eval-harness-skill

eval-harness-skill is a skill for OpenCode from darellchua2/opencode-config-template. It costs 24 tokens per session (2,397 once invoked), scanned C, original, Apache-2.0.

An evaluation framework for judging code, agent skills, and implementations against defined criteria. It produces scores and written feedback about what meets the bar and what does not.

In plain words
What is it for?
Use it to define quality criteria, run evaluations, score results, find gaps, and track improvement over time.
Why use it?
It replaces informal review with repeatable checks and clear evidence. It also helps compare results across iterations or enforce quality gates before a pull request or deployment.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions OpenCode.

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/darellchua2/opencode-config-template/eval-harness-skill
Any agent
npx skills add darellchua2/opencode-config-template --skill eval-harness-skill
Clone the repo
git clone --depth 1 https://github.com/darellchua2/opencode-config-template

Made for: OpenCode.

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-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/eval-harness-skill.svg)](https://agentmods.dev/skills/darellchua2/opencode-config-template/eval-harness-skill)
Your own site
<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/eval-harness-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/eval-harness-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,397 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found 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 $0.00024 $0.02397
Opus 5 $0.00012 $0.01198
Sonnet 5 $0.00005 $0.00479
Haiku 4.5 $0.00002 $0.00240

Measured 2d ago against content hash e21f0f540be1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

eval-harness-skill scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

9. **Iteration safety**: bounded-by-default (`Iterations: 25`); safety blocks `.env`, `node_modules/`, `rm -rf`, `git push --force`. See `autoresearch-core-skill/references/iteration-safety.md`.
opencode_app/.opencode/skills/eval-harness-skill/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I do

I provide a structured evaluation framework to assess code, skills, and implementations:

  1. Define Evaluation Criteria: Establish measurable quality benchmarks for code or skill output
  2. Execute Evaluations: Run automated checks against defined criteria with scoring
  3. Score Results: Generate quantitative scores with qualitative feedback
  4. Identify Gaps: Highlight areas below threshold with specific improvement suggestions
  5. Track Progress: Compare scores across iterations to measure improvement

When to use me

Use this skill when:

  • You want to evaluate the quality of generated code against best practices
  • You need to assess if a skill or agent is producing correct, high-quality output
  • You want to benchmark code quality before and after refactoring
  • You need to verify that implementation meets acceptance criteria
  • You want to establish quality gates for PRs or deployments

Trigger phrases:

  • "evaluate this code"
  • "run eval"
  • "score this implementation"
  • "quality check"
  • "benchmark against criteria"

Core Workflow

Step 1: Define Evaluation Criteria

Establish what "good" looks like for the evaluation target:

## Evaluation Criteria

### Correctness (0-10)
- Does the code do what it's supposed to do?
- Are edge cases handled?
- Are error paths covered?

### Code Quality (0-10)
- Follows language/framework conventions?
- Clean, readable, maintainable?
- Proper abstractions without over-engineering?

### Test Coverage (0-10)
- Are tests present and comprehensive?
- Do tests cover edge cases?
- Are tests maintainable?

### Performance (0-10)
- Efficient algorithms and data structures?
- No unnecessary computations?
- Proper caching where applicable?

### Security (0-10)
- Input validation?
- No injection vulnerabilities?
- Proper auth/authz?

Step 2: Configure Evaluation Scope

Define what to evaluate:

Scope Description Example
Single File Evaluate one file eval src/auth/login.ts
Module Evaluate a directory/module eval src/auth/
Skill Output Evaluate what a skill produces eval skill:tdd-workflow
PR Diff Evaluate changes in a PR eval pr:42
Acceptance Criteria Check against issue requirements eval issue:150

Read the full file on GitHub · 285 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 · 285 lines · 24 tokens per session scan C e21f0f540be1

Subscribe to this mod's changes

eval-harness-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,397 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

gate

Apply the acceptance decision that keeps optimization honest — always on the val split, by default requiring the improvement to exceed the significance bar (Δ > k·SE) so noise is not mistaken for progress. Use to inspect or reproduce a single accept/reject decision; the algorithms apply it internally every iteration.

skillberry-ai/cap-evolve · 62 tokens

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