Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,611 indexed, measured the same four ways as everything else here.
Search through Claude Code local chat history JSONL files to find information from past conversations. Use when the user asks "did we discuss X before", "what did we decide about Y", "how did we solve Z", or when context from a previous session would be useful. Searches all local session files efficiently via grep +…
Operational discipline framework for AI-assisted development. Deployment gates, epistemic humility enforcement, Docker hygiene, and completion verification. Born from $39.5K in mistakes so you don't have to make them.
★not rated 2
changed 18d agoA
tokens not measured
originalMIT
A design reviewer checks Claude Code plugin sub-agents against guidelines written in AGENTS.md. A sub-agent is a helper agent that performs a focused task inside a larger plugin.
Build production-quality Figma plugins from a natural-language description. Use this skill whenever the user wants to create, scaffold, modify, debug, or iterate on a Figma plugin — including FigJam widgets, Dev Mode plugins, and Slides plugins. Trigger on phrases like "build me a Figma plugin that…", "I want a plugin…
Vault-agnostic secret handling for Claude Code: store, list, and inject secrets without the model ever seeing plaintext. Multi-backend (file/Keychain/1Password) with PreToolUse blocking and output redaction.
★not rated 2 6mo agoA
tokens not measured
originalMIT
Arma laminas o slides nativos y editables (PowerPoint o Google Slides) que se ven identicos a un diseno hecho en HTML e imagen. Extrae la geometria real del navegador, emite el pptx nativo en el dialecto de cada motor, y valida contra el HTML midiendo lo que cada motor dibuja de verdad.
★not rated 2 3mo agoA
tokens not measured
originalMIT
A shared reference defining 24 layout types for visual-generator tools. Each layout includes its main idea, an ASCII sketch, visualization principles, suggested specifications, and cases where it should or should not be used.
Pipeline de skills e subagentes que conduz qualquer projeto de software (fullstack, API, CLI, biblioteca, dados/IA) do brainstorming ao código executável: analista e desenvolvedor de ideias, escritor de plano, designer, devs backend/banco/frontend/IA, analista de infra e analista de segurança — todos seniores, com…
★not rated 2 4mo agoA
tokens not measured
AGPL-3.0
Autonomous development loop: plan, ship, run codex adversarial-review, and iterate on findings until approved or threshold/iteration cap is reached. v0.3.2 adds --from-pr [ ] — a first-class entry path for mid-development PR handoff. When plan/implement/ship were done outside clodex, --from-pr bootstraps .clod.
★not rated 2 5mo agoA
tokens not measured
originalMIT
AI-powered college counseling tool that runs adaptive student interviews, generates competitive gap analyses, and optimizes campus visit plans. Built for school counselors working with limited time and large caseloads. Uses multi-agent deliberation to integrate equity considerations, academic competitiveness, and…
★not rated 2 6mo agoA
tokens not measured
AGPL-3.0
Recommends the right Claude model (Haiku/Sonnet/Opus) and effort level at session start by analyzing your first message, then pauses so you can switch before work begins.
★not rated 2 6mo agoA
tokens not measured
originalMIT
Security auditor and guard-builder for vibecoded apps. Finds vulnerabilities and missing guards across web, AI/LLM, Supabase/Firebase, Android, iOS, Electron, backend/IaC and CI/CD, then generates paste-ready hardening code. Community project, not an official Anthropic product.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Dispatch tasks to cursor-agent from Claude Code. In-place by default; --isolated opts into a sandbox worktree. Background jobs, session boundary safety, structured policy refusals.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Static security audit for projects extending Claude (skills, agents, hooks, plugins, MCP servers, slash commands, etc.) before installing them in Claude Code. Detects backdoors, prompt injection, persistence hooks, and supply-chain risks via parallel sub-agents.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Execute an approved plan or technical spec in Codex using complexity-based solo or multi-agent workflows. Use when the user wants implementation, especially with parallel agent teams.
Strict 3-role orchestration plugin — Orchestrator plans, Workers code, Validators verify. Hard enforcement via PreToolUse hooks.
★not rated 2 7mo agoA
tokens not measured
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: