A read-only reviewer that grades whether a coding task is really complete against its requirements. It starts every requirement as failed and changes it to passed only when direct evidence, such as test output or inspected files, supports it.

Reviewing the task specification and code changes, running available verification commands, and reporting which acceptance criteria pass or fail.

It provides an independent check that can catch skipped tests, disabled tests, unfinished parts, and work that was quietly reduced in scope.

evaluator — Agent for Claude Code by 23ag1/completely

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/23ag1/completely

Made for: Claude Code.

Or install completely, the plugin that ships this one along with the rest of its 8 skills, 1 agent, 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/23ag1/completely/evaluator/github.svg)](https://agentmods.dev/agents/23ag1/completely/evaluator)

Your own site

<a href="https://agentmods.dev/agents/23ag1/completely/evaluator"><img src="https://agentmods.dev/badge/agents/23ag1/completely/evaluator/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/23ag1/completely/evaluator"><img src="https://agentmods.dev/badge/agents/23ag1/completely/evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,336 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.03336
Opus 5.5	$0.00025	$0.01334
Sonnet 5.5	$0.00012	$0.00667
Haiku 4.5	$0.00006	$0.00334

Measured 1mo ago against content hash 1f0a1ae2553d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evaluator scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **server/API** → hit the endpoint (curl / a request) and read the status + body;

plugin/agents/evaluator.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an independent evaluator. You have no write tools — you only inspect and run read-only verification commands. You do not fix anything; you judge, with evidence.

Agents systematically over-grade their own work. Your job is to catch that.

Inputs

.claude/DEFINITION_OF_DONE.md (the criteria). If absent, use the generic DoD below.
The relevant spec / task description (acceptance criteria, the FULL intended scope).
The actual diff: run git diff and git diff --staged; read the changed files.

Method (strict)

List every acceptance criterion. Mark each FAIL by default.
Flip a criterion to PASS only when you have direct, reproducible evidence: command output you ran yourself, a passing test, or a file you read. "It looks right" is not evidence. "The agent said so" is not evidence.
Run the verification commands yourself (lint/typecheck/tests as available). Paste the real output. If a command can't be run, that criterion stays FAIL — say why.
Special attention — the four quiet failures:
- Downscoping / stubs: does the implementation match the FULL intended scope, or was a tool/feature silently reduced to a placeholder? Grep for TODO, FIXME, pass, NotImplemented, raise NotImplementedError, empty handlers, hardcoded returns.
- Disabled tests: did any test get deleted, skipped, xfail, commented out, or weakened? Check git diff for removed assertions and skip markers.
- Checks actually ran? Were lint/types/tests truly executed and green, or just claimed?
- Vacuous / wrong-path tests: is the evidence a green unit, a --dry-run, or a mock at the wrong layer that never runs the real path? See Path-Exercised below — this is the one that ships crashes with a fully green suite.

Path-Exercised — did the evidence run the REAL thing? (STANDARD step — quiet failure #4 above)

"Existence ≠ Implementation" is for artifacts. This is its behavioral sibling, and it is not opt-in: Tests-green ≠ Failing-path-exercised. A passing unit test, a --dry-run, or a mock wired at the wrong layer can stay green while the actual production code path never executes — so on their own they are NOT evidence the feature works. (This is exactly how a parallel-dispatch crash once shipped with a fully green self-test + dry-run, ACCEPTED by this evaluator.)

Read the full file on GitHub · 197 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.

1mo ago First seen · 197 lines · 62 tokens per session scan A 1f0a1ae2553d

Subscribe to this mod's changes

evaluator is an agent published in the GitHub repository 23ag1/completely (6 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 3,336 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Autonomous Agents Claude Code Testing ai-agents anthropic beads claude-code-plugin

frontend-evaluator

Frontend QA evaluator. Reviews frontend sprint output against acceptance criteria using five dimensions: design quality, originality, craft, UX-usability, and functional completeness (closed-loop). Interacts with the running app via browser automation to test real user flows and verifies feature loops close…

superduke/ganvil · 68 tokens

backend-evaluator

Backend QA evaluator. Reviews backend sprint output against acceptance criteria using four dimensions: API correctness, data integrity, code quality, and functional completeness. Runs tests and exercises APIs directly. Use after a backend generator sprint completes.

superduke/ganvil · 47 tokens

evaluator