eval-harness

eval-harness is a skill for Claude Code from KratosAR/claude-code-arsenal. It costs 19 tokens per session (1,647 once invoked), scanned A, a copy of eval-harness, MIT.

A testing framework for Claude Code sessions that checks whether an AI agent completes tasks as expected. It applies eval-driven development, meaning you define expected behavior first and test it throughout development.

In plain words
What is it for?
Use it to define capability tests, regression test suites, and reliability measurements, including pass@k—the rate at which an agent succeeds across repeated attempts. It can also compare performance between model versions.
Why use it?
It replaces guesswork about agent reliability with repeatable pass/fail checks. It also helps detect when a prompt or model change breaks behavior that previously worked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the arsenal-core plugin — 43 skills, 15 agents shipped together

Good fit Use it to define capability tests, regression test suites, and reliability measurements, including pass@k—the rate at which an agent succeeds across repeated attempts. It can also compare performance between model versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kratosar/claude-code-arsenal/eval-harness
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 KratosAR/claude-code-arsenal --skill eval-harness
Clone the repo
git clone --depth 1 https://github.com/KratosAR/claude-code-arsenal

Made for: Claude Code.

Or install arsenal-core, the plugin that ships this one along with the rest of its 43 skills, 15 agents.

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-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/kratosar/claude-code-arsenal/eval-harness.svg)](https://agentmods.dev/skills/kratosar/claude-code-arsenal/eval-harness)
Your own site
<a href="https://agentmods.dev/skills/kratosar/claude-code-arsenal/eval-harness"><img src="https://agentmods.dev/badge/skills/kratosar/claude-code-arsenal/eval-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,647 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.
Origin 84% copy Near-identical to another mod 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 $0.00019 $0.01647
Opus 5 $0.00010 $0.00823
Sonnet 5 $0.00004 $0.00329
Haiku 4.5 $0.00002 $0.00165

Measured 7d ago against content hash 5aa3cf00a03b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

eval-harness 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 7d 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.

Origin

This is a copy

84% identical to eval-harness — 54 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

arsenal-core/skills/eval-harness/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Harness Skill

A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.

When to Activate

  • Setting up eval-driven development (EDD) for AI-assisted workflows
  • Defining pass/fail criteria for Claude Code task completion
  • Measuring agent reliability with pass@k metrics
  • Creating regression test suites for prompt or agent changes
  • Benchmarking agent performance across model versions

Philosophy

Eval-Driven Development treats evals as the "unit tests of AI development":

  • Define expected behavior BEFORE implementation
  • Run evals continuously during development
  • Track regressions with each change
  • Use pass@k metrics for reliability measurement

Eval Types

Capability Evals

Test if Claude can do something it couldn't before:

[CAPABILITY EVAL: feature-name]
Task: Description of what Claude should accomplish
Success Criteria:
  - [ ] Criterion 1
  - [ ] Criterion 2
  - [ ] Criterion 3
Expected Output: Description of expected result

Regression Evals

Ensure changes don't break existing functionality:

[REGRESSION EVAL: feature-name]
Baseline: SHA or checkpoint name
Tests:
  - existing-test-1: PASS/FAIL
  - existing-test-2: PASS/FAIL
  - existing-test-3: PASS/FAIL
Result: X/Y passed (previously Y/Y)

Grader Types

1. Code-Based Grader

Deterministic checks using code:

# Check if file contains expected pattern
grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"

# Check if tests pass
npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL"

# Check if build succeeds
npm run build && echo "PASS" || echo "FAIL"

2. Model-Based Grader

Use Claude to evaluate open-ended outputs:

[MODEL GRADER PROMPT]
Evaluate the following code change:
1. Does it solve the stated problem?
2. Is it well-structured?
3. Are edge cases handled?
4. Is error handling appropriate?

Score: 1-5 (1=poor, 5=excellent)
Reasoning: [explanation]

Read the full file on GitHub · 298 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. 7d ago First seen · 298 lines · 19 tokens per session scan A 5aa3cf00a03b

Subscribe to this mod's changes

eval-harness is a skill published in the GitHub repository KratosAR/claude-code-arsenal (2 stars, last pushed 21d ago), licensed MIT. It adds 19 tokens to every session and 1,647 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to eval-harness, differing in 54 lines, and is treated as a copy.

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