🔌

agentic-eval

🔌Plugin

dotknewt/agency

What it does

Patterns and techniques for evaluating and improving AI agent outputs — self-critique loops, evaluator-optimizer pipelines, rubric-based scoring, and iterative refinement.

🏪

Part of

dotknewt/agency

Installation

Add marketplace in Claude Code:

/plugin marketplace add dotknewt/agency

Step 2. Install plugin:

/plugin install agentic-eval@agency

AddedJul 3, 2026

View on GitHub Back to Plugins

More from this repository10

🔌

github-toolkit🔌Plugin

Scaffold GitHub repo metadata — issue templates and CI workflows. /github-scaffold picks the task; /create-issue-template and /scaffold-ci-workflow run the subtasks.

🔌

ludus-toolkit🔌Plugin

Ludus cyber-range toolkit — skills for CLI, range config, environment setup, and troubleshooting, plus a bundled MCP server for the Ludus API.

🔌

context-engineering🔌Plugin

Memory and context engineering concepts for LLMs — context window management, RAG patterns, prompt injection attacks (red-team), and defenses. Covers three angles: supporting development, exploiting, and defending.

🏪

dotknewt/agency🏪Marketplace

General LLM plans, tests, ideas and more

🎯

agent-development🎯Skill

Skill

🎯

command-development🎯Skill

Skill

🎯

hook-development🎯Skill

Skill

🔌

instruction-management🔌Plugin

Tools to maintain and improve project instruction files (AGENTS.md and legacy CLAUDE.md) — audit quality, capture session learnings, and keep project instructions current.

🔌

agent-doublecheck🔌Plugin

Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.

🔌

make-a-monorepo🔌Plugin

Scaffold a flat monorepo from scratch or audit an existing project against monorepo conventions — /make-a-monorepo init <name> or /make-a-monorepo audit [--fix].