eval-audit

eval-audit is a skill for Claude Code, Codex from Galileo-Agent-Labs/eval-engineer. It costs 40 tokens per session (373 once invoked), scanned A, original, MIT.

A review workflow for checking an AI application before launch or after a production problem. It examines code, evidence, measurements, and workflow coverage, including security and safety risks.

In plain words
What is it for?
Use it for launch-readiness reviews, safety and security audits, OWASP agentic-risk checks, metric-coverage reviews, and production root-cause-analysis gap reviews.
Why use it?
It helps find unsafe permissions, data exposure, prompt injection risks, missing approval steps, weak monitoring, and gaps in failure evidence before they become larger problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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-audit
Any agent
npx skills add Galileo-Agent-Labs/eval-engineer --skill eval-audit
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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/galileo-agent-labs/eval-engineer/eval-audit.svg)](https://agentmods.dev/skills/galileo-agent-labs/eval-engineer/eval-audit)
Your own site
<a href="https://agentmods.dev/skills/galileo-agent-labs/eval-engineer/eval-audit"><img src="https://agentmods.dev/badge/skills/galileo-agent-labs/eval-engineer/eval-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 373 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 $0.00040 $0.00373
Opus 5 $0.00020 $0.00187
Sonnet 5 $0.00008 $0.00075
Haiku 4.5 $0.00004 $0.00037

Measured 6d ago against content hash e03b2c54ca89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

eval-audit 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.

skills/eval-audit/SKILL.md · 42 lines

What it actually says

Eval Audit

Use this skill to find risk before changing the app. Audits inspect evidence, code, metrics, and workflow coverage. Do not fix by default.

Audit Areas

  • OWASP agentic AI risks: control plane, tool permissions, data exposure, indirect prompt injection, identity boundaries, approval gates, and unsafe autonomy.
  • Metric coverage: quality, safety, grounding, cost, latency, tool behavior, segment regressions, and missing expected-output contracts.
  • Evidence quality: links back to Galileo traces, spans, sessions, log streams, experiments, and scorer status.
  • Launch readiness: failure cases, rollback criteria, verification commands, privacy/PII risks, and production monitoring gaps.

Secret Handling

Do not read secret values from .env, shell history, key files, or credential stores during an audit. It is okay to report variable names, expected variable presence, whether .env is ignored by git, and whether a project is a git repo. If values were already exposed in chat, logs, or committed files, recommend rotation; do not infer compromise merely because a local ignored .env exists.

Validation Loop

Before finalizing, check that each finding includes severity, evidence, affected surface, and the next command or verification step. If evidence is missing, mark the finding as a gap rather than a confirmed defect.

Output

Produce findings first, ordered by severity. Include evidence references and the next command: /eval-measure, /eval-fetch, /eval-diagnose, or /eval-cost.

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 · 42 lines · 40 tokens per session scan A e03b2c54ca89

Subscribe to this mod's changes

eval-audit is a skill published in the GitHub repository Galileo-Agent-Labs/eval-engineer (41 stars, last pushed 24d ago), licensed MIT. It adds 40 tokens to every session and 373 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-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

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

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