Validate the Intent Integrity Chain end-to-end: Intent → RQL → Plan → ADR → Spec → Tests → Code. Produces traceability matrix, identifies broken links, flags orphaned code without requirements. [EXPLICIT] Trigger: "validate chain", "traceability", "integrity check", "orphaned code", "governance audit"
From jm-adknpx claudepluginhub javimontano/jm-adk-alfaThis skill is limited to using the following tools:
agents/guardian.mdagents/lead.mdagents/specialist.mdagents/support.mdevals/evals.jsonknowledge/body-of-knowledge.mdknowledge/knowledge-graph.mdprompts/meta.mdprompts/primary.mdprompts/variations/deep.mdprompts/variations/quick.mdtemplates/output.docx.mdtemplates/output.html"A chain is only as strong as its weakest link — find the weak links before they break."
Validates the complete governance chain (Intent → RQL → Plan → ADR → Spec → Tests → Code) for a feature or the entire project. Produces a traceability matrix showing each requirement's chain status. Flags broken links (missing documents, orphaned code, tests without requirements) with severity. Essential for Constitution compliance and quality gate G1. [EXPLICIT]
.specify/requirements/ for RQL files.specify/plans/ for plan files.specify/adr/ for Architecture Decision Records.specify/specs/ for feature specificationstests/ or *.test.* files for test files| RQL | Plan | ADR | Spec | Tests | Code | Status |
|-----|------|-----|------|-------|------|--------|
| RQL-001 | plan-2026-03-22-auth | ADR-001 | spec-auth | auth.test.js | auth.js | COMPLETE |
| RQL-002 | plan-2026-03-22-cms | — | — | — | — | CRITICAL: No downstream |
| — | — | — | — | — | utils.js | HIGH: Orphaned code |
{complete}/{total} = chain health %| Anti-Pattern | Why It's Bad | Do This Instead |
|---|---|---|
| Only tracing forward (RQL → Code) | Misses orphaned code | Also trace backward (Code → RQL) |
| Ignoring test-to-requirement links | Tests without purpose drift | Every test must trace to a requirement |
| Accepting "we'll add tests later" | Technical debt compound interest | Block at G2 until tests exist |
| Manual chain tracking | Error-prone, doesn't scale | Automate with grep/glob scanning |
| Treating all gaps equally | Wastes time on low-impact items | Severity classification guides priority |
requirements-engineering — Creating RQL files that start the chaintest-strategy — Ensuring tests exist for the chaindiscovery-orchestration — Generating plan files as part of the chainsocratic-debate — Resolving ambiguities found during chain validationExample invocations:
| Scenario | Handling |
|---|---|
| Empty or minimal input | Request clarification before proceeding |
| Conflicting requirements | Flag conflicts explicitly, propose resolution |
| Out-of-scope request | Redirect to appropriate skill or escalate |
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.