eval-harness

eval-harness is a skill for Claude Code, Codex from gongyijie85/dsh-ecc. It costs 37 tokens per session (1,667 once invoked), scanned A, a copy of eval-harness, MIT.

A framework for testing whether an AI coding session behaves as expected before trusting or changing it. It treats evaluations as repeatable checks, similar to unit tests for AI workflows.

In plain words
What is it for?
Use it to create pass/fail evaluations, regression suites, reliability measurements, and comparisons between agent or model versions.
Why use it?
It helps define success clearly and catch regressions when prompts, agents, or models change.

Skill for Claude CodeCodex

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

Good fit Use it to create pass/fail evaluations, regression suites, reliability measurements, and comparisons between agent or model versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gongyijie85/dsh-ecc/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 gongyijie85/dsh-ecc --skill eval-harness
Clone the repo
git clone --depth 1 https://github.com/gongyijie85/dsh-ecc

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/gongyijie85/dsh-ecc/eval-harness/github.svg)](https://agentmods.dev/skills/gongyijie85/dsh-ecc/eval-harness)
Your own site
<a href="https://agentmods.dev/skills/gongyijie85/dsh-ecc/eval-harness"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/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/gongyijie85/dsh-ecc/eval-harness"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/eval-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,667 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 80% 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 $0.00037 $0.01667
Opus 5 $0.00018 $0.00834
Sonnet 5 $0.00007 $0.00333
Haiku 4.5 $0.00004 $0.00167

Measured 8d ago against content hash 9d3afbeca147, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 8d 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

80% 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. 8d ago First seen · 272 lines · 37 tokens per session scan A 9d3afbeca147

Subscribe to this mod's changes

eval-harness is a skill published in the GitHub repository gongyijie85/dsh-ecc (7 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,667 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to eval-harness, differing in 28 lines, and is treated as a copy.

Related

Other skills, from other repositories

manage-taskboard

Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…

shengsheng90/DSH-taskboard · 88 tokens

delivery-proof

Delivery proof and the doublecheck report. Use when the work is done and the delivery must be proven — consolidate the spec, test timeline, review verdicts, and verification checks into a doublecheckreport, and only then claim completion.

PerryLink/dsh-doublecheck · 50 tokens

red-green-tdd

Red/green test discipline for implementation work. Use once a doublecheck spec is on record and implementation is about to start — write a test that fails for the missing behavior, run it to see it fail (red), make the change, run again to see it pass (green).

PerryLink/dsh-doublecheck · 62 tokens

codebase-design-zh

A set of design principles for creating modules with small interfaces and substantial behaviour behind them. It explains terms such as interface, implementation, adapter, and seam in plain terms for this design approach.

gongyijie85/mattpocock-skills-dsh-zh · 70 tokens

code2skill-review-flow

A read-only reviewer for the main user flows in a package generated by Code2Skill. It checks whether representative paths are basically usable, without proving that every source-code detail is included.

leechen298/Code2Skill · 32 tokens

dev-qa

A development and quality process for building software, testing it, and checking it for security problems. It separates implementation, quality assurance, and security review while coordinating their handoffs.

songoao25/dsh-virtual-product-team · 50 tokens