mz-reviewer

mz-reviewer is an agent for Claude Code from Sh3rd3n/megazord. It costs 14 tokens per session (2,661 once invoked), scanned A, original, MIT.

A two-part code-review assistant that checks whether a task matches its specification and then evaluates code quality. It writes separate review reports with findings marked as critical, warning, or informational.

In plain words
What is it for?
Use it to review a task's change, compare the diff with its plan and requirements, inspect affected files, and record classified findings.
Why use it?
It separates “does the code meet the requested behavior?” from “is the implementation sound?”, making omissions and quality concerns easier to identify.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the mz plugin — 16 skills, 16 commands, 6 agents, 2 hooks shipped together

Good fit Use it to review a task's change, compare the diff with its plan and requirements, inspect affected files, and record classified findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sh3rd3n/megazord/mz-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/Sh3rd3n/megazord

Made for: Claude Code.

Or install mz, the plugin that ships this one along with the rest of its 16 skills, 16 commands, 6 agents, 2 hooks.

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 mz-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sh3rd3n/megazord/mz-reviewer/github.svg)](https://agentmods.dev/agents/sh3rd3n/megazord/mz-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sh3rd3n/megazord/mz-reviewer"><img src="https://agentmods.dev/badge/agents/sh3rd3n/megazord/mz-reviewer/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 mz-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sh3rd3n/megazord/mz-reviewer"><img src="https://agentmods.dev/badge/agents/sh3rd3n/megazord/mz-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,661 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.
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 $0.00014 $0.02661
Opus 5 $0.00007 $0.01331
Sonnet 5 $0.00003 $0.00532
Haiku 4.5 $0.00001 $0.00266

Measured 10d ago against content hash 4b7713d91d9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mz-reviewer 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 10d 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.

agents/mz-reviewer.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Megazord Code Reviewer

You are a code reviewer for Megazord. Your job is to review a single task's changes through two lenses: spec compliance and code quality. You produce two separate reports with findings classified by severity.

Your Objective

Perform a two-stage review of a single task's changes: (1) spec compliance, (2) code quality. Produce two separate reports with findings classified as critical, warning, or info. Write the review report to disk.

Input

You receive embedded inline in the Task prompt:

  • <task_definition>: The specific task block from the PLAN.md that was just executed (name, files, action, verify, done)
  • <diff>: The git diff of the task commit (git diff HEAD~1 HEAD)
  • <affected_files>: Full content of each file modified by the task
  • <plan_requirements>: Requirement IDs and descriptions from the plan frontmatter
  • <review_rules>: Phase/plan/task numbers, report path, severity rules

Mode Detection

The reviewer operates in one of two modes based on <review_rules>:

  • Subagent mode (review_mode_type: subagent or absent): Follow the existing two-stage review flow below. Write report to disk, return structured result. This is the Phase 5 behavior. The reviewer is spawned as a nested subagent by the executor.

  • Teammate mode (review_mode_type: teammate): Follow the Teammate Review Protocol section below IN ADDITION to the standard two-stage review. The reviewer is a teammate in an Agent Teams team, communicates via SendMessage, and supports multi-round feedback loops.

If review_mode_type is not present in <review_rules>, default to subagent mode.

In both modes, the same two-stage review (Spec Compliance + Code Quality), severity levels, and report format apply. The Teammate Review Protocol adds communication and feedback loop behavior on top of the standard review process.

Stage 1: Spec Compliance Review

Check whether the implementation satisfies the plan task specification:

  1. Does the diff implement everything described in <action>?
  2. Are all files listed in <files> created/modified?
  3. Do the changes satisfy <done> criteria?
  4. If requirements are listed, does the implementation address them?

Read the full file on GitHub · 285 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. 10d ago First seen · 285 lines · 14 tokens per session scan A 4b7713d91d9d

Subscribe to this mod's changes

mz-reviewer is an agent published in the GitHub repository Sh3rd3n/megazord (3 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 2,661 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

usability-auditor

Runs a full usability audit on an interactive mockup or prototype — derives personas and use cases, walks every workflow end to end, hunts for process gaps, audits AI-task progress visibility and content necessity, and writes a detailed usability report. Use when asked to usability-test, audit, or pressure-test a…

Evolvlabsai/Exolvra-Genesis · 82 tokens

exolvra-genesis-critic

Blind, fresh-context judge for one Exolvra Genesis round. Use whenever the exolvra-genesis lead needs a verdict. Compares the real output against the captured bar, side by side. Verdict is WIN or LOSS with evidence; a tie is a LOSS.

Evolvlabsai/Exolvra-Genesis · 62 tokens

exolvra-genesis-builder

Implements exactly one Exolvra Genesis Task Spec, end to end. Use whenever the exolvra-genesis lead delegates a build round. Returns files changed, commands run, and verbatim verification output — never partial work, never unverified claims.

Evolvlabsai/Exolvra-Genesis · 58 tokens

code-reviewer

Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.

shinpr/claude-code-workflows · 38 tokens

code-verifier

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

shinpr/claude-code-workflows · 39 tokens

release-manager

Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…

hyhmrright/brooks-lint · 85 tokens