eval-review

eval-review is a skill for Claude Code from opendatahub-io/agent-eval-harness. It costs 123 tokens per session (2,188 once invoked), scanned A, original, Apache-2.0.

An interactive skill for reviewing the results of an agent evaluation, which is a test run that scores an agent’s output. It collects human feedback and suggests focused changes to the skill or other instructions being tested.

In plain words
What is it for?
Use it to inspect a completed evaluation run, discuss what the judges missed, and improve a SKILL.md file or another tested instruction document.
Why use it?
Automated scores may miss problems with tone, intent, or usefulness. Human review adds context and turns that feedback into proposed instruction improvements.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the agent-eval-harness plugin — 10 skills shipped together

Good fit Use it to inspect a completed evaluation run, discuss what the judges missed, and improve a SKILL.md file or another tested instruction document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendatahub-io/agent-eval-harness/eval-review
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.

Any agent
npx skills add opendatahub-io/agent-eval-harness --skill eval-review
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/agent-eval-harness

Made for: Claude Code.

Or install agent-eval-harness, the plugin that ships this one along with the rest of its 10 skills.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-review/github.svg)](https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-review)
Your own site
<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-review"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-review/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 eval-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-review"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,188 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 139
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
How audits are shown
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 $0.00123 $0.02188
Opus 5 $0.00062 $0.01094
Sonnet 5 $0.00025 $0.00438
Haiku 4.5 $0.00012 $0.00219

Measured 8d ago against content hash 82a5ec0a6008, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

eval-review 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 8d 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-review/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an interactive reviewer. You present evaluation results to the user, collect their qualitative feedback, analyze patterns in what judges missed vs what humans noticed, and propose targeted SKILL.md improvements. You work alongside /eval-optimize (automated fixes) by catching things that judges can't — tone, intent, user experience.

Target artifact. Proposing SKILL.md changes assumes a skill under test (execution.skill). For prompt-mode evals (execution.prompt, from /eval-analyze --prompt) there is no skill — the artifact under test is the documentation or analysis prompt (e.g. CLAUDE.md, ai-docs/). Propose improvements to that artifact instead; everywhere below that says "SKILL.md", read "the artifact under test".

Step 0: Parse Arguments

Argument Required Default Description
--run-id <id> yes Which eval run to review
--config <path> no auto-discover Path to eval config
--cases <name> [<name> ...] no all Exact case directory names to review

Config Discovery

If --config was explicitly provided, use that path directly. Otherwise, auto-discover:

python3 ${CLAUDE_SKILL_DIR}/../../scripts/discover.py
  • 1 config found: auto-select it as <config>
  • Multiple configs found: present the list and ask the user which eval's results to review
  • No configs found: error, suggest running /eval-analyze first

After selecting a config, read its skill field to set <eval-name> (used in $AGENT_EVAL_RUNS_DIR/<eval-name>/<id> paths below).

Step 1: Load Results

Read the scoring summary and per-case results:

python3 ${CLAUDE_SKILL_DIR}/scripts/agent_eval/state.py read $AGENT_EVAL_RUNS_DIR/<eval-name>/<id>/summary.yaml

Also read eval.yaml to understand the skill being tested, the dataset schema, and the judges configured. Note the judge types — builtin Python and inline checks are deterministic (structural failures), LLM judges and LLM builtins are qualitative (judgment-based). The judge_type field is available in results.

Read the full file on GitHub · 146 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago Changed 82a5ec0a6008
  2. 12d ago First seen · 146 lines · 123 tokens per session scan A 1a948083414c

Subscribe to this mod's changes

eval-review is a skill published in the GitHub repository opendatahub-io/agent-eval-harness (41 stars, last pushed 9d ago), licensed Apache-2.0. It adds 123 tokens to every session and 2,188 once invoked, about $0.0006 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens