# Review

> Review a diff against its request or spec and report actionable correctness, security, regression, scope, and test gaps. Does not edit.

- **Type:** Skill
- **Install:** `agentstack add skill-bnet47-codexicon-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [bnet47](https://agentstack.voostack.com/s/bnet47)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [bnet47](https://github.com/bnet47)
- **Source:** https://github.com/bnet47/codexicon/tree/main/.agents/skills/review
- **Website:** https://bnet47.github.io/codexicon/repo-template-playbook.html

## Install

```sh
agentstack add skill-bnet47-codexicon-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Review

Review evidence, not intent. Do not modify files.

## Establish the comparison

Inspect `git status`, unstaged and staged diffs, and—when available—the branch diff from its merge base. Read the request or linked spec/plan plus relevant conventions. If no Git repository exists, review the explicitly supplied files and state the limitation.

For a broad or high-risk diff, delegate independent read-only passes to the `reviewer` profile (for example correctness, security, and test coverage), then deduplicate and verify the findings yourself.

## Findings threshold

Report only issues that can cause:

- unmet acceptance criteria;
- incorrect behavior or a regression;
- security, privacy, authorization, or data-integrity exposure;
- unsafe migration or compatibility behavior;
- meaningful missing verification;
- accidental scope drift that raises risk.

Do not report style preferences, speculative future improvements, or items already enforced by a passing formatter unless they affect behavior.

## Output

Order findings by severity:

```markdown
## Findings

### [P1] [Short title]
`path/to/file:line` — [Concrete impact, triggering condition, and violated requirement.]

## Verification gaps
- [Missing or untrustworthy evidence.]

## Verdict
READY | NEEDS WORK — [one sentence]
```

Severity: P0 blocks all use; P1 high-impact and likely; P2 material but limited; P3 low-impact and concrete. Use the tightest line reference possible. If no actionable issue exists, return `READY — no actionable gaps found.`

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [bnet47](https://github.com/bnet47)
- **Source:** [bnet47/codexicon](https://github.com/bnet47/codexicon)
- **License:** MIT
- **Homepage:** https://bnet47.github.io/codexicon/repo-template-playbook.html

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-bnet47-codexicon-review
- Seller: https://agentstack.voostack.com/s/bnet47
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.