Planning

35,491 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

ralph-planner

1681

vavasilva/ralph-planner

Plugin Claude Code

Bundles 9 commands · 88 tokens together

Create structured execution plans in Ralph Wiggum format with auto-generated loop commands. Companion plugin for ralph-wiggum.

not rated 7 8mo ago A tokens not measured

northstar

1682

AI-Native-Systems/north-star-advisor

Plugin Claude Code

Bundles 6 commands · 74 tokens together

Strategic document generation for agentic applications. Generate 23 design documents following the North Star methodology: brand guidelines, architecture blueprints, competitive analysis, and more.

not rated 7 5mo ago A tokens not measured original MIT

task

1683

SpaiR/task-pipeline

Plugin Claude Code

Bundles 8 skills, 8 agents · 753 tokens together

Chat-first task workflow: grill the plan one question at a time, then capture the discussion at the depth you pick — to-task / to-plan / to-roadmap / to-spec, never a flag — into a Markdown artifact under .task/. No execution skill — any session told to implement the artifact follows its stamped Execution block to a…

not rated 7 changed 7d ago A tokens not measured original MIT

continuous-improvement

1685

naimkatiman/continuous-improvement

Skill Claude CodeCodex

Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute, verify, reflect, learn, iterate. On-demand or weekly analysis to save tokens. Supports multi-agent parallel analysis.

not rated 7 changed 7d ago A 47 tokens original MIT

tour-de-controle

1686

steve-magne/hookstack

Skill Claude Code

Orchestre une tâche complexe en trois temps avec Claude Code — PLANIFIER avec le modèle le plus puissant (Fable 5 / Opus), DÉLÉGUER l'exécution à des sous-agents calibrés lot par lot (Haiku / Sonnet / Opus selon la complexité) lancés en parallèle, puis VÉRIFIER chaque livrable de façon adversariale avec le modèle…

not rated 7 2d ago A SkillSpector: pass 159 tokens original MIT

architect

1687

reasonkit/reasonkit

Agent Claude Code

Senior software architect for ReasonKit system design, architecture decisions, trade-off analysis, ADRs, and technical governance.

not rated 7 1mo ago A 22 tokens copy · 100% Apache-2.0

convergo

1688

gomilesf/convergo

Plugin Claude Code

Bundles 11 skills · 486 tokens together

Disciplined software engineering for coding agents: plan, build, and review in bounded loops until an independent fresh reviewer signs off.

not rated 7 2mo ago A tokens not measured copy · 86% MIT

sdlc-workflow

1690

criznguyen/SDLC

Cursor rule Cursor

SDLC multi-role workflow; on idea/request trigger pipeline through deployment (sub-agent per phase).

not rated 7 5mo ago A 0 tokens

best-practice

1691

kelisiWu123/cursor-rules-wizard

Cursor rule Cursor

A set of working rules for handling complex or uncertain tasks in ordered steps. It also describes using current official documentation when code depends on a specific library or version.

not rated 7 1y ago A 823 tokens original MIT

badi

1692

fatihkan/badi

Plugin Claude Code

Bundles 81 skills, 86 commands, 30 agents, 7 hooks · 4,016 tokens together

Workflow management for Claude Code, Cursor, Gemini, Windsurf, AGENTS.md — 30 AI agents, 86 commands, 14 hooks, 63 opt-in skill categories. Built for Anthropic Claude Opus 4.7 and Sonnet 4.6.

not rated 7 6d ago A tokens not measured original MIT

orchestrate

1693

KirschBluteX/agent-orchestration-gateway

Skill Codex

Plan and supervise user-approved software initiatives through Codex native tasks and bounded native subagents. Use when the user explicitly asks Agent Orchestration Gateway to clarify work, split it into non-overlapping modules, dispatch module tasks, or run an AOG module task.

not rated 7 27d ago A 57 tokens original MIT

athena-protocol

1694

n0zer0d4y/athena-protocol

MCP server Claude CodeCodexCursor +2

AI tech lead for coding agents with validation and impact analysis. Runs locally from the @n0zer0d4y/athena-protocol npm package.

not rated 7 8mo ago A tokens not measured original MIT

leader

1695

baizhine999/leader-skills

Cursor rule Cursor

A set of rules that makes the AI act as a demanding workplace mentor using management ideas associated with large technology companies. It asks about goals, points out weak parts of a plan, and tracks next steps.

not rated 7 3mo ago A 0 tokens original MIT

cursor-rules

1696

trianglegrrl/promptonomicon

Cursor rule Cursor

This project uses the Promptonomicon framework for structured, documentation-driven development.

not rated 7 6mo ago A 334 tokens original MIT

codebase-intelligence

1697

bntvllnt/codebase-intelligence

Skill Claude CodeCodex

Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.

not rated 7 4d ago A 54 tokens original MIT

cursorrules

1698

ReSkin-Games/memorybank-plus

Cursor rule Cursor

A project rule for using a memory-bank/ folder as structured project memory. Before working, the agent must read specified context files and follow a staged workflow from task definition through building and archiving.

not rated 7 3mo ago A 413 tokens original MIT

coach

1699

mreider/agilemarkdown

Cursor rule Claude CodeCursor

Agile Markdown coach mode. AI is the dev pair, the human is the product manager. Hard rules refuse, working agreements nudge.

not rated 7 3mo ago D 2,469 tokens original MIT

speckit.tasks

1702

Corpusvision/agent-framework

Agent Claude Code

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

not rated 7 3mo ago A 18 tokens copy · 92% MIT

ralph-parallel

1703

kavanaghpatrick/ralph-parallel

Plugin Claude Code

Bundles 1 skill, 3 commands, 5 hooks · 94 tokens together

Parallel spec execution via Claude Code Agent Teams. Analyzes tasks from ralph-specum specs, partitions them into parallelizable groups, and dispatches them to Agent Teams teammates for simultaneous execution.

not rated 7 5mo ago A tokens not measured original MIT

speckit-driver

1704

jeffkit/jeff-marketplace

Plugin Claude Code

Bundles 1 skill, 8 agents · 181 tokens together

Autonomous Spec-Driven Development orchestrator for Claude Code. Enables Claude to intelligently drive the entire speckit workflow (constitution → specify → clarify → checklist → plan → tasks → analyze → implement) with minimal user intervention, using sub-agents for execution while the main agent acts as project…

not rated 7 1mo ago A tokens not measured

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: