evalkit

v0.1.6

Offline golden-regression eval harness for Claude Code plugins: read golden *.jsonl cases (file-content or CLI-output assertions) and exit non-zero when a prompt edit or CLI contract regresses. The offline sibling of condukt's online verifier — runnable as a CI gate with no API key. Subscription-native (one bundled Rust binary).

Claude Code

By yukineko0 GitHub starsUpdated yesterday

Directory evidence

Runtimes: Claude Code
Parsed components: 0 skill or MCP entries
Source updated: Sep 23, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install evalkit for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install evalkit@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/yukineko/claude-harnesses

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is crates/evalkit/.

Plugin files

crates/evalkit/

└── .claude-plugin/plugin.json

Plugin manifests1

crates/evalkit/.claude-plugin/plugin.json

{
  "name": "evalkit",
  "version": "0.1.6",
  "description": "Offline golden-regression eval harness for Claude Code plugins: read golden *.jsonl cases (file-content or CLI-output assertions) and exit non-zero when a prompt edit or CLI contract regresses. The offline sibling of condukt's online verifier — runnable as a CI gate with no API key. Subscription-native (one bundled Rust binary).",
  "author": {
    "name": "yukineko"
  },
  "keywords": [
    "eval",
    "regression",
    "golden",
    "ci",
    "llmops",
    "rust"
  ]
}

Browse the “eval” tag →

ai-rag-engineering

by Matt Corbett

AI / RAG Engineering specialist team — agents (rag-architect-lead, retrieval-eval-analyst, ingestion-chunking-specialist, llm-serving-cost-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A RAG team for an ML engineer or AI product lead accountable for answer quality and serving cost — it fixes retrieval before generation, treats chunking as a retrieval decision, evals before it ships, and reads context-window and token economics. Inherits ravenclaude-core protocols.

Claude Code5 Skills

7Updated last week

evo

by Dan Lee

Self-evolving development pipeline — 3 lean agents across 6 phases with compound discovery loop, proactive research, and strict evaluation. No external dependencies.

CodexClaude Code30 Skills

5Updated last week

skill-authoring

by Aviv Sinai

Author and eval agent skills: write-skills (triggers, leading words, progressive disclosure, failure modes to prune) and eval-skills (blind golden-case runs in fresh subagents, judged against a bar, gap-driven edits). Vendored from dzhng/skills (MIT).

Codex2 Skills

2Updated 3 days ago

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[evalkit on Agent Plugins Marketplace](https://pluginsmp.com/plugins/evalkit)