anthropic-evaluations

anthropic-evaluations is a skill for Claude Code from dwmkerr/claude-toolkit. It costs 59 tokens per session (847 once invoked), scanned A, original, MIT.

A framework for testing AI agents with repeatable tasks, recorded attempts, and scoring rules. It covers code-based, model-based, and human review, including patterns for coding, conversational, research, and computer-use agents.

In plain words
What is it for?
It helps create evaluation suites, define success criteria, run trials, record transcripts, and grade coding or other AI agents.
Why use it?
It makes agent quality measurable instead of relying only on occasional manual checks. Repeated trials can reveal whether an agent succeeds consistently and whether its final result is actually correct.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the toolkit plugin — 15 skills, 3 commands, 1 agent shipped together

Good fit It helps create evaluation suites, define success criteria, run trials, record transcripts, and grade coding or other AI agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dwmkerr/claude-toolkit/anthropic-evaluations
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 dwmkerr/claude-toolkit --skill anthropic-evaluations
Clone the repo
git clone --depth 1 https://github.com/dwmkerr/claude-toolkit

Made for: Claude Code.

Or install toolkit, the plugin that ships this one along with the rest of its 15 skills, 3 commands, 1 agent.

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 anthropic-evaluations

README.md
[![agentmods](https://agentmods.dev/badge/skills/dwmkerr/claude-toolkit/anthropic-evaluations/github.svg)](https://agentmods.dev/skills/dwmkerr/claude-toolkit/anthropic-evaluations)
Your own site
<a href="https://agentmods.dev/skills/dwmkerr/claude-toolkit/anthropic-evaluations"><img src="https://agentmods.dev/badge/skills/dwmkerr/claude-toolkit/anthropic-evaluations/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 anthropic-evaluations

Your own site · 80×15
<a href="https://agentmods.dev/skills/dwmkerr/claude-toolkit/anthropic-evaluations"><img src="https://agentmods.dev/badge/skills/dwmkerr/claude-toolkit/anthropic-evaluations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 847 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 $0.00059 $0.00847
Opus 5 $0.00030 $0.00424
Sonnet 5 $0.00012 $0.00169
Haiku 4.5 $0.00006 $0.00085

Measured 9d ago against content hash 8dea0968bbfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

anthropic-evaluations 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 9d 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.

plugins/toolkit/skills/anthropic-evaluations/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anthropic Evaluations

Build rigorous evaluations for AI agents using Anthropic's proven patterns.

Quick Reference

You MUST read the reference files for detailed guidance:

YAML Templates:

Annotated Examples:

Core Definitions

Term Definition
Task Single test with defined inputs and success criteria
Trial One attempt at a task (run multiple for consistency)
Grader Logic that scores agent performance; tasks can have multiple
Transcript Complete record of a trial (outputs, tool calls, reasoning)
Outcome Final state in environment (not just what agent said)
Evaluation harness Infrastructure that runs evals end-to-end
Agent harness System enabling model to act as agent (scaffold)
Evaluation suite Collection of tasks measuring specific capabilities

Grader Types (Quick Reference)

Type Methods Best For
Code-based String match, unit tests, static analysis, state checks Fast, cheap, objective verification
Model-based Rubric scoring, assertions, pairwise comparison Nuanced, open-ended tasks
Human SME review, A/B testing, spot-check sampling Gold standard calibration

Read the full file on GitHub · 84 lines

Files

What ships with it

8 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. 9d ago First seen · 84 lines · 59 tokens per session scan A 8dea0968bbfc

Subscribe to this mod's changes

anthropic-evaluations is a skill published in the GitHub repository dwmkerr/claude-toolkit (23 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 847 once invoked, about $0.0003 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

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens