Validate AI Developer Workflow step outputs and contracts. Use when verifying workflow step completeness before proceeding.
Validates AI Developer Workflow step outputs and ensures contract compliance.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install google-ecosystem@melodic-software<step-type> [spec-path]Validate AI Developer Workflow step outputs and ensure contract compliance.
$ARGUMENTS: <step-type> [spec-path]
step-type: One of plan, build, review, fixspec-path: Optional path to spec file (auto-detected if not provided)| Step | Output Type | Key Requirements |
|---|---|---|
plan | Spec file | Summary, requirements, criteria, approach |
build | Code changes | Commits with prefix, tests pass |
review | Report | PASS/FAIL status, severity-rated issues |
fix | Resolutions | Issues addressed, no new issues |
Parse the step type from arguments:
Valid types: plan, build, review, fix
Plan Contract:
specs/*.mdBuild Contract:
build: prefixReview Contract:
Fix Contract:
fix: prefixFor Plan Step:
# Find latest spec file
ls -t specs/*.md | head -1
# Check required sections
grep -c "## Summary\|## Requirements\|## Acceptance\|## Technical" specs/latest.md
For Build Step:
# Check for build commits
git log --oneline -5 | grep "^[a-f0-9]* build:"
# Check build status
npm run build 2>&1 | tail -5
# or: dotnet build 2>&1 | tail -5
# Check tests
npm test 2>&1 | tail -10
# or: dotnet test 2>&1 | tail -10
For Review Step:
# Check for review report
ls -t .claude/temp/*review*.md 2>/dev/null | head -1
# Verify PASS/FAIL status
grep -E "STATUS:|Result:" review_report.md
For Fix Step:
# Check for fix commits
git log --oneline -5 | grep "^[a-f0-9]* fix:"
# Verify no new issues
# (re-run review step)
For each criterion in the contract:
Generate validation report.
## Workflow Validation Report
### Step Validated
**Step:** {plan|build|review|fix}
**Spec Path:** {path if applicable}
**Timestamp:** {ISO-8601}
### Contract Check
| Requirement | Status | Evidence |
| --- | --- | --- |
| {requirement} | ✅/❌ | {details} |
| {requirement} | ✅/❌ | {details} |
| {requirement} | ✅/❌ | {details} |
### Output Validation
#### {Output Name}
- **Path:** {path}
- **Exists:** ✅/❌
- **Format Valid:** ✅/❌
- **Issues:** {if any}
### Success Criteria
| Criterion | Met | Evidence |
| --- | --- | --- |
| {criterion} | ✅/❌ | {evidence} |
| {criterion} | ✅/❌ | {evidence} |
### Overall Status
**Result:** VALID | INVALID
**Summary:** {brief summary of validation result}
### Issues Found
1. **{Severity}:** {description}
- **Location:** {where}
- **Expected:** {what should be}
- **Actual:** {what was found}
- **Recommendation:** {how to fix}
### Next Steps
- {Recommended action if invalid}
- {Continue to next step if valid}
# Check spec exists
test -f specs/*.md && echo "Spec exists"
# Check sections
for section in "Summary" "Requirements" "Acceptance" "Technical"; do
grep -q "## $section" specs/*.md && echo "$section: OK"
done
# Check commits
git log --oneline -10 | grep "build:"
# Check tests
npm test --if-present || echo "No npm tests"
dotnet test 2>/dev/null || echo "No dotnet tests"
# Check report format
grep -E "^STATUS:|^Result:" review_output.md
# Check severity levels
grep -cE "CRITICAL|HIGH|MEDIUM|LOW" review_output.md
| Avoid | Why | Instead |
|---|---|---|
| Skipping validation | Proceeding with incomplete work | Always validate before next step |
| Partial checks | Missing critical issues | Complete all contract checks |
| Auto-fixing during validation | Scope creep | Validate only, fix separately |
| Ignoring warnings | Technical debt | Address all severity levels |
workflow-validator agent - Automated validationcomposable-step-design skill - Step design patterns