review

review is a skill for Claude Code from ryanczak/rexyMCP. It costs 33 tokens per session (2,924 once invoked), scanned A, original, MIT.

A review gate for a completed development phase. It checks the project’s Definition of Done, reruns its commands and tests, and records whether the phase passes or must return to development.

In plain words
What is it for?
Use it to review a phase marked ready for review, approve it when requirements pass, or file a bug and send it back when they do not.
Why use it?
It gives completed work a consistent final check instead of relying on the implementer’s own assessment. This helps catch missing requirements and failed tests before the work is accepted.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Claude Code.

Part of the rexymcp plugin — 5 skills, 1 MCP server shipped together

Good fit Use it to review a phase marked ready for review, approve it when requirements pass, or file a bug and send it back when they do not.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ryanczak/rexymcp/review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ryanczak/rexyMCP --skill review
Clone the repo
git clone --depth 1 https://github.com/ryanczak/rexyMCP

Made for: Claude Code.

Or install rexymcp, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ryanczak/rexymcp/review/github.svg)](https://agentmods.dev/skills/ryanczak/rexymcp/review)
Your own site
<a href="https://agentmods.dev/skills/ryanczak/rexymcp/review"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ryanczak/rexymcp/review"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 31
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Excessive Agency · line 6
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.02924
Opus 5 $0.00016 $0.01462
Sonnet 5 $0.00007 $0.00585
Haiku 4.5 $0.00003 $0.00292

Measured 9d ago against content hash 1b5faf4245fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/review/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Skill

This skill is the substantive review gate. It re-runs the project's commands, walks the Definition of Done from STANDARDS.md, spot-checks tests, and either writes the Review verdict (flip to done) or files a bug (flip back to in-progress). It does not execute the phase itself — that is the executor's job. On hard_fail or budget_exceeded results, it delegates to /rexymcp:escalate rather than reviewing.

Read these first

Before any action:

  1. Read the phase doc (resolve <phase> from the argument). Its Status: line must be review. If it is todo, in-progress, or done, stop and tell the user the phase is not in a reviewable state.
  2. Read <repo>/docs/dev/STANDARDS.md — the Definition of Done checklist (§1) is what you verify against.
  3. Read the milestone README (docs/dev/milestones/M<n>-<slug>/README.md) for the phase table — status must mirror the phase doc.
  4. Read the returned PhaseResult. If the dispatch skill passed it in context, use that. If not available, query via executor_log_tail + get_turn MCP tools using the phase's log_path from rexymcp.toml.

The repo root is <repo> — resolve it from CLAUDE_PROJECT_DIR, ANTIGRAVITY_PROJECT_DIR, or the nearest directory containing the milestone layout.

1. Refuse non-review-status phases

If the phase doc's Status: line is not review, stop. Tell the user: "This phase is not in review status (current status: <actual>). It must be reviewed by the executor first — re-dispatch via /rexymcp:dispatch <phase> if it is still todo."

2. Refuse hard_fail / budget_exceeded / cancelled results

Check PhaseResult.status:

  • If "hard_fail" or "budget_exceeded": this is an escalation, not a review. Point the user at /rexymcp:escalate <phase> and stop. Do not attempt to review partial work.
  • If "cancelled": the run was deliberately stopped mid-phase (rexymcp stop or stop_phase) — its work is partial and the tree is dirty, so it is not reviewable. Point the user at /rexymcp:escalate <phase> (to resume the partial work) or a fresh re-dispatch, and stop.
  • If "complete": proceed to §3.

Read the full file on GitHub · 262 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 262 lines · 33 tokens per session scan A 1b5faf4245fd

Subscribe to this mod's changes

review is a skill published in the GitHub repository ryanczak/rexyMCP (86 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 2,924 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories