40,000 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.
vtroisWhite/andrej-karpathy-skills
Plugin Claude Code
Bundles 1 skill · 46 tokens together
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Plugin Claude Code
Bundles 3 skills, 1 agent, 4 hooks · 137 tokens together
Multi-agent task orchestration with visual terminal panes. Decomposes complex dev tasks into parallel Claude Code instances coordinated through dependency-aware waves.
Plugin Claude Code
Bundles 5 skills, 4 commands, 3 hooks · 295 tokens together
CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.
yuting0624/antigravity-for-claude-code
Plugin Claude Code
Bundles 2 skills, 11 commands, 1 agent, 2 hooks · 1,034 tokens together
Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the SDLC. Claude conducts — requirements, architecture, the hard 20%, verification, review — and routes deterministic, high-volume work (scaffolding, tests, first-pass review, migrations, web/Vertex AI…
Skill Claude Code
Fan out a batch of autopilot-queued issues to parallel background worktree subagents — each runs /autopilot at the build model from its 'model:' label — with a gating review at Opus 5 or above and never below the build (Opus reviews Sonnet and Opus builds, Fable reviews Fable builds).
Community-Access/accessibility-agents
Plugin Claude Code
Bundles 108 skills, 6 hooks · 2,914 tokens together
WCAG 2.2 AA enforcement. Six router skills dispatch the specialist team; hooks block UI edits until the accessibility lead has reviewed.
Plugin Claude Code
Bundles 4 skills, 2 agents, 1 hook, 1 MCP server · 508 tokens together
Author, maintain, backfill, validate, visualize and serve (MCP) Open Knowledge Format (OKF) bundles: portable markdown knowledge for humans and agents.
Plugin Gemini CLI
MCP configuration declaring 1 server: nodeServer.
Skill Claude Code
Deep persona design for Agentforce agents with 50-point scoring. TRIGGER when: user designs agent personas, defines agent personality/identity, creates persona documents, encodes persona into Agentforce Builder fields or Agent Script, translates brand guidelines to agent voice, or asks about agent tone/voice/register.…
Skill Claude CodeCodex
Should invoke if an agent session is about to write data to a LaminDB instance to track this agent session as a run. Should also invoke when tasked to curate datasets.
Plugin Claude Code
Bundles 1 skill, 1 agent, 5 hooks · 86 tokens together
Royal Navy agent coordination framework — sailing orders, battle plans, action stations, and a captain's log.
Plugin Claude Code
Bundles 14 skills, 16 commands, 2 hooks · 446 tokens together
Multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 14 skills, 16 commands, quality gates, TDD enforcement.
Command Claude Code
Slash commands are typed at the Claude Code input prompt during an active session. Every command starts with /.
Skill Claude CodeCodex
Guided MARM MCP setup. Invoke after running marm-memory init on the CLI to configure MARM memory across your agent. Drives transport choice, runtime choice, MCP config writing, multi-agent linking, and server start. Works on Claude, Codex, Gemini, Qwen, Cursor, VS Code, and other MCP-capable agents.
Skill Claude CodeCodex
A task-routing and checking workflow for explicitly requested Metis work. It assigns work to defined roles, records checks, and limits recovery when something fails.
Plugin Claude Code
Bundles 1 skill, 23 commands, 14 agents · 1,584 tokens together
AI-SDLC governance framework for Claude Code — action enforcement, telemetry, quality gates, and review agents.
TheSyart/claude-agent-examples
Skill Claude CodeCodex
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Skill Claude CodeCodex
Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source…
Skill Claude CodeCodex
Use when the adopter asks to delegate to local OSS agents (OpenCode) on a READY local runtime.
Plugin Claude Code
Bundles 7 skills, 1 hook · 318 tokens together
TermCanvas skills: Hydra sub-agent orchestration, adversarial review, systematic debugging, security auditing, code review, and browser-based QA testing.
Skill Codex
Author, validate, and troubleshoot complete FlowCraft configuration: deployment documents (deploy.yaml with the runtime section, inference/workspace/sandbox/tool sub-documents, core/memory contracts, and graph JSON node wiring), craft.yaml application definitions, and plugin.json manifests. Use when writing or…
Varietyz/Disciplined-AI-Software-Development
Agent Claude Code
Meta-agent that generates portable, evidence-grounded investigation agents by walking the four-layer ten-node derivation-loop — discovers the target domain from real resources, gates the highest-worth agent shape (teleology; the 3/5/7 rigor is a ranked choice), composes a runtime-neutral portable contract grounded in…
Skill Claude CodeCodex
Continuously watch and operate a running §BRANDNAMETITLE§ multi-agent run from outside the agent pool: keep work progressing, intervene on concerns, maintain an operational journal, and escalate only at genuine forks. Use when operating/babysitting a §BRANDNAMETITLE§ run, not when authoring the work yourself.
adamallcock/codex-chatgpt-control
Skill Claude CodeCodex needs its repo
Backward-compatible alias for a visible Chat consultation with the Pro intelligence setting; prefer chatgpt-delegate for new Chat or Work delegation workflows.
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: