Skip to main content

opencode-plugin-eval

Three-layer quality evaluation framework for OpenCode skills and plugins.

Disclaimer: This plugin is not built by the OpenCode team and is not affiliated with OpenCode in any way. It is an independent community project.

Installation

From GitHub (recommended)

pip install git+https://github.com/jarbcs1-prog/opencode-plugin-eval.git

From source

git clone https://github.com/jarbcs1-prog/opencode-plugin-eval.git
cd opencode-plugin-eval
pip install -e .

Development install with LLM judge support

pip install -e "git+https://github.com/jarbcs1-prog/opencode-plugin-eval.git#egg=opencode-plugin-eval[llm]"

Or from source:

git clone https://github.com/jarbcs1-prog/opencode-plugin-eval.git
cd opencode-plugin-eval
pip install -e ".[llm]"

Quick Start

# Evaluate a skill (static only, instant)
opencode-plugin-eval score path/to/skill --depth quick

# Evaluate with LLM judge (~30s)
opencode-plugin-eval score path/to/skill --depth standard

# Full certification (all layers, ~2-5 min)
opencode-plugin-eval certify path/to/skill

# Head-to-head comparison
opencode-plugin-eval compare path/to/skill-a path/to/skill-b

# Initialize corpus for Elo ranking
opencode-plugin-eval init path/to/plugins

OpenCode Commands

After installing, use these commands directly in OpenCode:

CLI OpenCode Description
opencode-plugin-eval score /eval Score a plugin or skill
opencode-plugin-eval certify /certify Full certification with badge
opencode-plugin-eval compare /compare Head-to-head comparison
opencode-plugin-eval init Build corpus for Elo ranking

Layers

  1. Static Analysis — Structural checks, anti-pattern detection. Instant, free.
  2. LLM Judge — Semantic evaluation (triggering, orchestration, output, scope). ~30s, 4 calls.
  3. Monte Carlo — Statistical reliability via 50–100 simulated runs. ~2–5 min.

Documentation

See docs/opencode-plugin-eval.md for the full reference: layers, dimensions, scoring formula, anti-patterns, statistical methods and project structure.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

opencode_plugin_eval-0.1.3.tar.gz (50.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

opencode_plugin_eval-0.1.3-py3-none-any.whl (31.5 kB view details)

Uploaded Python 3

File details

Details for the file opencode_plugin_eval-0.1.3.tar.gz.

File metadata

  • Download URL: opencode_plugin_eval-0.1.3.tar.gz
  • Upload date:
  • Size: 50.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for opencode_plugin_eval-0.1.3.tar.gz
Algorithm Hash digest
SHA256 f480af03312d1ea7fecfe778412e3fdf4d523cef920070c6739790d38cc5e517
MD5 4a27c0c7b80115e751f36a08b0a62e13
BLAKE2b-256 0b009580323c5fbb1437db7c712045e025388d1c6004f7a49b99d02554707ecc

See more details on using hashes here.

Provenance

The following attestation bundles were made for opencode_plugin_eval-0.1.3.tar.gz:

Publisher: publish.yml on jarbcs1-prog/opencode-plugin-eval

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file opencode_plugin_eval-0.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for opencode_plugin_eval-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 07533e0521c6dab566e386a3db68cce76709395fbab3d2d4dfac46116dc34805
MD5 b12721c0255a892f21da0ed744830bcc
BLAKE2b-256 003113d751c01e8af1b8afe966a6ba55a9876f12db3643f2ee4a9e4f74a66c42

See more details on using hashes here.

Provenance

The following attestation bundles were made for opencode_plugin_eval-0.1.3-py3-none-any.whl:

Publisher: publish.yml on jarbcs1-prog/opencode-plugin-eval

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page