the-eval-designer

the-eval-designer is an agent for Claude Code from shrwnsan/vibekit-claude-plugins. It costs 73 tokens per session (995 once invoked), scanned A, original, no licence file.

An evaluation-design agent for checking whether an AI or machine-learning feature works well. It helps define test datasets, measurements, review rules, repeatable checks, and samples from real use.

In plain words
What is it for?
Use it to plan tests for an AI feature, compare versions, create human or AI review criteria, and monitor quality in production.
Why use it?
It turns the vague question “is this good enough?” into a documented way to measure quality and catch regressions before or after release.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the haku plugin — 52 skills, 22 agents shipped together

Good fit Use it to plan tests for an AI feature, compare versions, create human or AI review criteria, and monitor quality in production.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shrwnsan/vibekit-claude-plugins/the-eval-designer
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/shrwnsan/vibekit-claude-plugins

Made for: Claude Code.

Or install haku, the plugin that ships this one along with the rest of its 52 skills, 22 agents.

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 the-eval-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/shrwnsan/vibekit-claude-plugins/the-eval-designer/github.svg)](https://agentmods.dev/agents/shrwnsan/vibekit-claude-plugins/the-eval-designer)
Your own site
<a href="https://agentmods.dev/agents/shrwnsan/vibekit-claude-plugins/the-eval-designer"><img src="https://agentmods.dev/badge/agents/shrwnsan/vibekit-claude-plugins/the-eval-designer/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 the-eval-designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/shrwnsan/vibekit-claude-plugins/the-eval-designer"><img src="https://agentmods.dev/badge/agents/shrwnsan/vibekit-claude-plugins/the-eval-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 995 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 unknown 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 $0.00073 $0.00995
Opus 5 $0.00036 $0.00498
Sonnet 5 $0.00015 $0.00199
Haiku 4.5 $0.00007 $0.00100

Measured today against content hash 62063eeb2fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

the-eval-designer 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/haku/packs/evals/agents/the-eval-designer.md · 50 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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 First seen · 50 lines · 73 tokens per session scan A 62063eeb2fc7

Subscribe to this mod's changes

the-eval-designer is an agent published in the GitHub repository shrwnsan/vibekit-claude-plugins (7 stars, last pushed today), with no licence file. It adds 73 tokens to every session and 995 once invoked, about $0.0004 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

roadmap-implementer

Implement one assigned Foreman entry within its platform and file scope. Preserve shared work and report evidence; the coordinator owns roadmap writes and acceptance.

V-Songbird/foundry · 34 tokens

tdd-guide

Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly wants TDD or when a task should be driven by failing tests before code.

Galaxy-Dawn/claude-scholar · 45 tokens

tester

Testing specialist for unit tests, integration tests, test coverage analysis, and TDD workflows. Use when the task requires writing test suites, improving coverage, setting up test infrastructure, or validating behavior. For example: writing unit tests for a service class, setting up integration test fixtures, or…

josstei/maestro-orchestrate · 66 tokens

test-generator

Test generator for Shopware 6 tests. Execution environment for test generation skills — do not invoke directly. Skills fork into this agent via context: fork. Does not review tests — use the appropriate reviewer agent for that.

shopwareLabs/ai-coding-tools · 47 tokens

unfolding-po

PO (Product Owner) role in the Unfolding Specs process. Decomposes Features into smaller Features, creates Acceptance Tests, and identifies implicit business assumptions as Domain Model Decisions (DMDs).

t1/tdder · 45 tokens

dev-tooling-runner

Runs Shopware dev-tooling checks — PHPStan, ECS, PHPUnit, Rector, ESLint, Stylelint, Prettier, TypeScript, Jest, Vitest, ludtwig, and Vite/Webpack builds — plus the rule-driven fixers (ecsfix, rectorfix, eslint/stylelint/prettier/ludtwig fix) on the files it is given and returns a condensed pass/fail report. Use when…

shopwareLabs/ai-coding-tools · 141 tokens