Planning

37,021 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.

mapify-mcp-server

961

xmindltd/mapify-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server "mapify-mcp-server" as configured in xmindltd/mapify-mcp-server. Runs locally from the @xmindltd/mapify-mcp-server npm package.

not rated 27 1y ago A tokens not measured original MIT

migration-planner

962

codebygarv/Ai-skills

Skill Claude CodeCodex

Plans a safe, incremental migration (framework, database, service, or platform) with rollback points and a dual-running strategy. Use when replacing something that's already in production and can't just be swapped in one step.

not rated 27 2mo ago A 46 tokens original MIT

pipeline

963

Magerko/claude-code-skills

Skill Claude Code

A staged development process that takes a project from context and idea through planning, risk checks, design contracts, implementation, audit, feedback and release. Each stage produces files in docs/pipeline/ that serve as the project record.

not rated 27 +1 2mo ago A SkillSpector: warn 98 tokens original MIT

dual-brain

964

sleeplesshan/dual-brain

Skill Claude CodeCodex

Dual-brain review for ambiguous designs, risky refactors, and recurring project decisions. Combine macro-level design review with micro-level code verification and relevant project memory.

not rated 27 +6 changed 16d ago A 36 tokens original MIT

prd-writer

965

Panix22/prd-writer-skill

Skill Claude CodeCodex

A guided process for discovering a product idea and writing a PRD, or product requirements document. A PRD records what should be built, for whom, and how it should work.

not rated 27 +2 4mo ago A 119 tokens original MIT

sdd-prd

966

felipefontoura/spec-driven-development-book

Skill Claude Code

Core cognitive SDD skill for creating or updating requirements.md from an approved idea, plan, or feature request. Use when the conversation calls for defining WHAT and WHY: user stories, acceptance criteria, EARS functional requirements, NFRs, and boundaries, even without an explicit command. Do not use for technical…

not rated 27 +1 7d ago A 71 tokens

decisions

967

ctxpipe-ai/ctxpipe

Skill Claude CodeCodex

Write a knowledge file for each decision file (ADR) of the source repository, with its status, date, scope, and what it replaces. Use after the root steps, once for each repository.

not rated 27 today A 43 tokens original MIT

batch

968

terrense/LilBot-agent

Skill Claude Code

Break a large request into a tracked batch of smaller tasks.

not rated 26 2d ago A 14 tokens

BlueprintOS/analysis-to-delivery

Skill Claude Code needs its repo

A nine-stage workflow for taking a software project from analysis and requirements through design, testing, quality review, and handover.

not rated 26 4mo ago A 66 tokens original MIT

goal-advance

970

adeptify/GoalBoard

Skill Codex

Use GoalBoard in the current Runtime conversation to connect a user-selected project, clarify and plan Goal Trees with relevant professional methods, establish evidence-based dependencies, execute available work, and keep decisions and evidence in one shared truth source. Use only when the user explicitly asks to use…

not rated 26 changed 1mo ago A SkillSpector: pass 74 tokens original MIT

jdm4pku/RE-Skills

Skill Claude CodeCodex

Orchestrate requirements engineering for agile projects using just-in-time elaboration and continuous validation. Use when adopting agile and need to adapt RE practices without losing rigor.

not rated 26 6mo ago A 39 tokens

sdlc-skills

972

arozumenko/sdlc-skills

Plugin Claude Code

Bundles 60 skills · 5,288 tokens together

A bundled software delivery lifecycle toolkit for Claude Code: role-based agents (BA, Tech Lead, PM, Python dev, JS dev, QA, Personal Assistant) and composable skills (bug-fix workflow, feature planning, feature implementation, project seeding, code review, TDD, and more). Use when orchestrating an AI development team.

not rated 26 +1 yesterday A tokens not measured original MIT

work-loop

973

eugenelim/agent-ready-repo

Skill Claude Code

Use when implementing or resuming a non-trivial repository change: a feature, a fix whose cause is established (use bug-fix first to diagnose a defect whose cause is not), refactor, migration, framework or dependency upgrade, schema or API change, performance work, infrastructure or build-system change, reversion, or…

not rated 26 +1 changed today A SkillSpector: warn 180 tokens original Apache-2.0

executing-hard-tasks

974

wsbm393/Fable-Skill

Skill Claude CodeCodex

Use when a task spans multiple steps, files, or unknowns — before planning the order of work, whenever about to report completion or success in any wording, and when picking the next action after a result, failure, or surprise. Also under deadline pressure, or when resuming work built on questionable foundations.

