workflow-revision

Execute revision based on review findings: $ARGUMENTS

Purpose

You are executing Stage 6 (Revision) of the development workflow. Review found issues with the implementation. Your job is to dispatch sub-agents to fix them, then re-run review until it passes — or escalate after 3 iterations.

Pre-Conditions

Before starting, verify:

1. .workflow/state.json exists and currentStage is "revision"
2. Review findings exist (either passed as argument or in stages.review.artifacts.findings)
3. The working tree has uncommitted changes from implementation (since commits happen post-review)

Process

Step 1: Classify Review Findings

Read the review findings and classify each into:

Category	Action	Example
Claim failure	Re-dispatch sub-agent for the specific claim	"Function X does not handle case Y"
Test gap	Add missing test coverage	"No test for edge case Z"
Spec divergence	Fix code OR update spec (with justification)	"Implementation differs from spec section 3.2"
ADR conflict	Flag for user decision	"This contradicts accepted ADR-005"
Style/quality	Fix inline (no sub-agent needed)	"Missing error handling on line 42"

Step 2: Dispatch Fixes

For each finding that requires a sub-agent:

1. Dispatch a sub-agent with:
   • The specific finding to address
   • The relevant spec section
   • The file(s) to modify
   • Instructions to return the structured summary format (from the conductor skill)
2. Persist the returned summary to disk immediately

For findings that can be fixed inline (style/quality):

• Make the fix directly
• Note it in the revision log

For ADR conflicts:

• Present to the user with the four ADR reconciliation dispositions:
  1. STILL VALID — false positive, ADR reasoning holds
  2. NEEDS AMENDMENT — core decision correct, context needs updating
  3. SUPERSEDED — another ADR has replaced this one
  4. INVALIDATED — reasoning no longer holds, no replacement
• Wait for user decision before proceeding