skill-evaluation-workbench

skill-evaluation-workbench is a skill for Claude Code, Codex from yeaight7/agent-powerups. It costs 34 tokens per session (840 once invoked), scanned A, original, Apache-2.0.

A method for creating repeatable tests for agent skills, prompts, tool workflows, and MCP-backed cases. MCP is a standard way for an agent to connect to external tools or data.

In plain words
What is it for?
Use it to build evaluation suites with normal, boundary, and unrelated test cases, plus local graders and saved artifacts.
Why use it?
It makes agent quality easier to compare and helps trace failures before changing instructions.

Skill for Claude CodeCodex

Part of the agent-evaluation-lab plugin — 3 skills shipped together

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 skills/yeaight7/agent-powerups/skill-evaluation-workbench
Any agent
npx skills add yeaight7/agent-powerups --skill skill-evaluation-workbench
Clone the repo
git clone --depth 1 https://github.com/yeaight7/agent-powerups

Made for: Claude Code, Codex.

Or install agent-evaluation-lab, the plugin that ships this one along with the rest of its 3 skills.

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 skill-evaluation-workbench

README.md
[![agentmods](https://agentmods.dev/badge/skills/yeaight7/agent-powerups/skill-evaluation-workbench.svg)](https://agentmods.dev/skills/yeaight7/agent-powerups/skill-evaluation-workbench)
Your own site
<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/skill-evaluation-workbench"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/skill-evaluation-workbench.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 840 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 $0.00034 $0.00840
Opus 5 $0.00017 $0.00420
Sonnet 5 $0.00007 $0.00168
Haiku 4.5 $0.00003 $0.00084

Measured 5d ago against content hash 14989d856574, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-evaluation-workbench 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 5d 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.

plugins/agent-evaluation-lab/skills/skill-evaluation-workbench/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Evaluation Workbench

When To Use

  • A skill or prompt needs repeatable quality checks across models or configurations.
  • A workflow needs file-based graders, command traces, or local artifact checks.
  • A tool or MCP skill needs a hidden service fixture or sandboxed test workspace.
  • A previous agent attempt failed and you need trace-driven diagnosis before editing instructions.

Requirements / Checks

  • Confirm an eval runner exists locally before running anything. Do not install deps without approval.
  • Prefer local deterministic graders over model-graded assertions.
  • If Docker, remote models, API keys, or live services are involved, ask before execution.
  • Treat traces, result files, preserved workspaces, and stdout as potentially sensitive.

Minimal Suite Structure

Every suite should have at least three cases:

Case Purpose
Positive (golden path) Skill handles the normal use case correctly
Edge case Skill handles an important boundary condition
Control (no-tool-needed) Skill does not over-trigger on a clearly unrelated input

Place fixtures in cases/, skill/reference material in references/, and grader scripts in graders/.

Grader Types

Type When to use Deterministic?
File existence Skill was supposed to create a file Yes
File content match Output matches expected text or schema Yes
Command exit code Script/tool succeeded Yes
JSON schema Output is valid structured data Yes
Regex match Output contains expected pattern Yes
Custom script Complex logic not covered above Yes (if written correctly)
Model grader Subjective quality judgment No — use sparingly, pin model

Workflow

  1. Define observable behavior — state what the skill must produce: files, command args, JSON output, logs, or a safety refusal. If it's not observable, it can't be graded.

  2. Create the minimal suite — one positive, one edge, one control case. Add more only after the minimal suite passes.

Read the full file on GitHub · 87 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 87 lines · 34 tokens per session scan A 14989d856574

Subscribe to this mod's changes

skill-evaluation-workbench is a skill published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 840 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 2026-08-31.