout rule - Bump CONTRACTS.md review date to 2026-05-19; add step 7 to the contract- change workflow (review example flows when topic usage changes) - Bump nodes/generalFunctions pin (Home.md substrate_score reference removed) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2.0 KiB
2.0 KiB
name, description
| name | description |
|---|---|
| evolv-commissioning-validation | Plan and verify EVOLV commissioning readiness. Use when defining FAT/SAT test plans, acceptance criteria, loop checks, simulation-to-field validation, startup sequencing evidence, and rollout gates for operational deployment. |
EVOLV Commissioning Validation
Mission
Convert implementation changes into deployment-ready evidence with clear acceptance gates.
Harness Execution Contract
- Start from impacted contracts, modes, and site-operational constraints.
- Define invariants before edits:
- validation criteria are measurable and reproducible
- startup and failover behavior is proven, not assumed
- rollback path is explicit
- Produce evidence artifacts tied to concrete tests/checks.
Scope
- Cross-node behavior spanning control, measurement, and integrations
- Test plans and validation docs under repository documentation paths
- Node-level suites where commissioning evidence is derived
Workflow
- Build FAT/SAT matrix from impacted contracts and risk areas.
- Define pass/fail criteria and required instrumentation visibility.
- Execute or script reproducible validation checks.
- Capture evidence with timestamps, commands, and outcomes.
- Define rollout gates and rollback triggers.
Standards
- Prefer deterministic replayable checks over ad-hoc validation.
- Include negative-path and recovery-path tests.
- Tie each acceptance criterion to a concrete artifact.
- Keep operator handoff notes concise and actionable.
Test Expectations
Cover:
- startup/shutdown commissioning sequences
- failover and reconnect scenarios
- alarm/interlock behavior under commissioning cases
- post-deploy smoke checks and regression shortlist
Deliverables
Return:
- FAT/SAT-style validation matrix
- executed evidence summary
- go/no-go risks and mitigations
- rollback plan and monitoring checklist
Decision interview triggers:
- reduced commissioning scope under schedule pressure
- acceptance of unresolved high-severity risks
- rollout sequencing choices with operational impact