37,150 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.
loschenbd/claude-agent-boilerplate
Skill Claude Code
Run a focused research pass on the codebase before any planning or implementation. Use when starting a complex change to gather facts about the affected area without making code changes. Produces a research.md doc with file references, current patterns, data flows, types, and collision points.
Cursor rule Claude CodeCursor
Execution policy single source of truth.
Skill Claude CodeCodex
A workflow for letting an AI agent carry out a large task toward a deadline with minimal interruption. It covers planning, design, execution, reflection, submission, and a log of questions the agent answers along the way.
wesleysimplicio/simplicio-loop
Plugin Claude CodeCursor
Bundles 12 skills · 1,005 tokens together
Super-plugin: /simplicio-loop is the unified public entrypoint for core + hardened loop, draining any queue of work end-to-end on any runtime — discover→implement→verify→merge→close→watch 24/7 — with evidence-gated completion, bounded iterations, token economy, and adversarial review.
Plugin Claude Code
Bundles 30 skills, 5 agents · 9,354 tokens together
A Claude Code plugin containing a full software-development workflow from product definition through implementation, testing, review, release, and learning. Its steps produce files that scripts can check or require a human approval.
Skill Claude Code
Create branded architecture, architecture delta, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, exploded axonometric, axonometric plan, Venn, pyramid/funnel…
Plugin Claude Code
Bundles 1 skill · 36 tokens together
Review an implementation plan against the current repository and its explicit dependencies, reporting evidence-backed blockers, required revisions, and optional improvements before work begins. Use when asked to review a plan or assess implementation readiness.
hrabanazviking/Mythic_Agent_Coder_CLI
Skill Claude Code
Activate Mythic Engineering mode — architecture-first, document-guided, AI-orchestrated development with six specialist roles. Invoke at the start of any session or task to orient the session, load the correct role, and enforce the full ME protocol including the five-layer model, coding laws, daily routine, and…
WojcikMM/spec-development-protocol
Plugin Claude Code
Bundles 6 skills, 10 agents · 277 tokens together
An AI-agentic framework for spec-driven engineering — structured, traceable, and ready for both greenfield and legacy web projects.
cam-douglas/agent-instructions
Skill Claude CodeCursor needs its repo
Runs the named product delivery lifecycle for new ideas, major changes, resumption, remediation, or closure only when the user explicitly invokes /launch-pipeline or requests this named workflow.
Skill Claude CodeCodex
A feature-design workflow that turns one feature into a single written specification. It records the goal, acceptance criteria, known facts, diagrams, affected code areas, and implementation order, then checks the document for required structure and consistency.
Skill Claude CodeCodex
Use when asked to triage, rank, prioritise or organise the open issues of a repo or of a whole org; when asked for a backlog board or "what should we work on next"; or when asked to refresh or sync an existing triage.
Skill Codex
Plan a huge chunk of work (more than one agent session can hold) as a shared local map of decision tickets, and resolve them one at a time until the way to the destination is clear.
Skill Claude CodeCodex
Decision framework for which agent-engineering mechanism, if any, fits a workflow problem: durable rule, skill, hard constraint, verification, eval, eval harness, feature map, observability, or increased automation/trust. Use whenever agents keep breaking something, a change isn't trusted yet, it's unclear if Claude…
Plugin Claude Code
Bundles 11 skills, 6 agents, 1 hook · 693 tokens together
Personal engineering standards for Claude Code: an evidence-first persona, feature planning, ADRs and a decision council, session wrap-ups, a code review agent, and default Git conventions for projects that state none.
Skill Claude Code
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
Exponentially-Platform/Rapidly-MCP
Plugin Claude Code
Bundles 4 skills, 1 MCP server · 349 tokens together
Test the idea before you build it. Rapidly turns an idea into a Lean Canvas, a measurable hypothesis and Pretotyping experiments, then returns a build prompt for the smallest test worth running.
Skill Claude Code
Create or refresh backlog/docs/architecture.yml, the curated source of the project summary page (architecture diagram, flows, highlights, tech stack, commands). Use when the user asks for a project summary, an architecture overview or diagram, or after structural changes to the codebase.
Skill Claude CodeCodex
Create, audit and clean up a repo's .scratch/ notes bundle (an Open Knowledge Format folder with its own index.md). Use whenever writing a note, plan, ticket draft, PR description, research or reference doc into .scratch/, and when asked to clean up, audit, sort, promote or reorganize .scratch.
Skill Claude CodeCodex
Implement an already-approved plan end to end, autonomously, with verified work and a short final summary. Use for "plan-auto-work", "implement the plan", "go build it", "do it autonomously", or "run the plan end to end". Accepts a plan path and optional scope hint, or the plan most recently approved in the…
Skill Claude Code
Generate a custom checklist for the current feature based on user requirements.
Skill Claude CodeCodex
A skill for building a single HTML page that people can read, review, or use to submit answers. HTML is the standard format used to display web pages, and the page can be published as a Claude artifact or opened locally.
Plugin Claude Code
Bundles 3 skills · 211 tokens together
Reduce coding-agent delivery cost by proving one complete path before scaling implementation.
Skill Claude CodeCodex
Put the points a user has to decide on a decision board, a private claude.ai page where they answer each point and Claude replies on its card, round after round. Use when there are four or more points for the user, or a point likely to need more than one round; offer it in one line first. Needs the Artifact tools…
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: