tim-hub/powerball-harness / harness/skills/harness-review
harness-review
VerifiedMulti-angle code and plan review with security, scope, and UI profiles. Use when reviewing code, plans, PRs, or running pre-merge quality gates.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.2 KB |
| references/code-review.md | markdown | 2.1 KB |
| references/codex-closeout.md | markdown | 2.6 KB |
| references/codex-review.md | markdown | 1.2 KB |
| references/dual-review.md | markdown | 2.8 KB |
| references/governance.md | markdown | 2.2 KB |
| references/opencode-review.md | markdown | 2.3 KB |
| references/plan-review.md | markdown | 891 B |
| references/result-schema.md | markdown | 2.7 KB |
| references/scope-review.md | markdown | 344 B |
| references/security-profile.md | markdown | 11.8 KB |
| references/team-debate.md | markdown | 2.0 KB |
| references/ui-rubric.md | markdown | 7.3 KB |
| references/verdict-framework.md | markdown | 1.6 KB |
references/code-review.md
View on GitHub# Code Review Flow
## Summary
Collect the diff, examine implementation, spec, Plans, regressions, and tests, then block only the issues that must be blocked.
## Step 1: collect diff
Check:
```bash
git status --short
git diff --stat "${BASE_REF:-HEAD}"
git diff "${BASE_REF:-HEAD}"
git ls-files --others --exclude-standard
```
Untracked files do not appear in `git diff`. Always include them in scope.
## Step 2: static scans
AI Residuals:
```bash
bash scripts/review-ai-residuals.sh --base "${BASE_REF:-HEAD}"
bash scripts/review-weak-supervision-report.sh
```
Candidates:
- `mockData`
- `dummy`
- `fake`
- `localhost`
- `TODO`
- `FIXME`
- `it.skip`
- `describe.skip`
- `test.skip`
- `expect(true).toBe(true)`
Finding a candidate alone does not make it major. Assess in diff context whether it directly leads to a shipping incident or misconfiguration.
## Step 3: eight review lenses
| Lens | What to check |
|---|---|
| Security | SQL injection, cross-site scripting, secret leak, permission bypass |
| Performance | N+1, needless heavy IO, blocking work |
| Quality | duplicate logic, unclear boundary, fragile parsing |
| Accessibility | labels, focus, contrast, keyboard path |
| AI Residuals | fake success, skipped tests, mock-only implementation |
| Spec Alignment | Contradictions with the spec source-of-truth |
| Plans Alignment | Alignment with `Plans.md` task / DoD / Depends |
| Regression Safety | Regressions in existing behavior, mirrors, CLI/skill UX |
## TDD compliance
For tasks that require TDD, look for evidence that a failing test was confirmed first.
For docs-only or refactor-only tasks where TDD is excessive, recording the skip reason is sufficient.
## Verdict
1. critical / major present → `REQUEST_CHANGES`
2. Spec source-of-truth / `Plans.md` / regression gate fails → `REQUEST_CHANGES`
3. Decision needed from the user → `decision_needed`
4. Minor / recommendation only → `APPROVE`
5. Insufficient evidence → `REQUEST_CHANGES` or `decision_needed`
## Post-fix re-review
After `REQUEST_CHANGES`, always re-review once fixes are applied.
If the same issue fails two consecutive post-fix re-reviews, force TeamAgent Debate.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |