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/codex-closeout.md
View on GitHub# Quick / Codex Closeout
## Summary
For small changes: fix the scope, verify Codex advice against the actual code, and stop when the result is clean.
## Target selection decision tree
1. Working tree is dirty
- Recommended: uncommitted changes only
- base: `HEAD`
- Include untracked files
2. PR branch / feature branch has commits
- Recommended: `upstream..HEAD` or `origin/main..HEAD`
- If working tree is also dirty, use `AskUserQuestion` to choose: uncommitted only / all / commits only
3. Clean tree with no branch diff
- Recommended: most recent 1 commit
- Most recent 5 commits if needed
4. User specified `--base` / `--commit`
- Honor the explicit specification
## Advisory rule
Codex findings are advisory — they are reference opinions, not facts.
Always do the following:
- Read the cited location in the actual code
- Confirm reproducibility with the diff and tests
- Separate into accepted findings / rejected findings
- For each rejected finding, document why it was not adopted
## Stop-on-clean
Stop-on-clean: do not run additional reviews just for appearance after a clean result.
Example:
- Codex review: no major issues
- Focused tests: pass
- Manual spot check: pass
Stop in this state. Run additional heavy reviews only before release, for security-sensitive changes, spec source-of-truth changes, or when the user explicitly requests one.
## Helper contract
`harness/scripts/harness-review-closeout.sh` is a helper that locks down the execution plan for lightweight closeout.
Supported inputs:
- `--dry-run`
- `--parallel-tests`
- `--base REF`
- `--commit REF`
- `--uncommitted`
- `--test CMD`
- `--json`
Examples:
```bash
bash harness/scripts/harness-review-closeout.sh --dry-run --uncommitted
bash harness/scripts/harness-review-closeout.sh --base origin/main --parallel-tests --test "bash harness/tests/test-harness-review-governance.sh"
bash harness/scripts/harness-review-closeout.sh --commit HEAD --json
```
If Codex is unavailable:
- Fall back to full manual pass
- Do not treat failure as success
- Record `codex_available: false` in the final report
## Final report
Required fields:
- review command
- tests
- accepted findings
- rejected findings
- clean result
- fallback reason
Minimum JSON structure:
```json
{
"schema_version": "harness-review-closeout.v1",
"target": "working_tree | branch_range | commit",
"base_ref": "HEAD",
"review_command": "bash harness/scripts/codex-companion.sh review --base HEAD --json",
"tests": [],
"accepted_findings": [],
"rejected_findings": [],
"clean_result": true,
"codex_available": true,
"fallback": ""
}
```
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 |