eval-setup

eval-setup is a skill for Claude Code, Codex from Galileo-Agent-Labs/eval-engineer. It costs 41 tokens per session (735 once invoked), scanned A, original, MIT.

A setup guide for preparing a software project for Eval Engineer, a system for evaluating an AI application. It creates or reviews folders and configuration files and identifies the evidence still needed for later investigation.

In plain words
What is it for?
Use it to configure evaluation folders, record the application type and editable files, define verification commands, and identify needed traces, sessions, logs, experiments, metrics, or Galileo connection details.
Why use it?
It prevents a project from being described as ready for diagnosis when only basic setup is complete. It also keeps existing configuration and evidence intact while making missing inputs visible.

Skill for Claude CodeCodex

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/galileo-agent-labs/eval-engineer/eval-setup
Any agent
npx skills add Galileo-Agent-Labs/eval-engineer --skill eval-setup
Clone the repo
git clone --depth 1 https://github.com/Galileo-Agent-Labs/eval-engineer

Made for: Claude Code, Codex.

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 eval-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/galileo-agent-labs/eval-engineer/eval-setup.svg)](https://agentmods.dev/skills/galileo-agent-labs/eval-engineer/eval-setup)
Your own site
<a href="https://agentmods.dev/skills/galileo-agent-labs/eval-engineer/eval-setup"><img src="https://agentmods.dev/badge/skills/galileo-agent-labs/eval-engineer/eval-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 735 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 $0.00041 $0.00735
Opus 5 $0.00020 $0.00367
Sonnet 5 $0.00008 $0.00147
Haiku 4.5 $0.00004 $0.00073

Measured 3d ago against content hash bc16d843efe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval-setup 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 3d 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.

skills/eval-setup/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Setup

Use this skill to make a repo ready for Eval Engineer without pretending it is ready for RCA. Setup is operational: create or review workspace files, identify missing configuration, and tell the user what evidence is still needed.

Do

  • Ensure .galileo/config.yml, .galileo/current/, .galileo/eval-dataset/, .galileo/sessions/, and .galileo/learnings.md exist.
  • Preserve existing files. Do not overwrite user configuration or evidence.
  • Help fill in app type, editable files, blocked files, and verification commands when the user knows them.
  • Explain which evidence is needed next: trace, session, log stream, experiment, metric profile, or verification packet.
  • For live Galileo work, load skills/eval-engineer/references/galileo-live-readiness.md and report the project, evidence source, traces, metrics, scorer/recompute job, and queryable metric status before saying setup is ready.
  • Before creating or accepting local eval evidence, use skills/eval-engineer/references/galileo-integration-intake.md to ask for the required Galileo project, log stream, experiment, session, trace, metric/scorer, time window, or credential confirmation.
  • If the user wants local-only evaluation, record explicit local-only confirmation before creating local packets, scripts, or score reports.

Do Not

  • Do not guess metrics, providers, app type, or production safety requirements.
  • Do not fetch Galileo evidence unless the user provides a URL/ID or asks for /eval-fetch.
  • Do not create .galileo/current/debug-packet.json, verification packets, scripts/evaluate_*, synthetic traces, or local score reports as a substitute for missing Galileo integration inputs.
  • Do not diagnose or fix application behavior during setup.
  • Do not call a Galileo project ready when only the project exists. A ready Galileo source needs a log stream, experiment, session, or trace with records, enabled metrics, completed scoring/recompute, and queryable metric values.

Read the full file on GitHub · 76 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. 3d ago First seen · 76 lines · 41 tokens per session scan A bc16d843efe6

Subscribe to this mod's changes

eval-setup is a skill published in the GitHub repository Galileo-Agent-Labs/eval-engineer (41 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 735 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 2026-08-30.

Related

Other skills, from other repositories

install-gemini-code-review-action

Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.

derailed-dash/dazbo-agent-skills · 73 tokens

convert-to-devto

Converts Markdown content into the format required for Dev.to publication, ensuring correct YAML frontmatter, headers, liquid tags, and inline formatting. Use when the user asks to format or convert an existing blog post or Markdown file for Dev.to.

derailed-dash/dazbo-agent-skills · 53 tokens

fw-ai-actions-app

Expert-level skill for AI Actions and integrations on Freshworks Platform 3.0. Use when (1) Creating actions.json and SMI functions (flat request, nested response), (2) Request templates and third-party API integration, (3) Pre-build validation (pricing, paywalls, account prerequisites), (4) Failure-case validation…

freshworks-developers/fw-dev-tools · 123 tokens

fw-review

Full Freshworks marketplace app review — iparams, frontend, serverless, FDK, security, and structured text report output — in one skill.

freshworks-developers/fw-dev-tools · 34 tokens

secrets-with-git-crypt

Manages encryption and decryption of repository secrets (such as .env or .tfvars) using git-crypt, keeping credentials secure with parallel encrypted files. Use when managing secrets, setting up git-crypt, or encrypting/decrypting environment files.

derailed-dash/dazbo-agent-skills · 60 tokens

create-md-from-browsermcp-snapshot

Extracts and converts BrowserMCP accessibility tree snapshots into clean, high-fidelity Markdown documents with correct structures (headings, lists, tables, blockquotes, formatting, and links). Use when the user asks to create a markdown document from a webpage; especially if they ask to do it with BrowserMCP.

derailed-dash/dazbo-agent-skills · 75 tokens