Run Phase 4 (feedback routing) after an adversarial review FAIL. Routes adversary findings to the earliest affected phase, checks iteration limits, and escalates to human if limits are exceeded.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Runs the feedback integration loop (Phase 4). Reads adversary findings from the latest verdict, routes each to the appropriate phase, explicitly enters Phase 4, and then transitions the pipeline back for rework.
Run after /vcsdd-adversary returns a FAIL verdict. Normally starts from phase 3; if routing was already started, phase 4 is also valid.
reviews/sprint-N/output/verdict.jsonreviews/sprint-N/output/findings/FIND-NNN.jsonstrict: phase 3 max 5lean: phase 3 max 31a: [FIND-001, FIND-003] <- spec ambiguity
2a: [FIND-002] <- missing test
2b: [FIND-004, FIND-005] <- implementation bug
adversary-finding bead3, transition 3 -> 44, transition to the selected target phaserouteFeedback(featureName, targetPhase, reason) from scripts/lib/vcsdd-state.js instead of hand-rolling transitionPhase() callsrouteFeedback() only proceeds when the latest sprint verdict is FAILdimension controls grading. category controls routing. The routeToPhase field on each finding is authoritative.
| Category | Typical Severity | Route To |
|---|---|---|
spec_ambiguity | any | Phase 1a |
spec_gap | any | Phase 1a |
verification_tool_mismatch | any | Phase 1b |
requirement_mismatch | any | Phase 2b |
missing_edge_case | critical | Phase 1a |
missing_edge_case | high/medium/low | Phase 2a |
test_coverage | any | Phase 2a |
test_quality | any | Phase 2a |
implementation_bug | any | Phase 2b |
error_handling | any | Phase 2b |
security_surface | any | Phase 2b |
code_structure | any | Phase 2c |
naming | any | Phase 2c |
duplication | any | Phase 2c |
proof_gap | any | Phase 5 |
invariant_violation | any | Phase 5 |
purity_boundary | any | Phase 1b by default; Phase 2c or Phase 5 only when the architecture itself remains valid |
/vcsdd-feedback
/vcsdd-feedback --show-routing # display full routing table before applying
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use this skill when running or interpreting VCSDD adversarial reviews. Provides calibration guidance for the Adversary agent, finding severity classification, and anti-leniency enforcement patterns.
The English summary is being prepared. Showing the original description.
Run Phase 3 (adversarial review) for the active VCSDD feature. Spawns a fresh vcsdd-adversary agent with zero Builder context to review implementation against spec. Produces binary PASS/FAIL verdict per dimension.
The English summary is being prepared. Showing the original description.
Create a git commit for the current VCSDD phase. Auto-generates a conventional commit message from state.json including phase, sprint, gate verdict, and affected bead IDs. Tags with vcsdd/<feature>/phase-<id>.
The English summary is being prepared. Showing the original description.
Run the strict-mode sprint contract review after Phase 2c. Spawns a fresh vcsdd-adversary instance to review `contracts/sprint-N.md` and writes a PASS/FAIL verdict under `reviews/contracts/sprint-N/output/`.
The English summary is being prepared. Showing the original description.
Run Phase 6 (convergence check) for the active VCSDD feature. Validates four-dimensional convergence: finding diminishment, finding specificity, criteria coverage, and duplicate detection.
The English summary is being prepared. Showing the original description.
Use this skill during Phase 6 convergence checks. Provides four-dimensional convergence analysis, hallucination detection, and duplicate finding identification.
The English summary is being prepared. Showing the original description.