requesting-code-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited requesting-code-review (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<!-- Adapted from obra/superpowers requesting-code-review skill (v5.0.7), MIT-licensed, copyright 2025 Jesse Vincent. Modifications copyright 2026 Joe Amditis. v0.4.0 ports as a consumer category, no research phase per the v0.2.0 architecture, since dispatch mechanic; reviewer preferences live in the project instruction file and memory rather than a research phase. See CREDITS.md. -->
Dispatch a code-review subagent or parallel worker, if your client supports one, to catch issues before they cascade. In Claude Code, dispatch pr-review-toolkit:code-reviewer. Give the reviewer precise context instead of the full session history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work. If the client has no worker capability, perform the same review in sequence in a fresh review pass.
Core principle: Review early, review often.
Independence rule: Before merge, the independent review comes from a model provider other than the one that wrote the code. Scale the reviewer's effort to risk: low for a trivial change, high for behavior, security, data, or broad changes. A same-provider review can still catch issues during a task, but it does not count as the independent review.
Mandatory:
Optional but valuable:
1. Get git SHAs:
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)2. Dispatch code-reviewer subagent:
Use the client's worker capability and fill the template at code-reviewer.md. In Claude Code, use the Task tool with pr-review-toolkit:code-reviewer.
Placeholders:
{WHAT_WAS_IMPLEMENTED} - What you just built{PLAN_OR_REQUIREMENTS} - What it should do{BASE_SHA} - Starting commit{HEAD_SHA} - Ending commit{DESCRIPTION} - Brief summary3. Pin the snapshot:
Record the base, head, changed paths, and a diff digest. Ask the reviewer to repeat them. Discard a result that covers a different snapshot. If you change the code after review, the old result no longer covers the head.
4. Act on feedback:
Do not switch reviewers because the first one found problems or returned malformed output. Switch only when the reviewer's provider is unavailable. There is no cap on review rounds; stop when the reviewer finds no actionable defect in the exact head.
[Just completed Task 2: Add verification function]
You: Let me request code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[Dispatch a code-review worker from a different provider]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_OR_REQUIREMENTS: Task 2 from docs/superpowers/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
[Subagent returns]:
Strengths: Clean architecture, real tests
Issues:
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Fix progress indicators]
[Continue to Task 3]Subagent-Driven Development:
Executing Plans:
Ad-Hoc Development:
Never:
If reviewer wrong:
See template at: requesting-code-review/code-reviewer.md
Read Cross-provider code review when an independent reviewer must verify a completed change.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.