adapters/hermes/skills/cg-verification/SKILL.md
Activates when verifying implementation against contracts, when claiming work is complete, or when assessing whether tests actually prove contract satisfaction. Use for evidence-based acceptance.
npx skillsauth add dominonotesexpert/context-governance cg-verificationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You verify that implementations satisfy contracts. Tests passing is NOT enough — you verify contracts are met.
<HARD-GATE> Before accepting ANY implementation: 1. Call `governance_load_role_context(role="verification", module="<target>", baseline_constraints="<from SA>")` to load required documents 2. Call `governance_enforce_hardgate(role="verification", loaded_docs=[...], module="<target>")` to verify completeness 3. If FAIL: STOP and report missing documentsRequired documents: 0. Baseline constraints provided by System Architect (do NOT load PROJECT_BASELINE directly)
docs/agents/system/SYSTEM_INVARIANTS.mdMODULE_CONTRACT.mddocs/agents/verification/ACCEPTANCE_RULES.mdVERIFICATION_ORACLE.md (if exists)Do NOT accept work without reading the acceptance criteria first. </HARD-GATE>
Read VERIFICATION_ORACLE.md for the target module.
For each oracle check: test evidence, runtime evidence, code evidence.
| Verdict | Criteria | |---------|----------| | pass | All obligations met + evidence present + no blocking risks | | pass_with_risk | Core contract met + residual risk documented | | fail | Contract obligation not met OR contradicted by evidence | | insufficient_evidence | No clear proof → must escalate |
Must include: which items verified, what evidence used, which items insufficient, what risks remain.
REGRESSION_MATRIX.mdgovernance_record_verificationgovernance_complete_taskgovernance_record_escalationdevelopment
Validates Context Governance compliance — task routing, protected artifact checks, receipt management, and pre-commit gates. For use with Hermes Agent.
development
Activates when documents conflict, when historical mitigations are treated as baselines, when code is treated as design truth, when authority hierarchy needs adjudication, or when PROJECT_BASELINE has been created/updated and derived documents need to be generated or refreshed. Use for system-level truth arbitration and baseline derivation.
development
Orchestrates Context Governance role chain. Classifies tasks, determines routes, and executes each role sequentially via delegation. Use this as the entry point for any governed task in Hermes.
testing
Activates when defining module contracts, boundaries, dataflow, or workflows. Use when a module's responsibilities, inputs/outputs, or upstream/downstream interfaces need to be specified or updated.