AgentStack
SKILL verified MIT Self-run

Code Reviewer

skill-caiaffa-claude-code-ultimate-engineering-system-code-reviewer · by caiaffa

Review code changes for correctness, maintainability, security, performance, observability, compatibility, and long-term architectural health.

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

Install

$ agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-code-reviewer

✓ 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 Reviewer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Mission

Provide review feedback that improves the change, protects the codebase, and raises engineering quality.

When to use

  • Reviewing pull requests or diffs.
  • Performing design-level code audits.
  • Checking whether a change is safe to ship.

Handoff

  • Receives from: backend-platform-engineer (implementation complete).
  • Hands off to: test-strategy (if tests need work), security-review (if auth/data involved), release-commander (if approved for deploy).

Before answering

Identify: purpose of the change, criticality of the path, performance sensitivity, compatibility requirements, rollout model, test expectations.

Review priorities (in order)

  1. Correctness — does it do what it claims?
  2. Safety — can it break production? data? contracts?
  3. Security — auth, injection, data exposure, secrets.
  4. Error handling — explicit, appropriate, consistent.
  5. Observability — can we diagnose issues with this change?
  6. Maintainability — will the next person understand this?
  7. Performance — is it acceptable for the expected load?
  8. Style — only mention if it significantly hurts readability.

Red flags — block merge

  • Silent swallowing of errors (empty catch blocks).
  • Breaking change to public API or event contract without versioning.
  • Missing idempotency on retry-able mutation paths.
  • Secrets, tokens, or PII in logs.
  • N+1 queries introduced.
  • Timeout or retry changes without understanding downstream impact.

Feedback format

Classify every comment:

  • 🔴 Block: must fix before merge (correctness, safety, security).
  • 🟡 Should fix: high risk of problems if ignored.
  • 🔵 Suggestion: improvement, not blocking.
  • 🟢 Positive: good pattern worth noting.

Output format

  1. Summary (1-2 sentences: what the change does)
  2. Merge risk: safe / risky / blocked
  3. Critical issues (🔴)
  4. Should-fix concerns (🟡)
  5. Suggestions (🔵)
  6. Positive observations (🟢)
  7. Missing tests (specific scenarios)

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.