not rated 26 3mo ago A 68 tokens original MIT

step-by-step

975

KarelTestSpecial/real-agent-setup

Skill Claude CodeCodex

Patient, one-step-at-a-time guidance — exactly one step per message, always starting at step 1, waiting for the user's "done" or "next" before continuing, and pausing in front of anything that changes something. Use this when the user says "step by step", "walk me through it", "slow down", "one step at a time"…

not rated 26 today A 124 tokens original MIT

mm-web-bridge

977

mworldorg/markdown-memory

Skill Claude CodeCodex

An idea partner for a developer who discusses plans, checks current information online, and prepares self-contained tasks for Claude Code running in Windows PowerShell. It is designed for Russian-language work and mentions Telegram bots, Python, SQLite, and Railway deployment.

not rated 25 9d ago A SkillSpector: warn 154 tokens original MIT

flow-dev

978

aitanjp/flow-x

Skill Claude CodeCodex

A task-focused development assistant that completes one task from TASK.md using TDD, a method of writing a failing test, making it pass, and then improving the code.

not rated 25 4mo ago A 131 tokens

product-playbook

979

Kaminoikari/product-playbook

Plugin Claude Code

Bundles 18 skills, 2 agents, 3 hooks · 998 tokens together

MUST use when the user wants to plan, strategize, validate, or scope a product or feature. Composable product-thinking lenses (JTBD, PR-FAQ, positioning, pre-mortem, RICE, North Star, MVP, GTM, and more) that snap to the outcome and blend when the situation needs it, from raw idea to dev handoff.

not rated 25 1mo ago A tokens not measured original MIT

aura-frog

980

nguyenthienthanh/aura-frog

Plugin Claude Code

Bundles 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers · 2,925 tokens together

Planning-first LLM OS for software engineering. Hierarchical planning (T0-T4) survives session reset · forensic reasoning traces · L1+L2 conflict detection · self-healing safety gates · per-agent MCP security · durable project-context snapshots · cross-tool porter (Copilot/Codex/Cursor) · CLI dashboard. 15 agents…

not rated 25 changed 5d ago A tokens not measured original MIT

josemerca/mercadona-user-story-toolkit

Plugin Claude Code

Bundles 8 skills, 11 commands · 1,607 tokens together

Pipeline PRD/GSD → JTBDs → User Stories validadas y priorizadas. 7 skills + 11 comandos. Source-agnostic (acepta PRD pegado, fichero o URL — sin acoplamiento a Notion/Jira). Incluye /from-gsd para integrar artefactos de Get Shit Done y bridge/gsd-bridge.py para mantener consistencia entre planning y ejecución.

not rated 25 5mo ago A tokens not measured original MIT

loopgen

982

pro-vi/loopgen

Skill Codex

Compose a repo-specific, /goal-ready loop prompt from a primitive vocabulary — loopgen writes the weather, not just the target. Classifies a task to its nearest archetype (frontier / goal / story / greenfield), composes the prompt from primitive values — defaulting to the archetype, diverging where the task demands …

not rated 25 changed 1mo ago A 138 tokens

aliwei-skill

983

da-meng-mao/aliwei.skill

Skill Claude CodeCodex

A task-execution procedure for an AI agent, written in Chinese, that emphasizes understanding the goal, confirming the task, completing all steps, checking the result, and delivering it. It also requires the agent to reveal assumptions and constraints.

not rated 25 4mo ago A 74 tokens original MIT

codex-loop

984

aronprins/codex-loop

Skill Codex

Autonomous Codex workflow that implements codex-loop/prd.json with one fresh Codex subagent per story. Use when the user asks to run Codex Loop, run the loop, work through a PRD, process prd.json, implement all stories, iterate through user stories autonomously, or complete a feature broken into PRD stories.…

not rated 25 4mo ago A 133 tokens original MIT

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: