Discover Claude mods
By default this lists only evidenced Claude Code mods: plugins whose hooks configuration names function-hook modules. The server looks for new mods on GitHub every 6 hours and also takes repositories you submit.
Showing 1–20 of 22 results
★ is the repository's star count, not package quality. Download requests are not installs. Metric definitions
-
admin-capability-lockdownPlugin
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 t…
-
chessPlugin
Play chess against Claude (or Jev, when a Jev key is set) in a side pane while you work. Click a piece and a square, or type a move; Claude answers through a fork of the session, Jev through TypeSafe…
-
diff-invadersPlugin
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 …
-
pacmanPlugin
Pac-Man above the Claude Code prompt: a 19×15 maze, four ghosts that chase, scatter and flee, power pellets, three lives and faster levels. Plays while Claude works, pauses when the turn ends, keeps …
-
tool-defensePlugin
A tower defense above the Claude Code prompt where every enemy is one of Claude's real tool calls: Bash sends runners, an Edit or Write a slow tank, a web or MCP call a flyer, an Agent a boss. Build …
-
websearch-to-exaPlugin
Overrides the built-in WebSearch tool and routes queries to the Exa search API through $.http.fetch, answering in WebSearch's own result shape, with automatic fallback to the built-in search. A tool.…
-
universal-audit-logPlugin
One hook on * that records every event on $ (tool calls, prompts, turns, other plugins' fs/http/process calls) as JSON lines with origin plugin and tier, duration and outcome, including denials. Buff…
-
aitmplPlugin
/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 $.http.fetch. P…
-
jev-model-routerPlugin
Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at a…
-
jev-skill-suggestionPlugin
Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-sugge…
-
npm-to-pnpm-rewriterPlugin
Rewrites npm and npx invocations to pnpm (or yarn / bun) before the Bash tool runs them and tells the model what ran through context. A tool.call hook that forwards a modified event (the modifying pl…
-
webfetch-cachePlugin
Short-circuits repeated WebFetch calls for the same URL and prompt within a session, answering { result } from cache without a network round trip. A tool.call hook with TTL and size limits.
-
block-destructive-commandsPlugin
Denies Bash commands that match destructive patterns (recursive rm on roots, force push, hard reset, destructive SQL, disk formatting) before they run. A tool.call hook with a Bash matcher that retur…
-
jev-auto-modePlugin
A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a suba…
-
jev-guardrailsPlugin
Screens every prompt going into the conversation and every reply coming out of it with TypeSafe's Jev, a System One decision model, the way TypeSafe's guardrails cookbook does: one request per messag…
-
jev-vercel-sandboxPlugin
A Vercel Sandbox Claude sends work to on purpose: long test runs in the background, someone else's repository, an installer of unknown origin, a bulk change to preview as a patch, a clean build. Type…
-
large-edit-confirmationPlugin
Asks the user, in the engine's AskUserQuestion dialog ($.ui.ask), before Claude edits or overwrites a file larger than a configurable line count; denies by default when nobody can answer (headless ru…
-
protected-paths-guardPlugin
Denies Edit, Write and NotebookEdit calls on sensitive paths (.env files, lockfiles, CI workflows, git internals, private keys) with a glob allowlist override. A tool.call hook with an array matcher.
-
secret-redactorPlugin
Redacts API keys, tokens, JWTs, private keys and connection strings from every tool result before the model reads them, notes the redaction through context, and refuses to echo a redacted placeholder…
-
agent-flowPlugin
A side pane that draws the session's agent flow live: the main loop's context window, every subagent it spawns as a tree, and for each one the context handed down (its prompt, or the whole parent con…
Registry status
- Claude Mods
- 5
- Packages
- 2,636
- Repositories
- 175
- Versions
- 2,758
- Download requests
- 3
- Last collection
- Succeeded Run details
1,179 repositories are still waiting in the discovery queue, so the index is not complete.