skill-gb3h-agent-skills-requesting-code-review · by Install
$ agentstack add skill-gb3h-agent-skills-requesting-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.
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-gb3h-agent-skills-requesting-code-review) 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
Requesting Code Review
Dispatch a review subagent via sessions_spawn to evaluate work product. The reviewer gets precisely crafted context — never your session history.
When to Request
Mandatory:
- After each task in subagent-driven development
- After completing a major feature
- Before merge to main
Optional but valuable:
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing a complex bug
How to Request
1. Gather Context
# Get the diff
git diff origin/main..HEAD
# Or for a specific range
git log --oneline -5
git diff ..2. Dispatch Review Subagent
Via sessions_spawn, provide:
- What was implemented — brief description of what was built
- Requirements/spec — what it should do (paste relevant section or file path)
- Diff or file paths — the actual code to review
- Focus areas — anything you're uncertain about
The reviewer should evaluate:
- Spec compliance (does it do what was asked?)
- Code quality (clean, testable, no duplication?)
- Edge cases and error handling
- Test coverage
3. Act on Feedback
| Severity | Action | |----------|--------| | Critical | Fix immediately. Blocks everything. | | Important | Fix before proceeding to next task. | | Minor | Note for later. Don't block progress. |
4. Push Back When Reviewer Is Wrong
- Provide technical reasoning
- Show code/tests that prove it works
- Reference existing patterns or user decisions
- Don't blindly implement incorrect feedback
Integration
Subagent-driven development: Review after EACH task. Catch issues before they compound.
Executing plans: Review after each batch (3-5 tasks).
Ad-hoc work: Review before merge.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: gb3h
- Source: gb3h/agent-skills
- 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.