37,058 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.
Skill Claude CodeCodex
Multi-round implementation-oriented discussion framework (SDD-inspired): refines fuzzy ideas via docs/discuss/NN-topic.md + DECISIONS.md; maintains method-agnostic "facts / reasoning / unverified" 3-way separation; for unsolved or frontier topics defines verifiable spikes (EXP-xx) with continue/stop criteria for later…
Agent Claude Code
Activates when user needs help with migrations - database migrations, code migrations, or framework upgrades. Triggers on "migrate", "upgrade framework", "move to new version", "database migration", "schema change", "breaking changes", or migration planning.
YourTechBud/coding-harness-config
Skill Claude Code
Create a phase-wise implementation plan.
Skill Claude CodeCodex
Generate structured PRD (Product Requirements Document) planning documents optimized for AI-assisted development. Creates discrete, single-conversation tasks with reasoning level estimates to optimize token usage and model selection. Use when users want to plan implementation work, break down features into tasks…
Skill Claude CodeCodex
Convert an implementation plan into an interactive HTML review artifact with engagement gates, then hand back an execution-ready brief. Use when the user says "visual planner", "plan room", "review this plan", "make this plan reviewable", or after writing a plan the user should approve before implementation.
littlestudent886/complex-dev-skills
Plugin Claude Code
Bundles 1 skill, 1 command, 3 agents · 139 tokens together
Full-cycle 7-phase feature development workflow with persistent file-based planning (taskplan.md, findings.md, progress.md).
Skill Claude Code
This skill should be used when the user asks to "build a dev team lineup", "create dev team lines", "dev team game plan", "dev team strategy", "optimize dev team line combinations", "set up dev team special teams", "plan dev team absences", "update dev team playbook", "update dev team roster", "update dev team power…
Skill Claude CodeCodex
Interview the user relentlessly about a technical design or architecture until every major decision is examined, justified, and stress-tested. Use when the user wants to pressure-test a system design, validate an architecture, compare options, or mentions "grill me" in a technical context.
Plugin Claude Code
Bundles 1 skill, 4 commands, 3 agents · 207 tokens together
Iterative sprint workflow with delegated implementation and independent verify-repair loops. Finalize each sprint only after every required gate passes.
Skill Claude Code
Run an adversarial debate with a cross-model reviewer (Codex or Antigravity/agy) to stress-test a draft, plan, research claim, or design decision. Use this whenever you need structured critique before finalizing decisions.
Skill Claude Code
Produce higher-quality code by breaking a feature into small, focused tasks the coding agent can nail one at a time. Works like an engineering team: feature → milestones (product deliverables) → 30-min tasks with specific files, acceptance criteria, and dependencies. Each task runs in a fresh context — narrow scope…
Skill Claude CodeCodex
A workflow for developing one requirement across multiple Git repositories, which are separate code projects. It creates a shared workspace containing the requirement, implementation plan, and selected project copies.
Plugin Claude Code
Bundles 4 skills, 4 commands, 5 hooks · 162 tokens together
Single-file planning workflow for complex tasks.
Skill Claude CodeCodex
Framework for managing project file context after retros/planning. Trigger after weekly retro + planning complete, after monthly retro + planning complete, or when context feels bloated. Also triggers with "context curation", "clean up project files", "archive old summaries", "what can we remove". Uses fractal…
Skill Claude Code
Plan a feature - gathers context, researches, interviews, identifies risks, outputs PRD. Use when: user says autoplan, /autoplan, or wants to plan a feature with the full research-interview-premortem workflow.
Agent Claude Code
StoryForge orchestrator. Reviews planning, identifies active work, prevents unstructured implementation, delegates to specialists, and updates delivery artifacts.
minhoyoo-iotrust/claude-plugin
Plugin Claude Code
Bundles 1 skill, 2 commands · 143 tokens together
GSD Utilities — autopilot for phases + milestone runner for sequential objective execution.
Plugin Claude Code
Bundles 10 skills · 332 tokens together
Personal development workflow skills: brainstorming, planning, TDD, debugging, verification, review, and Codex integration.
Skill Claude CodeCodex
Use when refining the scope, audience, reader takeaways, hooks, evidence plan, examples, code snippets, benchmark/performance claims, narrative angle, or outline for a blog post before drafting. Trigger for requests to clarify what a post should be about, who it is for, what readers should learn or believe, how to…
ErzatIam/claude-skill-init-project
Skill Claude CodeCodex
A project-context setup tool for creating lasting guidance about a new repository. It can cover software, research, data science, web, systems, and mobile projects.
juliakrivchikova/AccordAgents-desktop-app
Skill Claude CodeCodex
Facilitate a skeptical multi-member AccordAgents discussion that ends in one agreed resolution approved by every selected member. Use only when User explicitly wants an accord, multi-member consensus, cross-checking by named members, or a resolution approved by multiple agents. Do not use for an ordinary single-agent…
ParkerRex/tec-claude-code-agents
Cursor rule Cursor
Generate a comprehensive technical specification document for a new feature.
Agent Claude Code
Database architecture and design specialist. Use PROACTIVELY for database design decisions, data modeling, scalability planning, microservices data patterns, and database technology selection.
Skill Claude CodeCodex
A tool that turns a product owner's request into a YAML task file for a software manager. YAML is a human-readable format for structured settings and instructions.
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: