Install
$ agentstack add skill-squadcodercom-squadcoder-code-review ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
About
Code Review — senior-engineer pass over a diff/PR
Find what matters and say it clearly. A good review surfaces real defects with evidence, not a list of style opinions. Default to reviewing the changed lines and their blast radius.
Step 0 — orient
- What is this change trying to do? (Read the PR description / commit messages / the diff intent.)
- What's the blast radius — what calls this, what does it call, what data does it touch?
- Get the actual diff (
git diff), don't review from memory.
Review dimensions (in priority order)
- Correctness & edge cases — does it do what it claims? Off-by-one, null/empty/None, error paths,
async races, unhandled rejections, boundary inputs, wrong default. This is most of the value.
- Security — input validation, injection (SQL/command/path traversal), authn/authz checks,
secrets in code/logs, unsafe deserialization, XSS/CSRF for web, SSRF for fetchers.
- Resource & performance — N+1 queries, unbounded loops/memory, missing pagination, blocking I/O
on a hot path, leaks (listeners, handles), needless re-renders.
- API & data contracts — backward compatibility, migration safety, nullable changes, error shapes.
- Readability & maintainability — names, dead code, duplication, function size, matches the
surrounding style. Flag, don't bikeshed.
- Tests — is the new behavior covered? Are the tests meaningful (assert real outcomes) or hollow?
How to report findings
For each finding:
- Severity:
blocker/major/minor/nit. - Location:
file:line(clickable). - What & why: the concrete problem and the failure it causes — quote the code.
- Fix: a specific suggestion (or a diff), not "consider improving this".
Group by severity; lead with blockers. Example: > [blocker] auth.ts:42 — token compared with ==, so an empty token matches when the stored > value is also falsy. Use a constant-time compare and reject empty tokens.
Discipline
- Verify before asserting. Trace the data flow; don't claim a bug you didn't confirm in the code.
If you're unsure, say "possible issue — verify X", don't state it as fact.
- Separate must-fix (correctness/security) from nice-to-have (style). Don't drown blockers in nits.
- Praise genuinely good choices briefly — it calibrates the rest.
- If the diff is large, review in passes (correctness → security → the rest) rather than skimming once.
- RTL/Hebrew web code: check for physical-CSS leftovers (
left/right/ml-/mr-) that break RTL —
prefer logical properties.
Output shape
A short summary verdict (approve / approve-with-changes / request-changes), then findings grouped by severity, then a one-line note on test coverage.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: squadcodercom
- Source: squadcodercom/squadcoder
- License: MIT
- Homepage: https://squadcoder.com
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.