eval-harness

eval-harness is a skill for Claude Code, Codex from JunMystery/Agent-Guidance-Python. It costs 19 tokens per session (1,650 once invoked), scanned A, a copy of eval-harness, MIT.

A formal way to evaluate AI coding sessions using predefined pass/fail checks. Eval-driven development treats these checks like automated tests for an AI workflow.

In plain words
What is it for?
It helps define capability and regression evaluations, measure pass@k reliability, build test suites for prompts or agents, and compare model versions.
Why use it?
It helps reveal regressions and unreliable agent behavior instead of relying on the agent to judge its own work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

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/junmystery/agent-guidance-python/eval-harness
Any agent
npx skills add JunMystery/Agent-Guidance-Python --skill eval-harness
Clone the repo
git clone --depth 1 https://github.com/JunMystery/Agent-Guidance-Python

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-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/junmystery/agent-guidance-python/eval-harness.svg)](https://agentmods.dev/skills/junmystery/agent-guidance-python/eval-harness)
Your own site
<a href="https://agentmods.dev/skills/junmystery/agent-guidance-python/eval-harness"><img src="https://agentmods.dev/badge/skills/junmystery/agent-guidance-python/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 1,650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 83% 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 $0.01650
Opus 5 $0.00010 $0.00825
Sonnet 5 $0.00004 $0.00330
Haiku 4.5 $0.00002 $0.00165

Measured 2d ago against content hash 2b0b5256a043, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 2d 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

83% identical to eval-harness — 28 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.

skills/eval-harness/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 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 · 272 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. 2d ago First seen · 272 lines · 19 tokens per session scan A 2b0b5256a043

Subscribe to this mod's changes

eval-harness is a skill published in the GitHub repository JunMystery/Agent-Guidance-Python (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,650 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to eval-harness, differing in 28 lines, and is treated as a copy.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

planning-and-task-breakdown

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

shashankswe2020-ux/whoop-mcp · 56 tokens

frontmcp-setup

Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…

agentfront/frontmcp · 176 tokens

compliance-frameworks

ISO 27001, NIST CSF 2.0, CIS Controls v8.1, EU CRA compliance mapping, multi-standard alignment per Hack23 ISMS policies.

Hack23/European-Parliament-MCP-Server · 40 tokens

arkana-analyse

British English alias for the arkana-analyze skill. Binary analysis skill for Arkana. Triggers on: analyse, analyze, binary, malware, reverse engineer.

JameZUK/Arkana · 38 tokens

apitap

ApiTap gives AI agents cheap access to web data through three layers.

n1byn1kt/apitap · 0 tokens