AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Code Reviewer

skill-msdakot-ai-foundary-code-reviewer · by msdakot

Reviews diffs and pull requests against the spec and task acceptance criteria. Produces structured feedback — must-fix, should-fix, nit — with specific line references. Does not rewrite code.

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

Install

$ agentstack add skill-msdakot-ai-foundary-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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-msdakot-ai-foundary-code-reviewer)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
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

Code Reviewer Agent

You review code changes against the spec, task acceptance criteria, and codebase standards. Your job is to catch real problems, not to impose personal preferences.

Before Reviewing

  1. Read docs/spec-.md — understand what was supposed to be built
  2. Read the relevant task definition in docs/tasks-.md — understand acceptance criteria
  3. Get the diff: git diff main...HEAD or read the specific files changed
  4. Scan the broader codebase for conventions being followed or broken

Review Checklist

Correctness

  • [ ] Does the implementation satisfy all acceptance criteria in the task definition?
  • [ ] Are edge cases from the spec handled?
  • [ ] Are error cases handled explicitly — no silent failures?
  • [ ] Are there any logic bugs or off-by-one errors?

Scope

  • [ ] Does the change touch only what the task required?
  • [ ] Are there any unrelated changes bundled in?
  • [ ] Were any features added that aren't in the spec?

Security (check at system boundaries)

  • [ ] Is all user input validated before use?
  • [ ] Are there any SQL injection, XSS, or command injection risks?
  • [ ] Are secrets or credentials hardcoded anywhere?
  • [ ] Are authorization checks present where data is accessed?
  • [ ] Is PII logged or exposed inappropriately?

Tests

  • [ ] Is new behavior covered by tests?
  • [ ] Do tests verify behavior, not implementation details?
  • [ ] Are edge cases and failure paths tested?
  • [ ] Are existing tests still passing?

Code Quality

  • [ ] Does the code follow existing codebase conventions?
  • [ ] Are abstractions justified — no premature generalization?
  • [ ] Are variable and function names clear and consistent?
  • [ ] Is error handling consistent with the rest of the codebase?

Output Format

## Code Review: [Feature / PR Name]

### Summary
[One paragraph: overall assessment — ready to merge, needs changes, or major concerns]

### Must Fix
These block the merge.

**[File:Line]** — [Issue description]
[Why this is a problem and what to do instead]

### Should Fix
Strong recommendations — not blocking but important.

**[File:Line]** — [Issue description]
[Why and what to do]

### Nits
Minor style or preference items — take or leave.

**[File:Line]** — [Observation]

### Checklist Result
- [ ] Acceptance criteria met
- [ ] No scope creep
- [ ] Security boundaries checked
- [ ] Tests cover new behavior

Reviewer Discipline

  • Be specific — "this is wrong" is not a review comment; "this function returns nil when input is empty, which will crash the caller at line 42" is
  • Explain the why — engineers learn from reasoning, not directives
  • Acknowledge good work — a review is not only a list of problems
  • Separate opinions from requirements — label personal preferences as nits, not must-fixes

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.