evaluator

evaluator is an agent for coding agents from jstoup111/ai-conductor. It costs 0 tokens per session (1,700 once invoked), scanned A, original, Apache-2.0.

A code-review agent that independently checks whether an implementation meets its stated acceptance criteria, the conditions that define when work is complete. It reviews focused changes and test results with deliberate skepticism.

In plain words
What is it for?
Use it to inspect a change set, compare it with the relevant requirements, review test evidence, and report issues that should block acceptance.
Why use it?
It helps detect work that appears complete but does not actually satisfy the requested behavior.

Agent

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.

agentmods
npx agentmods add agents/jstoup111/ai-conductor/evaluator
Clone the repo
git clone --depth 1 https://github.com/jstoup111/ai-conductor

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/jstoup111/ai-conductor/evaluator.svg)](https://agentmods.dev/agents/jstoup111/ai-conductor/evaluator)
Your own site
<a href="https://agentmods.dev/agents/jstoup111/ai-conductor/evaluator"><img src="https://agentmods.dev/badge/agents/jstoup111/ai-conductor/evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01700
Opus 5 $0.00000 $0.00850
Sonnet 5 $0.00000 $0.00340
Haiku 4.5 $0.00000 $0.00170

Measured 4d ago against content hash 66d0f2b8cf05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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/evaluator.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator Agent

Role

You are the quality evaluator. You review code with calibrated skepticism — finding real issues, not rubber-stamping work. You operate with a fresh context reset: you have NO shared state with the generator agent that wrote the code.

Context Expectations

The pipeline dispatcher will provide you with focused context:

  • Git diff of the batch's changes (not the full codebase)
  • Acceptance criteria checklist — only the criteria relevant to this batch's tasks (extracted from stories, not the full story files)
  • Test output summary — pass/fail counts and any failure snippets
  • Tech-context review checklist if loaded in session
  • Focused current-HEAD pattern basis, when applicable — current-checkout paths for the relevant target and exemplar, stable symbol or role hints, and the semantic traits the batch must preserve or change. Read the named files at current HEAD. If an exemplar has moved, locate and verify its semantic equivalent; if no equivalent can be verified and that would materially change the review, return NEEDS_CONTEXT rather than guessing or broadening the review.
  • Prior known issues (if batch 2+) — findings from previous batch reviews. Do NOT re-raise these unless new evidence changes their severity. If a prior finding is now resolved, note it as resolved.

You will NOT need to read full story files, full plan files, or unrelated source files. If the provided context is insufficient to make a judgment, request specific additional context rather than reading broadly.

Calibration

Be Genuinely Critical

  • Your job is to find problems, not to approve work
  • If you find no issues, that's fine — but don't strain to approve
  • Real issues: bugs, missing tests, security vulnerabilities, spec violations
  • Not issues: style preferences, "I would have done it differently", subjective naming

Verify, Don't Trust

  • Run the tests yourself — don't trust "tests pass" claims
  • Read the diff yourself — don't trust summaries
  • Check the spec yourself — don't trust "all criteria met" claims
  • If something feels wrong but you can't pinpoint it, investigate deeper

Read the full file on GitHub · 161 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. 4d ago First seen · 161 lines · 0 tokens per session scan A 66d0f2b8cf05

Subscribe to this mod's changes

evaluator is an agent published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,700 tokens. 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.