Planning agents

softaworks/agent-toolkit

Agent

Mermaid diagram specialist for creating flowcharts, sequence diagrams, ERDs, and architecture visualizations.

sdi2200262/agentic-project-management

Agent

Explores APM session archives to extract context for planning new sessions.

Wirasm/prp

Agent Claude Code

Finds repository documentation made false by a change and missing documentation required to use or operate a new public behavior. Use during PR review when user-facing behavior, configuration, commands, APIs, workflows, architecture maps, or contributor procedures change. Checks the documentation surfaces this…

Wirasm/prp

Agent Claude Code

Researches and validates GPUI usage patterns, APIs, and conventions. Always checks latest crate version, studies Zed editor and other GPUI projects for real-world patterns. Use when planning or researching GPUI features to ensure implementations match actual API surface and idioms.

carlvellotti/free-ai-courses

Agent Codex

Technical feasibility assessment, architecture review, and implementation complexity analysis. Use when evaluating technical specs, reviewing PRDs for engineering feasibility, estimating implementation effort, or getting feedback on system design decisions.

catlog22/Claude-Code-Workflow

Agent Claude Code

Pure execution agent for creating implementation plans based on provided requirements and control flags. This agent executes planning tasks without complex decision logic - it receives context and flags from command layer and produces actionable development plans. Examples: Context: Command provides requirements with…

catlog22/Claude-Code-Workflow

Agent Claude Code

Generic planning agent for lite-plan, collaborative-plan, and lite-fix workflows. Generates structured plan JSON based on provided template reference. Spawned by lite-plan, collaborative-plan, and lite-fix orchestrators. Core capabilities: Template-driven output (plan-overview-base-schema or plan-overview-fix-schema)…

catlog22/Claude-Code-Workflow

Agent Claude Code

Specialized agent for requirement-level roadmap planning with issue creation output. Decomposes requirements into convergent layers (progressive) or topologically-sorted task sequences (direct), each with testable convergence criteria, then creates issues and generates execution plan for team-planex. Core…

0-AI-UG/cate

Agent

Read-only planning specialist that turns gathered evidence into an implementation plan.

0-AI-UG/cate

Agent

Isolated implementation specialist for a clearly scoped coding task.

stacklok/toolhive

Agent Claude Code

Specialized in Kubernetes operator patterns, CRDs, controllers, and cloud-native architecture for ToolHive.

maxritter/pilot-shell

Agent

Changes review agent that verifies plan compliance, code quality, and goal achievement in a single pass. Returns structured JSON findings.

iannuttall/claude-agents

Agent

Use this agent when you need to create a comprehensive development task list from a Product Requirements Document (PRD). This agent analyzes PRDs and generates detailed, structured task lists covering all aspects of software development from initial setup through deployment and maintenance. Examples: Context: User…

lst97/claude-code-sub-agents

Agent

A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…

disler/pi-vs-claude-code

Agent

Plan critic — reviews, challenges, and validates implementation plans.

relaticle/relaticle

Agent Claude Code

You are a code-reading subagent dispatched by the business-review skill during Stage 1 (Understand), at the close of the stage. Your single job: build the main agent's business context of the touched code so its case planning is grounded in what the code actually does, what its tests claim, and why it reached its…

NeoLabHQ/context-engineering-kit

Agent

Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.

NeoLabHQ/context-engineering-kit

Agent

Use this agent at the END of an implementation phase to verify the phase's implementation against the task's acceptance criteria AND review code quality. Receives the task file path, the phase identifier and the artifact paths. Applies the phase's slice of the task's rubric/checklist, the built-in code quality…

NeoLabHQ/context-engineering-kit

Agent

Use this agent when breaking down architecture into implementation steps with success criteria, dependencies, and risk assessment, and reorganizing those steps for maximum parallel execution. Transforms architectural blueprints into executable, parallelized task sequences written as per-step sub-task files grouped…

yohey-w/multi-agent-shogun

Agent

Karo — task decomposition, assignment, and coordination.

yohey-w/multi-agent-shogun

Agent

Shogun — strategic oversight and command issuance.

cloudposse/atmos

Agent Claude Code

Use this agent when creating, updating, or refining Claude agents. Expert in agent architecture, frontmatter conventions, context management, and agent best practices. Invoke when: - User requests creation of a new agent - User asks to review, audit, or validate an existing agent - Existing agent needs updates or…

cloudposse/atmos

Agent Claude Code

Expert in Atmos flag handling patterns and command registry architecture. The pkg/flags/ infrastructure is FULLY IMPLEMENTED and robust. NEVER call viper.BindEnv() or viper.BindPFlag() directly - Forbidigo enforces this ban outside pkg/flags/. AUTO-INVOKE when ANY of these topics are mentioned: - flag, flags, flag…

cloudposse/atmos

Agent Claude Code

Expert in Atmos theme-aware TUI system. Use for developing new UI components, refactoring hard-coded colors to theme-aware patterns, or understanding theme architecture. Invoke when: - Creating new TUI/CLI output with colors, tables, or markdown - Refactoring hard-coded colors (lipgloss.Color("#...")) to theme-aware…