claude

agentdev

Create, implement, and review Claude Code agents and commands with multi-model validation, LLM performance tracking, and session-based artifact isolation. v1.5.2: Updated for claudish v4.5.1 (--agent flag removed).

288 on GitHubby Jack Rudenkov1.5.2MITupdated 7 months agodevelopment
/

Plugin agentdev from marketplace mag-claude-plugins in MadAppGang/claude-code. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (5)

  • debug-mode

    Enable, disable, and manage debug mode for agentdev sessions. Records all tool invocations, skill activations, hook triggers, and agent delegations to JSONL. Use when debugging agent behavior, optimizing workflows, or analyzing session performance.

  • patterns

    Common agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for Tasks integration, quality checks, and external model invocation via claudish CLI.

  • schemas

    YAML frontmatter schemas for Claude Code agents and commands. Use when creating or validating agent/command files.

  • xml-standards

    XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.

  • yaml-agent-format

    YAML format for Claude Code agent definitions as alternative to markdown. Use when creating agents with YAML, converting markdown agents to YAML, or validating YAML agent schemas. Trigger keywords - "YAML agent", "agent YAML", "YAML format", "agent schema", "YAML definition", "convert to YAML".

Slash commands (5)

  • /agentdev:debug-disable

    Disable debug mode for agentdev sessions. Stops recording tool invocations and agent delegations.

  • /agentdev:debug-enable

    Enable debug mode for agentdev sessions. Records tool invocations, skill activations, and agent delegations to JSONL files.

  • /agentdev:debug-status

    Check current debug mode status for agentdev sessions. Shows if enabled/disabled, debug level, and recent session files.

  • /agentdev:develop

    Full-cycle agent/command development with multi-model validation and performance tracking. Orchestrates design (architect) -> plan review -> implementation (developer) -> quality review (reviewer) -> iteration. Tracks model performance to ai-docs/llm-performance.json for shortlist optimization. Enab

  • /agentdev:help

    Show comprehensive help for the Agent Development Plugin - lists agents, commands, skills, and usage examples

Subagents (3)

  • architect

    Expert agent designer for Claude Code agents and commands. Use when planning new agents, improving existing agents, or designing slash commands. Examples: (1) "Design a GraphQL reviewer agent" - creates comprehensive design plan. (2) "Plan improvements to backend-developer" - analyzes and designs en

  • developer

    Expert agent implementer for Claude Code agents and commands. Use when you have an approved design plan and need to create the actual agent/command file. Examples: (1) "Implement agent from ai-docs/agent-design-graphql-reviewer.md" - creates the agent file. (2) "Create the /deploy command from desig

  • reviewer

    Expert agent quality reviewer for Claude Code agents and commands. Use when validating implemented agents for quality, completeness, and standards compliance. Examples: (1) "Review .claude/agents/graphql-reviewer.md" - validates YAML, XML, completeness. (2) "Check plugins/bun/agents/backend-develope

View source on GitHub

More from MadAppGang/claude-code

All 9 plugins →

dev

claude

Universal development assistant with real skill discovery. v1.31.3: Statusline extracted to standalone plugin. 46 skills.

47 skills · 15 commands · 16 agents · 1 MCP server

288

seo

claude

Highly autonomous SEO toolkit (~80% autonomy) with AUTO GATEs, self-correction loops, and multi-model validation. v1.6.2: Updated for claudish v4.5.1 (--agent flag removed). Features E-E-A-T self-assessment, keyword research, content optimization, technical audits.

10 skills · 9 commands · 5 agents · 2 MCP servers · hooks

288

Deep code investigation with claudemem. v3.2.2: Updated for claudish v4.5.1 (--agent flag removed). v3.0.0: ENRICHMENT MODE.

13 skills · 3 commands · 1 agent · 1 MCP server · hooks

288

Multi-model collaboration, orchestration, and workflow patterns. v2.4.1: Updated for claudish v4.5.1 (--agent flag removed). Hook logging simplified. 15 E2E tests.

15 skills · 1 command · hooks

288

conductor

claude

Context-Driven Development workflow inspired by Gemini Conductor. v2.1.0: Added explicit name: fields to commands for prefix-free invocation. Full-featured implementation with TDD workflow, Phase Completion Protocol, Git Notes audit trail, and comprehensive styleguides.

6 skills · 6 commands

288

Professional video editing toolkit with FFmpeg operations, Whisper transcription, and Apple Final Cut Pro project generation. v1.1.0: Added explicit name: fields to commands for prefix-free invocation. Features intelligent video analysis, automated transcription with timing sync, FCPXML timeline creation.

3 skills · 3 commands · 3 agents

288

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Maintain agentdev?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins