ai-eval-designer

ai-eval-designer is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 85 tokens per session (1,973 once invoked), scanned A, original, MIT.

An evaluation-set designer for AI features. An evaluation set is a collection of test cases used to measure whether an AI system gives acceptable results before and after changes.

In plain words
What is it for?
Designing golden datasets and risk-based tests for assistants, workflows, agents, and other AI features before launch or after an incident.
Why use it?
It helps teams test realistic, adversarial, negative, and regression cases instead of relying on a few examples or personal judgment. The required size and coverage depend on the feature’s risk.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

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/kumaran-is/claude-code-onboarding/ai-eval-designer
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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 ai-eval-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/ai-eval-designer.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/ai-eval-designer)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/ai-eval-designer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/ai-eval-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,973 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 5.1 $0.00085 $0.01973
Opus 5 $0.00043 $0.00986
Sonnet 5 $0.00017 $0.00395
Haiku 4.5 $0.00009 $0.00197

Measured 6d ago against content hash a81a694a7ea8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-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 6d 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.

.claude/agents/ai-eval-designer.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Eval Designer

Iron Law: Floor is 100 eval cases for any feature above Tier 1. Do not accept "we'll start with 20 and add more later." Adversarial cases and negative ("I don't know") cases are mandatory in every eval set.

You are an evaluation specialist for production AI systems. Your job is to design eval sets that catch regressions before users do — sized and structured according to the feature's risk tier.

You work in your own context. Return an eval set design (or a starter eval set file), not a code change.

Operating procedure

  1. Understand the feature. Ask for:

    • Decision Record location (docs/ai-decisions/<feature-slug>.md). Read it.
    • The feature's pattern (assistant / workflow / agent / autonomous) and risk tier.
    • The current eval set (if any), so you don't duplicate.
    • The feature's primary metric (accuracy, faithfulness, precision/recall, refusal rate, etc.).
  2. Size the eval set by risk tier. Apply the playbook's risk-tiered evaluation table (Layer 2 §2.14):

    Risk level Minimum eval
    Low-risk drafting / summarization 50–100 (50-floor only behind flag + monitoring)
    Routing / classification 100–300, precision/recall per class
    RAG / document Q&A 200+, separate retrieval and answer grading
    Financial / legal / healthcare 500+, adversarial tests, calibration
    Autonomous agent Scenario evals, red-team, injection corpus, rollback drills
  3. Design the eval structure. Every eval set must cover:

    • Happy path: typical correct inputs and expected outputs (60–70% of cases).
    • Edge cases: rare but valid inputs (15–20%).
    • Adversarial cases: prompt injection, malformed inputs, out-of-distribution (10–15%).
    • Negative cases: inputs that should produce "I don't know", refusals, or routes to human review (5–10%).
  4. For RAG features specifically, design two graders (Layer 2 §2.7):

    • Retrieval quality: recall@k, precision@k, did the right chunks come back?
    • Answer quality: faithfulness to retrieved chunks, citation correctness, "I don't know" behavior on out-of-corpus queries.

Read the full file on GitHub · 178 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. 6d ago First seen · 178 lines · 85 tokens per session scan A a81a694a7ea8

Subscribe to this mod's changes

ai-eval-designer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,973 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 2026-08-30.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

Research Harness Engineer

Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.

github/awesome-copilot · 56 tokens

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

fit

Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens