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.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Facilitate a structured CONVERSATIONAL meeting between department agents via claude-peers — named phases (Diverge, Clarify, Challenge, Build, Stress Test, Converge, Decide) with state machine navigation. Agents push back on each other and build on each other's ideas. Minimum path: Diverge → Challenge → Build → Stress…
Plugin Claude Code
Bundles 9 skills · 300 tokens together
Track-aware strategic diagnosis and evidence review Skills for Guochuang projects.
Skill Claude CodeCodex
Structured adversarial analysis protocol. Quick single-agent modes (challenge, panel, pre-mortem, red team) plus a decision-review protocol where one agent proposes, one critiques, the proposer revises, and a binding/advisory judge panel decides ADOPT/REVISE/REJECT/ESCALATE.
Plugin Claude Code
Bundles 15 skills, 1 command, 1 hook · 1,759 tokens together
Interactive architecture advisor for multi-agent LLM systems. Guides through structured discovery, tension resolution, requirements stress testing, and architecture proposal. Generates C4 diagram, ADR, decision matrix, and NFR checklist. Supports post-artifact deepening on domain-specific topics.
Plugin Claude Code
Bundles 15 commands, 21 agents · 2,264 tokens together
An accountability mirror: a council of adversarial advisors that tells you what you need to know, not what you want to hear. A setup interview builds your dossier; then gauntlets for decisions, negotiation prep, voice-led writing and video, and PR trials — all aligned to your north star.
Skill Claude CodeCodex
Dia-GramV (DGV) — plan a system's architecture as a typed, linted, live diagram BEFORE writing code. Use when the user wants to design or map an app's architecture, see how modules / APIs / programs / databases / bridges connect, check a plan for incompatibilities, review an existing codebase's structure as a diagram…
Plugin Claude Code
Bundles 3 skills · 225 tokens together
Three agent skills that catch structural decisions as you make them, ask you to defend each one, and hand back a mastery map of your project: /ledger, /ledger-audit, /ledger-report.
Plugin Claude Code
Bundles 30 skills · 1,784 tokens together
briefbound-skills. Chinese-first Codex skill pack for intent alignment, dynamic routing, lightweight development, code review, UI design, and AI research workflows.
Skill Codex
Run a bounded SPEC → BUILD → REVIEW → REPAIR workflow until verified or blocked. Explicit invocation only: $specloop in Codex or /specloop in Claude Code.
Skill Codex
Evidence-first opportunity discovery — finds novel, defensible product/startup/project opportunities by researching before ideating, and mechanically rejects generic "AI-powered X" slop with deterministic validators. Use whenever the user asks for startup ideas, product or business opportunities, "what should I…
fattain-naime/engineering-docs
Plugin Claude Code
Bundles 22 skills, 4 agents, 1 hook, 1 MCP server · 1,592 tokens together
22 engineering documentation skills covering the complete software lifecycle: business concept, project planning, personas, specs, feasibility, UX flow, architecture, design system, API, database, ADR, access control, security, testing, implementation, deployment, SLO, operations, disaster recovery, and incident…
mrsunjc/TravelPilot-agent-skills
Skill Codex
A travel-planning guide for building practical itineraries for one city or several destinations. It arranges places by location and travel time, then accounts for opening hours, bookings, weather, transport, and budget.
Plugin Claude Code
Bundles 10 skills · 780 tokens together
productivity skills by claude plugin.
Skill Claude CodeCodex
Orchestrate the canonical task↔PR↔release flow end-to-end. Two modes — /dev-flow start scaffolds an OpenSpec change + branch + (optional) worktree + git hook ready for commits; /dev-flow ship validates the current branch + pushes + opens PR + monitors CI. Use whenever you start any non-trivial change in a…
Skill Claude CodeCodex
Use when a proposed skill, workflow, or decision needs adversarial review before it ships: convenes reviewers drawn from the agent-forge registry as hostile personas, adds a BUYER who states plainly whether they would pay, and forces every verdict to include the cheapest 48-hour test that could kill or validate the…
Skill Claude CodeCodex
THE primary entry point for all SDLC and PDLC work. Use when user mentions: "SDLC", "PDLC", "build this feature", "implement the spec", "run the SDLC loop", "go back to SDLC", "continue implementation", "product context", "document this feature", "launch prep", or any spec-related work (requirements, design, tasks…
Skill Claude CodeCodex
Use when an agent must decide whether to proceed autonomously, ask for clarification, request approval, or select an appropriate verification scope for a coding or documentation task.
bin1874/before-you-build-skill
Skill Claude CodeCodex
Use before building or changing a product, feature, SaaS, AI app, side project, or startup idea to run a short demand, distribution, and failure-pattern reality check. Not for ordinary coding tasks where the decision to build is already clear.
Skill Claude CodeCodex
Build one prioritized plan across a person's whole equity position - incentive stock options (ISOs), non-qualified stock options (NSOs), restricted stock units (RSUs), and held company stock - instead of answering one grant at a time. Use when someone has more than one grant type, asks "what should I do with my…
Skill Claude CodeCodex
Review a large question by staying inside one assigned slice, then support synthesis across several focused shard answers.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 70 tokens together
Deterministic, resumable multi-agent workflows that orchestrate Codex, Claude, Cursor, and Kimi agents — five MCP tools plus the workflow-authoring skill.
Cursor rule Cursor
This project uses md-feedback for structured human review of implementation plans.
Skill Codex
Stress-test a plan or design from three angles: drill down into branches, scan laterally for missing alternatives, and zoom out to expose systemic gaps until ambiguity becomes explicit decisions. Use when the user wants rigorous plan review, design pressure-testing, or deep decision clarification. Question-asking…
Skill Claude Code
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
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: