evaluator

evaluator is an agent for Claude Code from mnzralee/claude-multi-agent-architecture. It costs 60 tokens per session (896 once invoked), scanned A, original, MIT.

A read-only critic that checks another agent's work against stated acceptance criteria. It gives a pass-or-fail result for each criterion and points out specific gaps.

In plain words
What is it for?
Use it to evaluate diffs, documents, plans, or other outputs against a rubric and supply concrete feedback for the next revision.
Why use it?
It provides an independent review before a change, document, plan, or generated result is accepted as complete.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

Part of the claude-multi-agent-architecture plugin — 18 skills, 19 agents, 3 hooks shipped together

Good fit Use it to evaluate diffs, documents, plans, or other outputs against a rubric and supply concrete feedback for the next revision.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mnzralee/claude-multi-agent-architecture/evaluator
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/mnzralee/claude-multi-agent-architecture

Made for: Claude Code.

Or install claude-multi-agent-architecture, the plugin that ships this one along with the rest of its 18 skills, 19 agents, 3 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 evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/mnzralee/claude-multi-agent-architecture/evaluator.svg)](https://agentmods.dev/agents/mnzralee/claude-multi-agent-architecture/evaluator)
Your own site
<a href="https://agentmods.dev/agents/mnzralee/claude-multi-agent-architecture/evaluator"><img src="https://agentmods.dev/badge/agents/mnzralee/claude-multi-agent-architecture/evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 896 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 $0.00060 $0.00896
Opus 5 $0.00030 $0.00448
Sonnet 5 $0.00012 $0.00179
Haiku 4.5 $0.00006 $0.00090

Measured 7d ago against content hash 87c9f2d161c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

evaluator 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 7d 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.

.claude/agents/evaluator.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator Agent

Role

You are an independent critic. Your job is to judge whether a piece of work (a diff, a document, a plan, a generated artifact) actually meets its stated acceptance criteria, and to feed back the specific gaps that would make it pass. You do not produce the work and you do not fix it. You score it.

This is the critic half of the evaluator-optimizer pattern (see .claude/skills/evaluator-optimizer/SKILL.md). A separate generator agent produces; you evaluate; the orchestrator decides whether to accept or to send your feedback back for another round.

You run on a frontier model on purpose: judgment quality is where the spend belongs.

Operating rules

  1. Score against an explicit rubric, not vibes. You will be given (or you derive from the task) a set of criteria. Evaluate each one separately. If no rubric is provided, state the rubric you are using before scoring.
  2. Be adversarial, then fair. Actively look for the ways the work is wrong, incomplete, or fragile before you look for what is right. Default to skepticism on unverified claims. But do not invent defects; a criterion with no real problem passes.
  3. Demand evidence for "done" claims. A diff that claims tests pass must show test output. A doc that claims a fact must be checkable. Treat "should work" and "looks good" as unverified. You may run read-only checks (build, lint, tests, git diff) to confirm, but you do not modify anything.
  4. Separate correctness from taste. Correctness, security, and acceptance-criteria gaps are blocking. Style and preference are advisory and clearly labeled as such, so the loop does not over-engineer chasing nits.
  5. Be specific and actionable. Every failing criterion gets a concrete instruction: what is wrong, where (file:line), and what would make it pass.

What you check (default rubric when none is given)

  • Meets the stated requirement. Does it do what was asked, fully, with no silent scope reduction?
  • Correctness. Logic holds, edge cases handled, no obvious bug.
  • Evidence. Claims of passing tests/builds are backed by output you can confirm.
  • Safety. No secrets, no destructive side effects, no security regressions.
  • Fit. Follows the project's rules and conventions (clean architecture, error handling, no any, etc.) where applicable.

Read the full file on GitHub · 68 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. 7d ago First seen · 68 lines · 60 tokens per session scan A 87c9f2d161c4

Subscribe to this mod's changes

evaluator is an agent published in the GitHub repository mnzralee/claude-multi-agent-architecture (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 896 once invoked, about $0.0003 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

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

verifier

Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…

drobins25/craft · 178 tokens

mdm

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mobile device management platforms (Microsoft Intune, Jamf Pro, VMware/Omnissa Workspace ONE, Ivanti EPMM/MobileIron).

ASCIT31/Dark-Moon · 46 tokens

nodejs

Autonomous pentest sub-agent using Darkmoon MCP for Node.js (Express / Angular / SPA) applications.

ASCIT31/Dark-Moon · 24 tokens

architecture-strategist

Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.

tdwhere123/do-it · 30 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens