AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Requesting Code Review

skill-skywalkercyt-mp-implement-requesting-code-review · by skywalkercyt

Dispatch an independent reviewer subagent over a diff. Use when completing a task or feature, or before merging.

No reviews yet
0 installs
21 views
0.0% view→install

Install

$ agentstack add skill-skywalkercyt-mp-implement-requesting-code-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-skywalkercyt-mp-implement-requesting-code-review)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Requesting Code Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Requesting Code Review

> Adapted skill — discipline originating in Superpowers v5.1.0 (MIT, Jesse Vincent), rewritten in mattpocock-skills style. Drives the independent review in /mp-implement-issue step 8 and the code-quality reviewer in /mp-implement Phase 3 (via subagent-driven-development).

An independent reviewer checks the work before merge — self-review doesn't count. Review early, review often: after each task or slice, and always before merge to main.

The reviewer is a subagent with fresh context, so it gets a crafted brief, not your session history. Fresh eyes on the work product are what make the review independent; your reasoning so far is noise to it.

Fix the range first

BASE_SHA=$(git merge-base origin/main HEAD)  # the slice's branch point
HEAD_SHA=$(git rev-parse HEAD)

Confirm the base resolves (git rev-parse $BASE_SHA) and the three-dot diff (git diff $BASE_SHA...$HEAD_SHA) is non-empty before dispatching. A bad ref or empty diff fails here, not inside the subagent.

Dispatch the reviewer

Spawn a subagent with this brief filled in:

You are reviewing a change before merge. Work from this brief and the repo only.

## What was built
{DESCRIPTION}
## Requirements
{PLAN_OR_REQUIREMENTS — issue body, acceptance criteria, or plan file}
## Diff under review
git diff {BASE_SHA}...{HEAD_SHA}   (commits: git log {BASE_SHA}..{HEAD_SHA} --oneline)

Report findings as Critical (must fix) / Important (fix before proceeding) /
Minor (later), each with file:line, why it matters, and the fix. Severity is
actual, not diplomatic. End with a verdict: ready to merge, or what changes first.

Split big reviews into axes

A review can split into independent axes (e.g. Standards vs Spec) as parallel subagents, so neither axis pollutes the other. /mp-implement-issue step 8 does exactly this and carries its own inlined briefs — there, follow step 8 instead of the template above.

Act on the findings

What to do with the Critical / Important / Minor findings — evaluate each technically, fix, or push back with evidence — is governed by receiving-code-review.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.