lidge-jun/codexclaw / plugins/codexclaw/skills/dev-code-reviewer
cxc-dev-code-reviewer
VerifiedUse for code/PR/diff review and refactor audits. Triggers: review this, before merge, antipattern, 리뷰, 코드 리뷰, 머지 전에 확인.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.0 KB |
| agents/openai.yaml | config | 144 B |
| references/ai-assisted-review.md | markdown | 5.8 KB |
| references/common-antipatterns.md | markdown | 2.1 KB |
| references/external-review-evidence.md | markdown | 416 B |
| references/finding-verification.md | markdown | 1.9 KB |
| references/quality-thresholds.md | markdown | 1.2 KB |
| references/review-feedback.md | markdown | 2.0 KB |
| references/review-process.md | markdown | 2.8 KB |
| references/security-performance-review.md | markdown | 2.9 KB |
| references/subagent-and-slop-review.md | markdown | 3.3 KB |
| references/tech-debt.md | markdown | 5.1 KB |
references/finding-verification.md
View on GitHub## Changed-File Coverage Ledger (REVIEW-COVERAGE-01, DEFAULT)
Account for every changed file as `reviewed`, `skipped (reason)`, or
`out-of-scope (reason)` before verdict. Generated, lock, vendored, binary, and
outside-domain files may be skipped only with an explicit reason. Any
unaccounted file makes the verdict incomplete.
## Finding Falsification (REVIEW-FALSIFY-01, DEFAULT)
Before reporting a finding:
1. State it as a testable claim.
2. Search tests, guards, caller context, and docs for contradictory evidence.
3. Downgrade or retract the claim when contradictory evidence disproves it.
4. Retain the claim when it survives the falsification attempt.
Every finding includes `verification: verified|unverified`. Use `unverified`
when the falsification attempt could not be completed or evidence is incomplete.
## Interdiff Re-Review (REVIEW-INTERDIFF-01, DEFAULT)
Anchor the re-review to both the previous reviewed commit/range and the new head;
record those anchors in the review. Review only the interdiff, preserve unresolved
findings, verify each claimed fix, and process new findings normally. Revisit
unchanged code when a cross-file dependency changed. If either anchor is missing,
history was rewritten ambiguously, or the interdiff cannot be trusted, fall back
to a full review of the current base-to-head diff.
**REVIEW-WORKTREE-01 (DEFAULT).** Never check out another review ref in the worktree you
were handed. If the review target is already checked out in the worktree the dispatcher
assigned, review it there; otherwise create or attach a dedicated named worktree and run the
checkout, tests and QA in that one. Record `pwd -P` and the target `HEAD` alongside the
anchors above.
The condition is observable state, not ownership: a reviewer — often a subagent — cannot know
which branch the parent session "owns", but it can always see what is checked out where it
stands.
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: 467k | 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: 467k | 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: 467k | 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: 193k | Updated | Claude CodeCodex | Verified | Install |