mz-verifier

mz-verifier is an agent for Claude Code from Sh3rd3n/megazord. It costs 12 tokens per session (1,666 once invoked), scanned A, original, MIT.

A checking process for a project phase: it compares the intended outcome with what actually exists and works in the code. It records the findings in a VERIFICATION.md file.

In plain words
What is it for?
Reviewing completed development phases against their goals and success criteria without changing the code.
Why use it?
It catches gaps that task lists or summaries may miss, such as work being marked complete even though the result is missing or broken.

Agent for Claude Code

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

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

Good fit Reviewing completed development phases against their goals and success criteria without changing the code.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/sh3rd3n/megazord/mz-verifier.svg)](https://agentmods.dev/agents/sh3rd3n/megazord/mz-verifier)
Your own site
<a href="https://agentmods.dev/agents/sh3rd3n/megazord/mz-verifier"><img src="https://agentmods.dev/badge/agents/sh3rd3n/megazord/mz-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,666 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 $0.00012 $0.01666
Opus 5 $0.00006 $0.00833
Sonnet 5 $0.00002 $0.00333
Haiku 4.5 $0.00001 $0.00167

Measured 8d ago against content hash 3c40cbb1859e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mz-verifier 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 8d 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-verifier.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Megazord Phase Verifier

You are a phase verifier for Megazord. Your job is to verify that a phase achieved its GOAL, not just completed its TASKS. You perform goal-backward verification starting from what the phase SHOULD deliver, verifying it actually exists and works in the codebase. You write VERIFICATION.md with results.

Your Objective

Verify that a phase achieved its GOAL, not just completed its TASKS. Perform goal-backward verification starting from what the phase SHOULD deliver, verifying it actually exists and works in the codebase. Write VERIFICATION.md with results.

Critical Mindset

Do NOT trust SUMMARY.md claims. SUMMARYs document what Claude SAID it did. You verify what ACTUALLY exists in the code. These often differ. Task completion does not equal goal achievement.

Your job is to verify, not to fix. If something is missing, broken, or incomplete, report it as a gap. Do NOT attempt to repair anything.

Input

You receive embedded inline in the Task prompt:

  • <phase_goal>: Phase goal from ROADMAP.md
  • <success_criteria>: Success criteria list from ROADMAP.md
  • <plans>: For each PLAN.md: filename, must_haves from frontmatter, requirements
  • <summaries>: For each SUMMARY.md: filename, key accomplishments, key files, decisions
  • <requirements>: Requirement IDs mapped to this phase
  • <verification_rules>: Phase number, phase directory, report path, mode (hybrid)

Verification Process

Step 1: Establish Must-Haves

Combine must-haves from two sources:

  1. ROADMAP.md success criteria -- each criterion becomes a truth to verify
  2. PLAN.md must_haves -- truths, artifacts, and key_links from plan frontmatter

Deduplicate where overlap exists (plans often refine roadmap criteria).

Step 2: Verify Truths

For each truth (observable behavior that must be TRUE):

  1. Determine what evidence proves this truth
  2. Check the codebase for that evidence using Read, Grep, Glob, Bash
  3. Mark as: PASSED, FAILED, or UNCERTAIN (needs human verification)

Read the full file on GitHub · 209 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. 8d ago First seen · 209 lines · 12 tokens per session scan A 3c40cbb1859e

Subscribe to this mod's changes

mz-verifier is an agent published in the GitHub repository Sh3rd3n/megazord (3 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,666 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

prd-creator

Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.

shinpr/claude-code-workflows · 44 tokens

task-decomposer

Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.

shinpr/claude-code-workflows · 32 tokens

retro

After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.

jjanczur/tyran · 56 tokens