eval-harness

A framework for testing whether AI-assisted coding sessions produce the expected results. Eval-driven development means defining success checks before implementation and running them like tests for an AI workflow.

In plain words
What is it for?
Use it to define pass/fail criteria, build capability and regression evaluations, measure pass@k reliability, and compare agent performance across model versions.
Why use it?
It makes agent reliability visible and helps catch regressions when prompts, workflows, or models change.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,405 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% 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 $0.00019 $0.01405
Opus 5 $0.00010 $0.00702
Sonnet 5 $0.00004 $0.00281
Haiku 4.5 $0.00002 $0.00140

Measured 2d ago against content hash 0bc29828b0b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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

91% identical to eval-harness — 5 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.

data/affaanmustafa/eval-harness/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 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 · 237 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 · 237 lines · 19 tokens per session scan A 0bc29828b0b2

Subscribe to this mod's changes

eval-harness is a skill published in the GitHub repository x-cmd/skill (26 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,405 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to eval-harness, differing in 5 lines, and is treated as a copy.

Related

Other skills, from other repositories

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

CherryHQ/cherry-studio · 64 tokens

gh-pr-review

Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks…

CherryHQ/cherry-studio · 147 tokens

prepare-release

Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run /prepare-release.

CherryHQ/cherry-studio · 44 tokens

claude-automation-recommender

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what…

CherryHQ/cherry-studio · 77 tokens

cherry-tool-guide

Cherry Studio first-party tool and bundled-shell routing for general agents. For straightforward local work in shell-capable sessions, run JS/TS with bun and one-off JS tools with bun x; run Python with uv run [--with ] python and one-off Python CLIs with uvx; search with rg. Load this guide before changing project…

CherryHQ/cherry-studio · 171 tokens

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

CherryHQ/cherry-studio · 67 tokens