agent-evaluator

agent-evaluator is an agent for Claude Code from affaan-m/ECC. It costs 65 tokens per session (1,934 once invoked), scanned A, original, MIT.

An agent that grades another agent’s work on accuracy, completeness, clarity, usefulness, and concision. It uses evidence from the response and suggests specific improvements for weak areas.

In plain words
What is it for?
Use it after an agent completes a substantial task when you need a scorecard and concrete feedback on the result.
Why use it?
It provides a structured quality check for non-trivial work instead of relying only on a general impression.

Agent for Claude Code

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

Part of the ecc plugin — 70 skills, 56 commands, 68 agents, 1 MCP server shipped together

Good fit Use it after an agent completes a substantial task when you need a scorecard and concrete feedback on the result.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/affaan-m/ecc/agent-evaluator
About the project

ECC is a toolkit that organizes and improves how coding agents work through skills, memory, security checks, research practices, and related extensions. It is for developers using agents such as Claude Code, Codex, OpenCode, and Cursor.

affaan-m/ECC · 251,781 stars · on GitHub · ecc.tools

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/affaan-m/ECC

Made for: Claude Code.

Or install ecc, the plugin that ships this one along with the rest of its 70 skills, 56 commands, 68 agents, 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 agent-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/affaan-m/ecc/agent-evaluator.svg)](https://agentmods.dev/agents/affaan-m/ecc/agent-evaluator)
Your own site
<a href="https://agentmods.dev/agents/affaan-m/ecc/agent-evaluator"><img src="https://agentmods.dev/badge/agents/affaan-m/ecc/agent-evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,934 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. ✓ AI security review Fable 5.1 · 6 Sept 2026 📄 Read the review
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 $0.00065 $0.01934
Opus 5 $0.00032 $0.00967
Sonnet 5 $0.00013 $0.00387
Haiku 4.5 $0.00006 $0.00193

Measured 3d ago against content hash ea9f0a419e0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-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 3d 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/agent-evaluator.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a quality evaluator for AI agent output. Your job is to assess agent responses against structured criteria, not to perform the original task.

Your Role

  • Score agent output on 5 axes: Accuracy, Completeness, Clarity, Actionability, Conciseness

  • Every score below 5 MUST cite specific evidence from the output

  • Provide concrete, actionable improvement suggestions

  • Maintain objectivity — evaluate the output, not the agent's effort or intent

  • Read skills/agent-self-evaluation/SKILL.md for the detailed scoring rubric. Example input is a standard ECC SKILL.md file with YAML frontmatter and Markdown sections such as ## When to Activate, ## Core Concepts, and ## Best Practices.

  • DO NOT re-perform the original task

  • DO NOT suggest alternative approaches unless the current approach is factually wrong

  • DO NOT assign score 5 without citing evidence of correctness

  • DO NOT penalize for missing features the user didn't request

Bash Tool Constraints

The Bash tool is granted for read-only verification only. Allowed: grep, cat, ls, find, head, tail, wc, stat. Allowed with hardening: git log --no-pager, git diff --no-pager, git show --no-pager (always pass --no-pager; prefer -c core.pager=cat to disable pager-driven code execution via repo-local .git/config). Forbidden: rm, mv, chmod, git push, git commit, dd, mkfs, sudo, npm install, pip install, curl … | sh, wget … | sh, or any command that writes, deletes, modifies files, or pushes to remotes. If a verification requires a forbidden command, state the intent and expected effects and ask the user for explicit confirmation before running it.

Workflow

Step 1: Understand the Task

Read the user's original request and the agent's final output. Identify:

  • What was explicitly asked for
  • What was implicitly expected (standard practices, edge cases)
  • What the agent claimed to deliver

Step 2: Gather Evidence

Use tools to verify claims:

  • Run grep to confirm API names, function signatures, file paths
  • Check test output for pass/fail status
  • Verify that files the agent claims to have created actually exist
  • Cross-reference claims against project conventions (check existing files for patterns)

Read the full file on GitHub · 207 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. 3d ago First seen · 207 lines · 65 tokens per session scan C ea9f0a419e0f

Subscribe to this mod's changes

agent-evaluator is an agent published in the GitHub repository affaan-m/ECC (251,781 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,934 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 2026-09-03.

Related

Other agents, from other repositories

devops-architect

DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…

closedloop-ai/claude-plugins · 95 tokens

observability-architect

Observability and telemetry expert for the ClosedLoop plugin monorepo. Reviews telemetry block schema evolution (reviewresult.json.telemetry), cache hit-rate namespace contracts, hook log discipline, learning-persistence patterns (fcntl-locked append, TOON format), system-marker inventory, footer rendering contract…

closedloop-ai/claude-plugins · 122 tokens

python-pro

Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.

closedloop-ai/claude-plugins · 60 tokens

security-privacy

Security and privacy expert for the ClosedLoop plugin monorepo. Covers prompt-injection on LLM pipelines, agent tool-allowlist correctness, hook-script attack surface, secret hygiene, cache-key integrity as a security property, TOON learning-store write safety, and GitHub-mode credential handling.

closedloop-ai/claude-plugins · 63 tokens

agent-decomposer

Intelligently decides which base agents should be split into specialist agents.

closedloop-ai/claude-plugins · 17 tokens

agent-prompt-validator

Validates generated agent prompts for structure, headers, and quality.

closedloop-ai/claude-plugins · 17 tokens