plugin agents

kyopark2014/agent-plugins

Agent

Compare two outputs WITHOUT knowing which skill produced them.

kyopark2014/agent-plugins

Agent

Evaluate expectations against an execution transcript and outputs.

dashpot4/grok-plugin-for-claude

Agent

Proactively use when Claude Code should hand a substantial debugging, investigation, or implementation task to Grok Build CLI through the shared runtime.

ladiossoop5star/open_magi

Agent

Use this agent only when the Open Magi skill requests Balthasar deliberation. Balthasar evaluates architecture, boundaries, maintainability, long-term evolution, and design tradeoffs. Return a Magi report only; do not edit files or run commands.

ladiossoop5star/open_magi

Agent

Use this agent only when the Open Magi skill requests Casper deliberation. Casper evaluates root cause, failure paths, counterexamples, and verification gaps. Return a Magi report only; do not edit files or run commands.

ladiossoop5star/open_magi

Agent

Use this agent only when the Open Magi skill requests Melchior deliberation. Melchior evaluates feasibility, implementation risk, edge cases, cost, and verification strategy. Return a Magi report only; do not edit files or run commands.

martineserios/thebrana

Agent

Adversarially review a plan, architecture decision, or approach. Stress-test before commitment. Use when a significant decision is being made. Not for: data collection, project diagnostics.

martineserios/thebrana

Agent

Extract errata, learnings, and patterns from a work session. Use at end of implementation sessions or when notable learnings emerge. Not for: adversarial review, project scanning, knowledge recall.

martineserios/thebrana

Agent

Review PR diffs for code quality, bugs, and style issues. Auto-triggered on PR creation. Not for: implementation, file editing, test writing.

bzantium/meta-harness

Agent

Harness architecture designer that takes project analysis and pattern library input to produce a complete harness specification — agents, skills, hooks, rules, and data flow. Uses opus for deep reasoning about optimal agent team composition.

bzantium/meta-harness

Agent

Fast codebase analyst that explores project structure, tech stack, existing harness components, and development patterns. Separates current state (verified) from planned state (user-stated but unimplemented) — essential for accurate pattern selection. Spawned by create-harness and update-harness skills.

product-on-purpose/agent-skills-toolkit

Agent

Surveys a repository broadly and reports a structural map of its components and layout. Use when delegating broad read-only exploration - the bounded discovery role for answering what exists and how a repo is organized.

product-on-purpose/agent-skills-toolkit

Agent

Applies a specified set of file create and edit operations precisely, reading each target first. Use when delegating bounded file mutations - the role that carries out write and edit work an authoring skill has already decided on.

product-on-purpose/agent-skills-toolkit

Agent

Judges whether a skill triggers and behaves correctly by running it against its eval-set and grading the outputs. Use when delegating a behavioral evaluation - the opt-in LLM-judge role behind askit-evaluate's behavioral mode, distinct from the deterministic conformance core.

kai-wedekind/claude-code-grok-bridge

Agent

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Grok Build through the bridge runtime.

Poorgramer-Zack/copilot-cli-things

Agent

Conversation analysis for hookify — scan user messages for frustration signals, corrections, repeated issues, explicit "don't do X" requests. Detects unwanted tool behaviors and extracts regex patterns for hook rule generation. Triggered by hookify-create without arguments or explicit conversation analysis requests.

Poorgramer-Zack/copilot-cli-things

Agent

Agent creation: generate .agent.md files with optimized descriptions, system prompts, model/tool selection. Triggered by create agent, new agent, build agent, generate agent.

Poorgramer-Zack/copilot-cli-things

Agent

Plugin validation: check plugin structure, directory layout, component correctness (agents, skills, hooks, MCP). Triggered by validate plugin, check plugin, verify plugin, plugin structure.

Teknesyum/Teknesyum-Base

Agent

Relay auditor. Verifies a finished contract's acceptance criteria independently. Read-only pass/fail; give the contract path.

Teknesyum/Teknesyum-Base

Agent

Relay plan council member. Returns an independent plan proposal, writes nothing. Opens in pairs; one question goes to advisor.

Teknesyum/Teknesyum-Base

Agent

Prior-art worker. Studies repos that solved the same problem, writes docs/taramalar/. No code. Give 2-3 repo names.

leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Agent Claude Code

An agent for designing a multi-step workflow and the software agents that carry out each step. It combines workflow planning with decisions about sequence, responsibilities, tools, models, and communication.

leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Agent Claude Code

You are an adversarial design reviewer for Claude Code harness setup.

leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Agent Claude Code

A read-only reviewer that checks new screens, components, layouts, and interactions from the viewpoint of real users.