plan
2065iberant/iberant-ai-starter-kit
Command Claude Code
Explore the codebase, then produce a detailed implementation plan (no code yet).
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.
iberant/iberant-ai-starter-kit
Command Claude Code
Explore the codebase, then produce a detailed implementation plan (no code yet).
meerita/monorepo-nextjs-golang-rust-python-ai-rules
Skill Claude Code
Author an executable, phased implementation plan under docs/plans — first gather real context from the repo and docs, debate the ambiguities, trade-offs and open decisions with the human, and only after explicit human confirmation write the plan. Produces Master Plans (a directory with a bootstrap entry point, master…
Skill Claude CodeCodex
Translate PRDs for engineering audiences. Use when writing technical specifications, defining API contracts, or bridging product requirements to engineering execution.
jackreacher80/product-manager-skill
Skill Claude CodeCodex
Acts as a junior/associate product manager producing professional PM deliverables. Use whenever users ask to write PRDs, feature specs, user stories, acceptance criteria, competitive analyses, feature prioritization (RICE, MoSCoW, Kano), sprint planning, backlog grooming, release notes, go-to-market briefs…
dungnotnull/Diplomacy-Negotiation-Advisor-agent-skill
Skill Claude CodeCodex
A comprehensive skill for negotiation and diplomatic strategy across interpersonal, business, and international contexts. Use this skill whenever the user needs negotiation analysis, BATNA calculation, game-theoretic reasoning, cross-cultural strategy, diplomatic communication, conflict resolution, or any form of…
Skill Claude CodeCodex
A project-starting workflow that turns a broad software idea into written product and technical context. It can also document the first small end-to-end slice of a product, meaning one useful path that works from beginning to end.
Skill Claude CodeCodex
Extracts exact, behaviour-first specifications from an existing codebase. Defines domain concepts, use cases, and business rules with precision — zero implementation details. Use when reverse-engineering a legacy project into precise specs or preparing an AI-friendly spec set for a rewrite.
Command Claude Code needs its repo
Add a new feature to this Quiver app: $ARGUMENTS.
Skill Claude CodeCodex
Guidance for choosing the smallest suitable development process based on a task's risk and complexity.
Skill Codex
Map the minimal evidence-backed implementation, coupling, test, and repository-constraint surface for a non-trivial code task by delegating one fresh repository scout instructed to remain read-only to gpt-5.6-terra. Use when explicitly invoked with $code-scout, or before implementing, debugging, reviewing, or planning…
Skill Claude CodeCodex
Run one YASDEF ASDLC worker planning iteration for an assigned step. Use when yasdef or the user asks to create, update, validate, or finish a step plan artifact under .asdlcworker/stepplans after design is complete.
Skill Codex
Protects the parts of a user's thinking they want to keep human. Use for product direction, original interaction ideas, taste, judgement, synthesis, human feel, exploration, personal philosophy, first-run boundary setup, Human Model corrections, or /human-model commands. Do not interfere with routine execution…
juanlamadrid20/databricks-context-engineering-cookbook
Command Claude Code
🚨 MANDATORY: Feature specification is required for PRP generation.
Skill Claude CodeCodex
Conduct structured requirements-gathering interviews before creating implementation plans. Use this skill when planning non-trivial tasks involving multi-file changes, new features, refactors, or architectural decisions. Auto-skip for clearly scoped, unambiguous single-file changes.
1139030773-cmd/agent-workflow-system
Skill Claude Code
A Chinese-language guide for beginners who have an unclear goal or do not know how to break a task into steps.
Plugin Claude Code
Bundles 22 commands, 3 agents, 3 hooks · 405 tokens together
Autonomous SWE pipeline for Claude Code, Cursor, and compatible hosts — Hypervisor policy, structured phases, human gates, and 135+ specialist agents.
Command Claude Code
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
Command Claude Code
Prepare a plan that implements the PRD or subcomponent that is informed by recent research.
Skill Claude CodeCodex
Three-model build pipeline routing design, spec/verification, and implementation to cost-appropriate models with hard gates (Fable design, Opus spec+verify, Sonnet build). Trigger on 'tiered build', 'run my pipeline', 'design-then-build', /tiered-build, or handing over a design doc to take to the next phase.
Plugin Claude Code
Bundles 8 skills, 10 commands, 4 agents, 4 hooks · 790 tokens together
Get Shit Right — PRD-first, human-in-the-loop workflow for building production apps.
Command Claude Code
Interview the user, then generate or update all Ralph Loop control files (PROMPT.md, AGENT.md, specs/.md, fixplan.md) with diff-preview before writing. Never makes the user hand-write markdown.
dungnotnull/ecological-cemetery-planning-agent-skill
Skill Claude CodeCodex
Comprehensive ecological cemetery planning and development advisor. Use this skill for ANY task involving ecological burial grounds, green cemetery planning, landscape design for burial sites, environmental impact assessment of cemeteries, native planting for memorial landscapes, sustainable cemetery maintenance…
Agent Claude Code
Extracts operator direction efficiently using structured discovery — gap-fill synthesis, option-led questions, progressive disclosure. Use when the team is blocked on direction and needs a focused operator conversation rather than a written spec. Operates in two phases: (1) produce a direction brief for the operator…
Plugin Claude Code
Bundles 12 skills, 3 agents, 2 hooks · 348 tokens together
Professional engineering discipline with user-owned workflows and model-specific corrections.
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: