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.
npx skills add Galileo-Agent-Labs/eval-engineer --skill eval-setupgit clone --depth 1 https://github.com/Galileo-Agent-Labs/eval-engineerWrote 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.
[](https://agentmods.dev/skills/galileo-agent-labs/eval-engineer/eval-setup)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00735 |
| Opus 5.5 | $0.00016 | $0.00294 |
| Sonnet 5.5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
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 1mo 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.
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.mdexist. - 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.mdand 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.mdto 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.
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.
- 1mo ago First seen · 76 lines · 41 tokens per session scan A bc16d843efe6
eval-setup is a skill published in the GitHub repository Galileo-Agent-Labs/eval-engineer (43 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 735 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
agent-testing-harness
Use this skill when testing AI agent systems. Activate when the user needs to test agent behavior, write tests for multi-agent systems, implement agent evaluation frameworks, create test harnesses for autonomous agents, or validate agent outputs systematically.
test-generation-patterns
Use this skill when generating tests with AI assistance. Activate when the user wants to create unit tests, integration tests, generate test cases, improve test coverage, write tests for existing code, or set up testing patterns for their project.
api-test-patterns
Write comprehensive API tests for REST and GraphQL endpoints. Use this skill when testing APIs, writing contract tests, or validating integrations. Activate when: api testing, REST test, GraphQL test, endpoint testing, integration test, postman, contract testing.
playwright-patterns
Write reliable, maintainable E2E tests with Playwright best practices. Use this skill when writing Playwright tests, debugging flaky tests, or setting up E2E automation. Activate when: playwright, e2e test, end-to-end, browser testing, UI automation, web testing.
test-case-design
Design comprehensive test cases with proper coverage and clear documentation. Use this skill when writing test cases, creating test suites, or improving test coverage. Activate when: test case, test scenario, test coverage, test design, write tests, BDD, gherkin.
skill-testing
Test skills for correct activation, content quality, and regression — both automated checks (frontmatter validity, lint) and manual verification (query-suite activation testing). Covers CI integration and how to catch skill regressions before users do. Use this skill when adding skills to a repo, setting up CI for a…