AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Code Review

skill-shivae372-claude-bootstrap-code-review · by shivae372

Structured code review. Invoke before committing, before opening a PR, or when you want feedback on changes. Auto-activates on "review this code", "check my changes", "look for issues", "review before I push". Routes to code-reviewer sub-agent to keep main context clean.

↗ Repository
— No reviews yet
0 installs
3 views
0.0% view→install

Install

$ agentstack add skill-shivae372-claude-bootstrap-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.

Are you the author of Code Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Purpose

Run a structured code review using the code-reviewer sub-agent. Returns findings organized by severity. The sub-agent runs in its own isolated context window.

Steps

1. Get the Scope

Determine what to review:

# If reviewing uncommitted changes
git diff HEAD

# If reviewing staged changes
git diff --cached

# If reviewing a specific file
# (user will have specified)

2. Delegate to Sub-agent

Use the code-reviewer agent to: review [the diff / file / changes described above]
Focus on: correctness, security, performance, and adherence to project conventions in CLAUDE.md

3. Present Findings

Format the sub-agent's output as:

## Code Review

### 🔴 Critical (must fix)
[list]

### 🟠 High (should fix)
[list]

### 🟡 Medium (consider fixing)
[list]

### ✅ Looks Good
[things done well]

**Verdict**: [Approved / Needs changes / Blocking issues found]

4. If No Issues

✅ Code review complete — no significant issues found.
[Optional: one positive observation]
Ready to commit.

Rules

  • Never skip the sub-agent for large diffs — isolation protects the main context
  • Always read CLAUDE.md conventions before reviewing
  • If the user asks to fix issues found, do them one at a time and re-review each fix

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.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML