ai-agents hooks

310 tagged ai-agents, measured the same way as everything else here.

Browse within: claude-code-plugin 287cli 174agentic-ai 140cursor 126agent-memory 124agent-orchestration 122LLM 119ai-coding 90Multi-Agent 78agentic-coding 77codex-cli 68ai-memory 63Autonomous Agents 62ai-tools 58

SessionStart

01

google-gemini/gemini-cli

Hook Claude Code ✓ vendor

Runs when a session starts, executing on-start.js via node. From google-gemini/gemini-cli.

not rated 107k +124 today A ✓ AI review tokens not measured original Apache-2.0

PostToolUse

02

aaif-goose/goose

Hook Claude Code

One of 4 in hooks.json

Runs after a tool call finishes for developer__shell and developer__text_editor tool calls, executing announce.sh. From aaif-goose/goose.

not rated 55k +213 today A ✓ AI review tokens not measured original Apache-2.0

SessionStart

03

code-yeongyu/lazycodex

Hook Claude Code

Runs when a session starts, executing cli.js via node. From code-yeongyu/lazycodex.

not rated 3.8k +31 changed 2d ago A tokens not measured original MIT

SessionStart

04

moorcheh-ai/memanto

Hook Claude Code

One of 3 in hooks.json

Runs when a session starts on startup and resume, running an inline shell check. From moorcheh-ai/memanto.

not rated 2.3k +15 changed 1mo ago A tokens not measured original MIT

SessionStart

05

tractorjuice/arc-kit

Hook Claude Code

One of 6 in hooks.json

Runs when a session starts on startup, resume and clear, executing arckit-codex-hook.mjs. From tractorjuice/arc-kit.

not rated 2.3k +6 yesterday A tokens not measured

PreToolUse

06

RyanAlberts/best-of-Agent-Harnesses

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing guard.sh. From RyanAlberts/best-of-Agent-Harnesses.

not rated 1.2k +109 4d ago A tokens not measured CC-BY-SA-4.0

PostToolUse

07

alibaba/skill-up

Hook Claude Code ✓ vendor

One of 4 in hooks.json

Runs after a tool call finishes for ^mcp__skill_up_observer__(mark_skill_invocation, attach_skill_evidence and record_skill_feedback)$ tool calls, executing observer.py via python3. From alibaba/skill-up.

not rated 1.2k +51 2d ago A tokens not measured original Apache-2.0

UserPromptSubmit

08

EverMind-AI/SkillCorpus

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing hook.mjs via node. From EverMind-AI/SkillCorpus.

not rated 686 +2 yesterday A tokens not measured original Apache-2.0

SessionStart

09

josstei/maestro-orchestrate

Hook Claude Code

One of 4 in hooks.json

Runs when a session starts, executing hook-runner.js via node. From josstei/maestro-orchestrate.

not rated 479 +14 5d ago A tokens not measured original Apache-2.0

SessionStart

10

qualixar/superlocalmemory

Hook Claude Code

One of 4 in hooks.json

Runs when a session starts, running an inline shell check (2 commands). From qualixar/superlocalmemory.

not rated 241 +11 changed 7d ago A tokens not measured AGPL-3.0

PreToolUse

11

johnkf5-ops/the-dev-squad

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool, executing approval-gate.sh. From johnkf5-ops/the-dev-squad.

not rated 240 5mo ago A tokens not measured original MIT

PreToolUse

12

weijiafu14/pi2dsh

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, running touch "$CLAUDE_PROJECT_DIR/.hook-fired". From weijiafu14/pi2dsh.

not rated 216 +4 2d ago A tokens not measured original MIT

PostToolUse

13

serradura/okf

Hook Claude Code

One of 5 in settings.json

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, running "$CLAUDE_PROJECT_DIR"/.claude/hooks/run post-edit. From serradura/okf.

not rated 179 +1 1mo ago A tokens not measured copy · 44% Apache-2.0

UserPromptSubmit

14

mtarcure/claude-vibe-squad

Hook Claude Code

One of 2 in settings.json

Runs when you submit a prompt, before the agent sees it, executing context-tripwire.sh via bash. From mtarcure/claude-vibe-squad.

not rated 165 25d ago A tokens not measured original MIT

PreToolUse

15

arbiterForge/codeArbiter

Hook Claude Code

One of 6 in hooks.json

Runs before the agent uses a tool for Bash, shell_command, exec_command, unified_exec, apply_patch, Write, Edit, spawn_agent, collaborationspawn_agent, multi_agent_v1send_input, multi_agent_v1resume_agent, multi_agent_v1close_agent, collaborationsend_message, collaborationfollowup_task, collaborationinterrupt_agent…

not rated 149 +2 changed 5d ago A tokens not measured AGPL-3.0

PostToolUse

16

NeoTheCapt/RedteamAgent

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Bash, Agent, Write and Edit tool calls, executing post-tool-log.sh via bash (4 commands). From NeoTheCapt/RedteamAgent.

not rated 146 +3 2mo ago A tokens not measured

SessionStart

17

Xiaoyangy/novel-studio

Hook Claude Code

One of 5 in hooks.json

Runs when a session starts on startup, resume, clear and compact, executing story_codex_hook.py. From Xiaoyangy/novel-studio.

not rated 137 +6 23d ago A tokens not measured original Apache-2.0

PostToolUse

18

cowwoc/cat

Hook Claude Code

One of 4 in hooks.json

Runs after a tool call finishes for Bash, Write, Edit, Read, Glob, Grep, WebFetch and WebSearch tool calls, executing get-posttool-output.py, detect-assistant-giving-up.sh, get-bash-posttool-output.py, remind-restart-after-skill-modification.sh and get-read-posttool-output.py via python3 (5 commands). From cowwoc/cat.

not rated 101 2mo ago A tokens not measured

SessionStart

19

FareedKhan-dev/claude-code-staff-engineer

Hook Claude Code

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From FareedKhan-dev/claude-code-staff-engineer.

not rated 93 6mo ago A tokens not measured original MIT

SessionStart

20

nota-america/forgecat-agent-profiles

Hook Claude Code

One of 2 in settings.json

Runs when a session starts, executing _fc_wrap.sh. From nota-america/forgecat-agent-profiles.

not rated 91 +1 changed 29d ago A tokens not measured original Apache-2.0

BeforeTool

21

Jamkris/everything-gemini-code

Hook Claude Code

One of 6 in hooks.json

Runs on the BeforeTool event for tool == "run_shell_command", tool == "run_shell_command", tool == "run_shell_command" && tool_input.command matches "^\\s*(npm (install, test, i, ci), pnpm (install, test, i), yarn (install, test, add, remove, upgrade), bun (install, test, i, add, remove), cargo build, make, docker…

not rated 89 +1 4mo ago A tokens not measured original MIT

UserPromptSubmit

22

sysnet4admin/_Book_Claude-Code

Hook Claude Code

One of 2 in settings.json

Runs when you submit a prompt, before the agent sees it, running date >> last_prompting_history.log. From sysnet4admin/_Book_Claude-Code.

not rated 82 12d ago A tokens not measured

PostToolUse

23

Arcadia-1/analog-agents

Hook Claude Code

One of 4 in hooks.json

Runs after a tool call finishes for spectre, virtuoso-bridge, Write and Edit tool calls, executing post-sim.sh and post-netlist-check.sh (2 commands). From Arcadia-1/analog-agents.

not rated 80 +3 3mo ago A tokens not measured

SessionStart

24

superplan-md/superplan-plugin

Hook Claude Code

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From superplan-md/superplan-plugin.

not rated 75 5mo ago A tokens not measured original Apache-2.0

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: