evaluation-runner

evaluation-runner is an agent for Claude Code from orin-dx/agent-plugins. It costs 31 tokens per session (620 once invoked), scanned A, original, MIT.

An isolated test runner for checking how a workflow behaves on a fixed input without exposing the expected answer. It records a completed run for separate review.

In plain words
What is it for?
Use it for regression checks and release testing of agent or plugin workflows. It helps produce a clean run that another evaluator can compare with the expected result.
Why use it?
It prevents the workflow from seeing the answer key or changing its own results, making the test less biased. It also records unavailable capabilities and unfinished work instead of hiding them.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Good fit Use it for regression checks and release testing of agent or plugin workflows. It helps produce a clean run that another evaluator can compare with the expected result.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/orin-dx/agent-plugins/evaluation-runner
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/orin-dx/agent-plugins

Made for: Claude Code.

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 evaluation-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/orin-dx/agent-plugins/evaluation-runner/github.svg)](https://agentmods.dev/agents/orin-dx/agent-plugins/evaluation-runner)
Your own site
<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/evaluation-runner"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/evaluation-runner/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.

agentmods 80×15 button for evaluation-runner

Your own site · 80×15
<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/evaluation-runner"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/evaluation-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 620 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 $0.00031 $0.00620
Opus 5 $0.00015 $0.00310
Sonnet 5 $0.00006 $0.00124
Haiku 4.5 $0.00003 $0.00062

Measured today against content hash a01638fdc9a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

evaluation-runner 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 today.

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.

plugins/mason/agents/evaluation-runner.md · 44 lines

What it actually says

<load_first> Load shared/references/evaluation/behavioral.md. Load only the selected fixture's public input before the target workflow finishes; reserve its oracle for the adjudicator. </load_first>

WHEN preparing the run, THE SYSTEM SHALL expose only the fixture's public input to the target workflow. WHEN a requested host capability is unavailable, THE SYSTEM SHALL record the limitation instead of substituting a different mode silently. WHEN a started command or delegated task has not reached a terminal result, THE SYSTEM SHALL wait or terminate it and record the failure; a returned evaluation-run@1 SHALL have no pending checks. THE SYSTEM SHALL NEVER edit the target artifacts after the workflow produces them. THE SYSTEM SHALL NEVER read or disclose the fixture oracle before the target workflow reaches a terminal result.

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. today Changed · +1 lines a01638fdc9a6
  2. yesterday First seen · 43 lines · 31 tokens per session scan A 6bfd07d8c18e

Subscribe to this mod's changes

evaluation-runner is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 620 once invoked, about $0.0002 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 2026-09-10.

Related

Other agents, from other repositories