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.
Skill Claude CodeCodex
Use when a plausible mainline or strategic direction meets a concrete carrier/proxy, concentrated scarce-resource exposure, or continue/commit/hold/exit/switch decision under path volatility, costs, delays, fragility, or counter-forces; not for method-reference evidence review.
Plugin Claude Code
Bundles 6 skills, 8 commands, 8 agents, 3 hooks · 483 tokens together
Spec-Driven Development: specifications compiled into executable, verifiable behavior.
Skill Claude Code
Use this skill when the user wants AI work they can trust without watching every step: the AI fixes direction first (rules, assumptions, failing checks sealed in git), builds to green, then proves the result with evidence for the human to review. Trigger when a repo has .add/, the user says "add", "/add", "start a…
Command Claude Code
Thin wrapper (GETSITREP-10) over getsitrep plan-update — the CLI owns the table lookup, row insertion, and commit. This file's only remaining job is the one step no CLI can do on its own: interpreting the free-form request in $ARGUMENTS into the structured JSON the CLI expects.
bjorndavidhansen/google-ads-mcp-server
Cursor rule Cursor
C:\Users\bjorn.hansen\Documents\google-ads-mcp\ ├── PROJECT-MASTER.md # Overarching project plan (constant) ├── project-planning\ │ ├── implementation-plans\ # Specific implementation plans │ │ ├── SAGE-Plan.md # Structured Approach for Google-ads Enhancement │ │ ├── PRISM-Plan.md # Powerful Rendering & Interactive…
Cursor rule Cursor
Cursor rule "mcp-agent-rules" from emmahyde/thinking-patterns, covering 1.0 core mandate, 2.0 guiding principles, 2.1 think before acting, 2.2 iterate and refine and 2.3 maintain context.
Skill Claude CodeCodex
Design thinking with forcing questions, anti-sycophancy, adversarial review. Reads past decisions and mistakes to avoid re-debating and front-load failure patterns.
Skill Claude CodeCodex
Create the minimum execution contract needed to implement accepted product intent.
EvilFreelancer/cursor-vibe-prompts
Cursor rule Cursor
Workflow rules for documentation, bug fixes, and new features.
Skill Claude Code
Render an interactive HTML board for the user to pick among multiple comparable options side-by-side at once — engineering trade-offs, copy audits, action-item triage, architecture decisions, policy calls. Returns the picks (and optional hold/note flags) as a JSON file the agent can apply.
Command Claude Code
Scaffold a new OpenSpec change and validate strictly.
Plugin Claude Code
Bundles 44 skills, 71 commands, 18 agents, 3 hooks · 2,267 tokens together
Plan-Build-Run — Structured development workflow for Claude Code. Solves context rot through disciplined subagent delegation, structured planning, atomic execution, and goal-backward verification.
Skill Claude CodeCodex
Top-level orchestration skill for Hermes Agent startup workflows. Use it to route ideas between validation, PRD, architecture, build, UX, growth, and launch skills; summarize context between stages; prevent context pollution; and recommend the next workflow without doing every specialist task directly.
cis2042/product-design-harness
Skill Claude CodeCodex
Use when a product direction, feature, workflow, experiment, launch, feedback signal, automation, or scale decision needs judgment before execution or the next iteration.
Skill Claude CodeCodex
Produce a single-file HTML swimlane brief that walks a system, module, or upcoming feature past a non-specialist reader, with provenance badges that separate what is measured from what is merely intended. Use this whenever someone needs to explain how something works to people outside the team — a flow diagram, an…
Skill Claude CodeCodex
Start, resume, inspect, or continue SLDD spec-driven development workflows, including /sldd slash-style commands, gated intent/design/test/implementation steps, structured journals, and workflow kind routing.
Skill Claude Code
Create Spec-Driven Development changes (OpenSpec-style) — multi-project openspec, understanding gate, assigned tasks before coding.
chefjefff/mckinsey-problem-solving
Skill Claude CodeCodex
McKinsey's 7-step Bulletproof Problem Solving framework from Conn & McLean. Covers problem definition (SMART + porpoising), disaggregation (MECE logic trees -- component, deductive, inductive, hypothesis, decision), prioritization (impact/ability matrix), workplanning (hypothesis-driven, knock-out order, one-day…
SuperChason/ontology-driven-ai-data-management-skills
Skill Codex
A method for deciding whether an ontology is suitable for an enterprise AI scenario and testing that choice with a small end-to-end sample. An ontology is a structured model of concepts, rules, and relationships.
Plugin Cursor
Bundles 14 skills, 13 agents, 1 MCP server · 1,174 tokens together
Specky — Spec-Driven Development plugin (58 MCP tools, 13 agents, 10-phase pipeline).
Cursor rule Cursor
Cursor rule "cursor" from nitingupta220/riperflow, covering riperflow σ and ω₁=🔍r→ℙ(ω₁)→research.
Skill Claude CodeCodex
High-value project analyst + impl strategist. Any project type (code, docs, research, strategy, workflow, creative, ops, non-tech, hybrid). Inspect deep, infer top-value objective from signals, find top 3 gaps, propose 3 macro-steps user picks (none/one/two/all). After pick, plan + implement autonomously. Triggers…
chrisallenlane/claude-swe-workflows
Plugin Claude Code
Bundles 17 skills, 40 agents · 2,687 tokens together
Software engineering workflows with skills for planning, implementation, quality review, and structured thinking, plus a suite of specialist agents.
Skill Claude CodeCodex needs its repo
Manages the full epic planning lifecycle using Prompt-Driven Development (PDD). Use for idea honing, requirements extraction, requirements planning, research, architectural design, adversarial review, story breakdown, feature planning, roadmap planning, and epic decomposition into stories. Also triggers on "plan an…
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: