Install
$ agentstack add skill-viknesh20-20-claude-code-tool-kit-review-pr ✓ 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
Pull Request Code Review
Gather Context
Changed Files
!git diff --name-only HEAD~1 2>/dev/null || echo "No commits to diff"
Diff Summary
!git diff --stat HEAD~1 2>/dev/null || echo "No diff available"
Full Diff
!git diff HEAD~1 2>/dev/null | head -500
Recent Commits
!git log --oneline -10 2>/dev/null
Review Checklist
Analyze every changed file against the following categories. For each finding, provide:
- File path and line number
- Severity: Critical / High / Medium / Low
- Description of the issue
- Suggested fix with code snippet
1. Correctness
- Logic errors or off-by-one mistakes
- Missing null/undefined/nil checks
- Incomplete error handling
- Race conditions or concurrency issues
- Incorrect use of APIs or library functions
2. Security
- Input validation gaps (SQL injection, XSS, command injection, path traversal)
- Hardcoded secrets, tokens, or credentials
- Authentication/authorization bypass risks
- Insecure data handling (PII exposure, logging sensitive data)
- Missing CSRF/CORS protections where applicable
3. Performance
- N+1 query patterns
- Unnecessary loops or redundant computations
- Missing pagination for unbounded queries
- Blocking operations in async contexts
- Large memory allocations in hot paths
- Missing indexes for new database queries
4. Test Coverage
- Are new code paths covered by tests?
- Are edge cases and error paths tested?
- Are mocks appropriate and not over-mocking?
- Do test names clearly describe the scenario?
5. Code Quality
- Readability and naming clarity
- Unnecessary complexity that can be simplified
- Code duplication that should be extracted
- Dead code or unused imports
- Missing or misleading comments
6. Conventions
- Adherence to project coding standards (check CLAUDE.md)
- Consistent formatting and style
- Proper commit message format
- Documentation for public APIs
Output Format
Findings
Group findings by severity:
Critical (must fix before merge)
High (strongly recommend fixing)
Medium (should fix)
Low (nice to have)
Summary
Provide a 2-3 sentence executive summary of the PR quality.
Verdict
State one of:
- GO — Ready to merge (no critical/high issues)
- CONDITIONAL GO — Merge after addressing critical/high findings
- NO-GO — Significant issues require rework before re-review
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: viknesh20-20
- Source: viknesh20-20/claude-code-tool-kit
- License: MIT
- Homepage: https://viknesh20-20.github.io/claude-code-tool-kit/
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.