Hooks

Shell commands your agent runs at defined points. A hook is code, so read it before you install it.

PostToolUse

337

mihai-dinculescu/tapo

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From mihai-dinculescu/tapo.

not rated 798 8d ago A tokens not measured original MIT

SessionStart

338

firoorg/firo

Hook Claude Code

One of 2 in settings.json

Runs when a session starts, executing session-start.sh. From firoorg/firo.

not rated 794 5d ago A tokens not measured copy · 55% MIT

UserPromptSubmit

339

regent-vcs/re_gent

Hook Claude Code

One of 4 in settings.json

Runs when you submit a prompt, before the agent sees it, running rgt message-hook user. From regent-vcs/re_gent.

not rated 789 2mo ago A tokens not measured copy · 55% Apache-2.0

Stop

340

regent-vcs/re_gent

Hook Claude Code

One of 4 in settings.json

Runs when the agent finishes a response, running rgt message-hook assistant. From regent-vcs/re_gent.

not rated 789 2mo ago A tokens not measured copy · 63% Apache-2.0

PostToolBatch

341

regent-vcs/re_gent

Hook Claude Code

One of 4 in settings.json

Runs after a batch of tool calls, running rgt tool-batch-hook. From regent-vcs/re_gent.

not rated 789 2mo ago A tokens not measured original Apache-2.0

PreToolUse

342

assistant-ui/tool-ui

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash(git add*) and Bash(git commit*) tool calls, running an inline shell check (2 commands). From assistant-ui/tool-ui.

not rated 772 4d ago A tokens not measured original MIT

SessionStart

343

assistant-ui/tool-ui

Hook Claude Code

One of 3 in settings.json

Runs when a session starts, running an inline shell check (2 commands). From assistant-ui/tool-ui.

not rated 772 4d ago A tokens not measured original MIT

PostToolUse

344

carlrannaberg/claudekit

Hook Claude Code

One of 6 in settings.json

Runs after a tool call finishes for Write, Edit, MultiEdit, Write, Edit, MultiEdit, Write, Edit, MultiEdit, Write, Edit, MultiEdit, Edit, MultiEdit, Write, Edit and MultiEdit tool calls, running claudekit-hooks run typecheck-changed (6 commands). From carlrannaberg/claudekit.

not rated 761 5mo ago A tokens not measured original MIT

Stop

345

carlrannaberg/claudekit

Hook Claude Code

One of 6 in settings.json

Runs when the agent finishes a response, running claudekit-hooks run create-checkpoint (6 commands). From carlrannaberg/claudekit.

not rated 761 5mo ago A tokens not measured original MIT

UserPromptSubmit

346

carlrannaberg/claudekit

Hook Claude Code

One of 6 in settings.json

Runs when you submit a prompt, before the agent sees it, running claudekit-hooks run thinking-level (2 commands). From carlrannaberg/claudekit.

not rated 761 5mo ago A tokens not measured original MIT

PostToolUse

347

traceroot-ai/traceroot

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, executing lint.sh. From traceroot-ai/traceroot.

not rated 755 today A tokens not measured

SessionStart

348

vshulcz/deja-vu

Hook

One of 3 in hooks.json

Runs when a session starts on startup and resume, executing deja.sh. From vshulcz/deja-vu.

not rated 765 today A tokens not measured original MIT

UserPromptSubmit

349

vshulcz/deja-vu

Hook

One of 3 in hooks.json

Runs when you submit a prompt, before the agent sees it, executing deja.sh. From vshulcz/deja-vu.

not rated 765 today A tokens not measured original MIT

PreCompact

350

vshulcz/deja-vu

Hook

One of 3 in hooks.json

Runs before the context is compacted for manual and auto tool calls, executing deja.sh. From vshulcz/deja-vu.

not rated 765 today A tokens not measured original MIT

PostToolUse

351

3b1b/3Blue1Brown.com

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From 3b1b/3Blue1Brown.com.

not rated 737 today A tokens not measured

SessionStart

352

desplega-ai/agent-swarm

Hook

One of 6 in hooks.json

Runs when a session starts, running bunx @desplega.ai/agent-swarm@latest hook. From desplega-ai/agent-swarm.

not rated 740 today A tokens not measured original MIT

UserPromptSubmit

353

desplega-ai/agent-swarm

Hook

One of 6 in hooks.json

Runs when you submit a prompt, before the agent sees it, running bunx @desplega.ai/agent-swarm@latest hook. From desplega-ai/agent-swarm.

not rated 740 today A tokens not measured copy · 86% MIT

PostToolUse

354

desplega-ai/agent-swarm

Hook

One of 6 in hooks.json

Runs after a tool call finishes, running bunx @desplega.ai/agent-swarm@latest hook. From desplega-ai/agent-swarm.

not rated 740 today A tokens not measured copy · 86% MIT

PreToolUse

355

yunus-0x/meridian

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From yunus-0x/meridian.

not rated 728 2mo ago A tokens not measured

PostToolUse

356

citypaul/.dotfiles

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Write, Edit and NotebookEdit tool calls, running an inline shell check. From citypaul/.dotfiles.

not rated 725 today A tokens not measured

PostToolUse

357

kdlbs/kandev

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check (2 commands). From kdlbs/kandev.

not rated 739 today A tokens not measured AGPL-3.0

PreToolUse

358

vybestack/llxprt-code

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing git-pre-push-check.sh. From vybestack/llxprt-code.

not rated 700 today A tokens not measured original Apache-2.0

SessionStart

359

vybestack/llxprt-code

Hook

Runs when a session starts, executing on-start.js via node. From vybestack/llxprt-code.

not rated 700 today A tokens not measured copy · 100% Apache-2.0

SessionStart

360

arklexai/Agent-First-Organization

Hook Claude Code

One of 4 in settings.json

Runs when a session starts, running an inline shell check. From arklexai/Agent-First-Organization.

not rated 699 +1 4mo ago A tokens not measured original MIT

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: