35,517 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
Two related workflows for a locally-cloned codebase, in one skill. Documentation mode produces a single, comprehensive, verifiable architecture document primarily by reading files on disk (local-first) — use it whenever the user wants to understand, map, document, research, or onboard onto a codebase ("research this…
Skill Claude CodeCodex
Evidence-bound Build Necessity / Minimum Necessary Change specialist for MC-GPT. Use before implementation, dependency selection, architecture expansion, refactoring, installer creation, database/entity creation, agent/RAG creation, or when reviewing complexity and duplication. Select the first sufficient no-change…
Skill Codex
Use Forum route preview, context preflight, runtime inspection, and prose contracts before continuing, decomposing, or dispatching agent work. Do not use for automatic execution or per-specialist wrappers.
Command Claude Code
INTERIM. This command's own inlined text below is authoritative for cleanlanguage and is reviewed through this repository's PR gate. It adapts the fleet /flow standard, whose co-owned reference copy is /opt/inbox/FLOW.md (reconciled with labinfra's docs/operating-model.md); that reference is a cross-check, not an…
Skill Claude Code
Convert an approved design/implementation plan (from brainstorming/writing-plans) into reviewed Backlog.md tasks with acceptance criteria, milestones and dependencies. Use after a design is approved, when the user asks to decompose work into tasks, or before starting planned work in this project.
MCP server Claude CodeCodexCursor +2
Multi-city flight routing intelligence — plan RTW trips, validate alliances, get carrier picks. Runs locally from the airtreks-mcp npm package.
Instructions file GitHub Copilot
Instructions for flight505/MCP_DinCoder, covering dincoder spec-driven development, mcp tools available, project initialization, specification phase and planning phase.
MCP server Claude CodeCodexCursor +2
Schedule agent work and report write-once outcomes via CueAPI from any MCP host. Runs locally from the @cueapi/mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Analyse activities, build training plans and sync structured workouts to your sports watch. Remote server at www.tredict.com.
ottotheagent/openclaw-otto-travel
MCP server Claude CodeCodexCursor +2
Plan, book, and manage business travel. Remote server at api.ottotheagent.com.
MCP server Claude CodeCodexCursor +2
The Tenth Man Protocol — structured contrarian analysis for decision-makers via MCP. Runs locally from the kontra-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Strategic task prioritization and agent orchestration for multi-project operators. Runs locally from the quarterback Python package.
MCP server Claude CodeCodexCursor +2
Score your specs before feeding them to an LLM. MCP server with radar chart visualization. Runs locally from the spec-score-mcp npm package.
MCP server Claude CodeCodexCursor +2
Local-first Ownly evidence and repeatable Planner visits with preview-before-commit writes. Runs locally from the @ownly-app/mcp npm package. Needs 3 environment variables to run.
Skill Codex
Use Codexa selectively for ambiguous, cross-cutting, or high-risk repository work that needs search, change planning, dependency context, or verification guidance beyond exact source inspection.
smythmyke/govtoolspro-mcp-server
Skill Claude CodeCodex
Use when a user is evaluating a U.S. federal contracting opportunity (a SAM.gov notice, RFP/RFQ, solicitation number, NAICS code, or agency) and wants a bid/no-go decision, the competitive picture, a pricing benchmark, teaming partners, or a recompete pipeline. Drives the GovToolsPro connector tools in the right order…
Skill Claude Code
Parallel code implementation orchestrator. Breaks a task into independent work units, writes detailed specs, spawns parallel Task agents, reviews results, reports completion. Triggers on "/delegate", "/delegate [task]", "delegate this", "parallel implement".
MCP server Claude CodeCodexCursor +2
Build intent specs via Socratic AI conversation. Connect to your Intent Layer for context. Runs locally from the @pathmode/mcp-server npm package. Needs 1 environment variable to run.
zhengbingquant/frontier-skills
Skill Claude CodeCodex
Bootstrap a new Python project from a proven scaffold. Use whenever the user asks to start, create, scaffold, or set up a new Python tool, library, CLI, package, service, or experiment repo — or says 'set up a project the usual way'. Do NOT hand-roll a project structure from memory when this skill is available: run…
Plugin Claude Code
Bundles 1 skill, 7 agents · 177 tokens together
Turn Claude Code into a virtual startup — describe your idea in one line and a team of AI agents builds the MVP autonomously.
limengzhe27-boop/claude-product-doc-skills
Skill Claude CodeCodex needs its repo
A product-requirements writing guide that turns an idea into a detailed document an AI coding assistant can follow. PRD means product requirements document.
meesp123/claude-code-agent-team-debate
Command Claude Code
A debate command asks several AI agents to discuss a topic through proposals, challenges, and rebuttals before a lead agent gives a final decision. It can also include outside command-line AI tools when configured.
Skill Claude CodeCodex
Challenges decisions, plans, and code by systematically arguing the opposing side. Surfaces risks, pokes holes in assumptions, and stress-tests thinking before committing. Supports intensity levels (gentle, balanced, ruthless, linus) and works with conversation context or a specific file reference. Trigger on requests…
jneaimi/evaluate-before-you-build
Skill Claude CodeCodex
Solution design skill based on Bloom's AI Collaboration model. Use when the user says /design, wants to design a solution, compare architectural options, evaluate tradeoffs, or produce a solution design document before building. Also trigger on phrases like "design the solution", "how should we architect this"…
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: