eval-validity-review

eval-validity-review is a skill for Claude Code from UKGovernmentBEIS/inspect_evals. It costs 83 tokens per session (5,225 once invoked), scanned A, original, MIT.

A review process for checking whether an evaluation really measures the ability it claims to measure. An evaluation is a test used to compare how well systems perform.

In plain words
What is it for?
It helps assess an evaluation's claims, name, test data, and scoring method, then produce findings and recommendations without changing the evaluation code.
Why use it?
It can reveal unsupported claims, misleading names, samples that cannot distinguish success from failure, or scores that measure a substitute instead of the real target.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps assess an evaluation's claims, name, test data, and scoring method, then produce findings and recommendations without changing the evaluation code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ukgovernmentbeis/inspect_evals/eval-validity-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 UKGovernmentBEIS/inspect_evals --skill eval-validity-review
Clone the repo
git clone --depth 1 https://github.com/UKGovernmentBEIS/inspect_evals

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 eval-validity-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ukgovernmentbeis/inspect_evals/eval-validity-review"><img src="https://agentmods.dev/badge/skills/ukgovernmentbeis/inspect_evals/eval-validity-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,225 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 pass 7 Sept 2026
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 $0.00083 $0.05225
Opus 5 $0.00042 $0.02612
Sonnet 5 $0.00017 $0.01045
Haiku 4.5 $0.00008 $0.00522

Measured 10d ago against content hash a94698c3a88c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eval-validity-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 10d 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/skills/eval-validity-review/SKILL.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluation Validity Review

This skill assesses whether an evaluation measures what it claims to measure. It checks four dimensions of validity:

  1. Claims Coherence — Do the evaluation's claims about its data, mechanisms, capabilities, and results hold up under scrutiny?
  2. Name Validity — Does the name accurately represent the capability being measured?
  3. Dataset Validity — Can models both succeed and fail at each sample given the available affordances?
  4. Scoring Validity — Does the scorer measure ground truth rather than proxies?

The first dimension is a high-level sense check that should be performed before diving into the mechanical details of the other three. If the evaluation's claims are fundamentally false or unsupported, the detailed checks matter less.

This review is read-only. It produces a report with findings and recommendations but does not modify evaluation code.

Important: The phases below are guidelines, not a rigid checklist. Use your judgement throughout. If something feels off at any point — an explanation that doesn't quite add up, a mechanism that seems more complex than it needs to be, samples that feel generic rather than sourced — investigate it, even if no specific step tells you to. The goal is to determine whether the evaluation is sound, not to mechanically complete every listed check.

Identifying the Evaluation

If the user has given you a name, that takes priority. If you were just building an evaluation, or the user has uncommitted code for one specific evaluation, you can assume that's the correct one. If you are not confident which evaluation to look at, ask the user.

Setup

  1. Determine the evaluation name (the folder name under src/inspect_evals/). This will be referred to as <eval_name>.
  2. Determine the task version from the @task function's version argument. Combine them as <eval_name>_<version> (e.g., gpqa_1_1_2). If this exact folder name already exists under agent_artefacts/, append a number (e.g., gpqa_1_1_2_2). This combined name is referred to as <artefact_name>.
  3. Create the output directory: agent_artefacts/<artefact_name>/validity/
  4. All .md files created by this workflow go in that directory.
  5. Create a NOTES.md file for recording observations during the review. Err on the side of taking lots of notes.

Read the full file on GitHub · 356 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. 10d ago First seen · 356 lines · 83 tokens per session scan A a94698c3a88c

Subscribe to this mod's changes

eval-validity-review is a skill published in the GitHub repository UKGovernmentBEIS/inspect_evals (664 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 5,225 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.