eval-harness

eval-harness is a skill for Claude Code, Codex from JSK9999/ai-nexus. It costs 18 tokens per session (1,323 once invoked), scanned A, a copy of eval-harness, Apache-2.0.

A framework for evaluating coding-agent abilities and checking that changes do not break existing behavior. It treats evaluations, or tests of agent results, as a development tool.

In plain words
What is it for?
Defining capability and regression evaluations, checking results with code-based graders, and tracking reliability with pass@k measurements.
Why use it?
It makes expected behavior explicit and helps detect regressions, meaning previously working behavior that stops working after a change.

Skill for Claude CodeCodex

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

Good fit Defining capability and regression evaluations, checking results with code-based graders, and tracking reliability with pass@k measurements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jsk9999/ai-nexus/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 JSK9999/ai-nexus --skill eval-harness
Clone the repo
git clone --depth 1 https://github.com/JSK9999/ai-nexus

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/jsk9999/ai-nexus/eval-harness/github.svg)](https://agentmods.dev/skills/jsk9999/ai-nexus/eval-harness)
Your own site
<a href="https://agentmods.dev/skills/jsk9999/ai-nexus/eval-harness"><img src="https://agentmods.dev/badge/skills/jsk9999/ai-nexus/eval-harness/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-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/jsk9999/ai-nexus/eval-harness"><img src="https://agentmods.dev/badge/skills/jsk9999/ai-nexus/eval-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,323 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 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 $0.00018 $0.01323
Opus 5 $0.00009 $0.00661
Sonnet 5 $0.00004 $0.00265
Haiku 4.5 $0.00002 $0.00132

Measured 10d ago against content hash 5078be09d63d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 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.

Origin

This is a copy

83% identical to eval-harness — 11 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.

config/skills/eval-harness/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 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.

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]

3. Human Grader

Flag for manual review:

[HUMAN REVIEW REQUIRED]
Change: Description of what changed
Reason: Why human review is needed
Risk Level: LOW/MEDIUM/HIGH

Metrics

pass@k

"At least one success in k attempts"

  • pass@1: First attempt success rate
  • pass@3: Success within 3 attempts
  • Typical target: pass@3 > 90%

Read the full file on GitHub · 227 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 · 227 lines · 18 tokens per session scan A 5078be09d63d

Subscribe to this mod's changes

eval-harness is a skill published in the GitHub repository JSK9999/ai-nexus (19 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,323 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 11 lines, and is treated as a copy.

Related

Other skills, from other repositories

Cursor Skill (.mdc) Authoring

Author effective Cursor rules in .cursor/rules/.mdc - YAML frontmatter (description, globs, alwaysApply), the four rule types, scoped QA rules, subagents, and structure that actually steers the model.

PramodDutta/qaskills · 55 tokens

test-fix

Diagnose and minimally fix a failing test, then re-run.

patriceckhart/zot · 17 tokens

hatch3r-browser-verify

Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…

hatch3r/hatch3r · 83 tokens

hatch3r-feature

End-to-end feature implementation workflow. Covers data model, domain logic, API, and UI as a vertical slice. Use when implementing new features or working on feature request issues.

hatch3r/hatch3r · 41 tokens

hatch3r-qa-path

Produces a human-run manual QA test path from a PR, branch diff, or uncommitted working tree — a risk-ordered table of steps, expected results, and automated-coverage references plus a shippability sign-off. Rows are auto-proven via delegated verification sub-agents before emission, so the human walks only what…

hatch3r/hatch3r · 100 tokens

hatch3r-bug-fix

Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.

hatch3r/hatch3r · 47 tokens