Find plugins

by HashiCorp

The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.

by Greptile

AI code review agent for GitHub and GitLab. View and resolve Greptile's PR review comments directly from Claude Code.

by The Hugging Face team

Conventions and task skills for contributing to diffusers

by Volcano Engine

Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.

by OpenViking

Long-term semantic memory for Codex, powered by OpenViking. Recall on UserPromptSubmit, incremental add_message on Stop (per turn), commit on PreCompact, and active-window heuristic + idle-TTL sweep on SessionStart (source=startup|clear). Includes a local stdio MCP proxy that reads OpenViking credentials from env/ovcli.conf.

by OpenViking

Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.

by feder-cr

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

by feder-cr

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

by feder-cr

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

by Seza Akgün

2048 above the Claude Code prompt: slide and merge tiles up to 2048. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs function hooks (early access) and an interactive terminal with a mouse.

by claude-code-templates

Organization control mod: withholds the http and process nouns from $ so no plugin beneath it can reach the network or spawn processes, refuses user-tier plugins by name allowlist or by the $ calls their source declares, and withholds the Bash tool (shellPolicy "deny", default) or, in "guardrail" mode, denies well-known network clients as a bypassable speed bump. Hooks engine.create, plugin.register and tool.call; seat it in the managed prepend tier.

by claude-code-templates

/aitmpl opens a component browser above the prompt: the aitmpl.com catalog (agents, commands, MCPs, settings, hooks, skills, loops, mods) read live from the site's public JSON through $.http.fetch. Pick a type or a trending component, filter, page, open a component and install it from there ($.process.run with the fixed CLI argv and a validated path, no shell), drop its install command into the prompt, or open its page in your browser. Hooks session.start, command.run and ui.render on AbovePrompt; browsing costs no tokens.

by claude-code-templates

Denies Bash commands that match destructive patterns (recursive rm on roots, force push, hard reset, destructive SQL, disk formatting) before they run. A tool.call hook with a Bash matcher that returns { deny } without calling next.

by Seza Akgün

Games above the Claude Code prompt (snake, Tetris, 2048, Minesweeper, Flappy, Pong, typing test, Space Invaders, Doom) plus a pet that grows as Claude tests, commits and edits. Clones of the genre, not affiliated with or endorsed by Tetris Holding, Taito, Atari or id Software. Needs function hooks (early access) and an interactive terminal.

by claude-code-templates

Space Invaders above the Claude Code prompt where every wave is the code Claude just wrote: each line an Edit or Write added becomes a row of the formation and every two characters one alien, so you shoot your own diff. Ship, one shot at a time, bombs, three lives, best score. Zero tokens. Needs function hooks (early access) and an interactive terminal.

by Seza Akgün

Doom above the Claude Code prompt: a corridor shooter: imps, a shotgun, and the floor below. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs function hooks (early access) and an interactive terminal with a mouse.

by Seza Akgün

Flappy above the Claude Code prompt: flap through the gaps in the pipes. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs function hooks (early access) and an interactive terminal with a mouse.

by Seza Akgün

Space Invaders above the Claude Code prompt: shoot each wave before it lands. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs function hooks (early access) and an interactive terminal with a mouse.

by claude-code-templates

Screens every prompt going into the conversation and every reply coming out of it with TypeSafe's Jev, a System One decision model, the way TypeSafe's guardrails cookbook does: one request per message asks a battery of hazard questions (jailbreak, harm or a crime, a diagnosis or a dosage, self-harm) and scores how much harm complying would do. The thresholds live here, in a named policy (strict or permissive), and turn the probabilities into pass, review (the user is asked), block (the prompt is dropped, or the reply withheld) or support. Falls back to the engine's built-in classifier when no key is set.

by claude-code-templates

Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to the engine's built-in classifier when no key is set.

by claude-code-templates

Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-suggestion cookbook does: one request ranks every skill and asks whether the prompt needs a skill at all, a second re-reads the top three with their SKILL.md and can reject them all. The winner's SKILL.md is attached to the prompt, so the skills can be hidden from the model altogether (/jev-skill-suggestion:setup makes them user-invocable-only and /context counts them at 0). Falls back to the engine's built-in classifier when no key is set.

by claude-code-templates

Asks the user, in the engine's AskUserQuestion dialog ($.ui.ask), before Claude edits or overwrites a file larger than a configurable line count; denies by default when nobody can answer (headless runs). A tool.call hook on Edit and Write using $.fs.read.

by Seza Akgün

Minesweeper above the Claude Code prompt: open every cell that is not a mine. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs function hooks (early access) and an interactive terminal with a mouse.

by claude-code-templates

Rewrites npm and npx invocations to pnpm (or yarn / bun) before the Bash tool runs them and tells the model what ran through context. A tool.call hook that forwards a modified event (the modifying placement).