Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/ai-agency/hyperflow/skills/audit

audit

Flagged

Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a multi-level (L1-L5) review with a standalone Reviewer; on NEEDS_FIX, offers to apply findings via /hyperflow:plan. Trigger with /hyperflow:audit, "review this change", "review my PR", "audit the diff", "code review".

FileKindSize
SKILL.mdskill md26.8 KB
references/examples.mdmarkdown2.1 KB
references/memory-system.mdmarkdown15.3 KB
references/output-style.mdmarkdown8.4 KB
references/review-levels.mdmarkdown4.4 KB
references/reviewer-prompt.mdmarkdown3.4 KB
references/security.mdmarkdown4.6 KB

references/examples.md

View on GitHub
## Examples

### Default — review uncommitted changes at L2

```
/hyperflow:audit

── Review Result ──────────────────────
Scope: git diff HEAD + git diff --staged (3 files)
Level: L2
Verdict: NEEDS_FIX

[Critical]
- src/auth/middleware.ts:42 — token compared with == instead of timingSafeEqual; switch to crypto.timingSafeEqual.

[Important]
- src/auth/middleware.ts:18 — missing rate-limit on /login. Wire token-bucket from src/lib/limiter.ts.

[Suggestions]
- src/auth/types.ts:5 — TokenClaims interface could be a discriminated union for refresh vs access tokens.
───────────────────────────────────────
Agents: 2 total · ~Xk tokens

?  Audit found 3 issues — apply fixes?
   Fix all (Recommended)   — Critical + Important + Suggestions
   Critical + Important    — skip Suggestions
   Critical only           — fix the must-haves
   No, leave as-is         — stop; handle manually
```

### Explicit target + deep review

```
/hyperflow:audit src/payments --level 4

── Review Result ──────────────────────
Scope: src/payments/** (12 files)
Level: L4
Verdict: PASS
[Praise]
- src/payments/processor.ts:120 — idempotency key handling is correct under retries.
───────────────────────────────────────
Audit clean — no fixes needed.
```

### PR review

```
/hyperflow:audit --pr 145 --level 3

(reviews the diff between the PR's base and head; same output format)
```

## Resources

- [DOCTRINE.md](../../hyperflow/DOCTRINE.md) — orchestration rules (especially #8 structural gates, #12 per-step agents).
- [review-levels.md](references/review-levels.md) — full checklist for L1-L5.
- [reviewer-prompt.md](references/reviewer-prompt.md) — reviewer template.
- [security.md](references/security.md) — security scan policy (mandatory at L3+).
- [memory-system.md](references/memory-system.md) — how patterns are persisted.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall