Review Code Change
Review a code change for concrete defects, regressions, security risk, and missing tests. Use for pull requests, diffs, patches, and pre-release quality checks.
Install
$ agentstack add skill-ryosukesama-github-ai-review-code-change ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ryosukesama-github-ai-review-code-change) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Review Code Change
Athena analyzes contracts and risk; Hephaestus validates implementation details.
Review Order
- Understand the intended behavior and the boundaries changed.
- Trace modified inputs through state changes, side effects, and outputs.
- Look for correctness defects, compatibility breaks, unsafe assumptions,
security exposure, concurrency issues, and data-loss paths.
- Check whether tests cover the newly introduced behavior and important failures.
- Ignore purely stylistic preferences unless they hide a behavioral problem.
Output
Lead with findings ordered by severity. Each finding must name the affected file or component, explain the failure scenario, and propose a concrete correction. Then list open assumptions and test gaps. If there are no actionable findings, say so clearly and identify the remaining verification risk.
Do not invent line numbers, command results, or repository context that was not provided by a file, diff, connected tool, or prior task step.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: RyosukeSAMA
- Source: RyosukeSAMA/github-ai
- License: MIT
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.