ai-agent hooks

70 tagged ai-agent, measured the same way as everything else here.

Browse within: claude-code-plugin 122ai-tools 62agentic-ai 57ai-coding 50agentic-coding 48LLM 41cursor 37agent-tracing 35ai-observability 35cli 33hooks 33agent 32autonomous-agent 30mcp-server 30

SessionStart

01

FailproofAI/failproofai

Hook Claude Code

One of 5 in hooks.json

Runs when a session starts, executing dev-hook.mjs with --hook and --cli. From FailproofAI/failproofai.

not rated 5.5k +257 yesterday A tokens not measured

SessionStart

02

brycewang-stanford/Auto-Empirical-Research-Skills

Hook Claude Code

One of 3 in hooks.json

Runs when a session starts on compact and resume, executing setup-project-dirs.sh and post-compact-restore.py via bash (2 commands). From brycewang-stanford/Auto-Empirical-Research-Skills.

not rated 4.6k +90 yesterday A tokens not measured

SessionStart

03

fuxicodex/Fuxi

Hook Claude Code

Runs when a session starts, executing session-start.sh via bash. From fuxicodex/Fuxi.

not rated 3.3k +10 changed 16d ago A tokens not measured

PostToolUse

04

cloudwego/abcoder

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Write, Edit, mcp__abcoder__list_repos, mcp__abcoder__get_repo_structure, mcp__abcoder__get_package_structure and mcp__abcoder__get_file_structure tool calls, executing need_update.sh, prompt.sh and reminder.sh (3 commands). From cloudwego/abcoder.

not rated 390 1mo ago A tokens not measured original Apache-2.0

SessionStart

05

agenticmail/agenticmail

Hook Claude Code

One of 3 in hooks.json

Runs when a session starts, running agenticmail-codex-mail-hook. From agenticmail/agenticmail.

not rated 237 +1 2d ago A tokens not measured original MIT

PostToolUse

06

001TMF/blatant-why

Hook Claude Code

One of 3 in hooks.json

Runs after a tool call finishes, executing statusline.js and campaign-tracker.js via node (2 commands). From 001TMF/blatant-why.

not rated 117 today A tokens not measured original MIT

SessionStart

07

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

UserPromptSubmit

08

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

09

Desko77/claude-code-skills-1c

Hook Claude Code

One of 6 in hooks.json

Runs after a tool call finishes for Read, Edit, Write, MultiEdit, ^(mcp__[A-Za-z0-9._-]+__(validate_query, code_review, diagnostics, validate_for_export, get_project_errors, security_audit, check_1c_code, ask_1c_ai, syntaxcheck, detect_query_anti_patterns, insights), Bash, PowerShell)$, ^(Write, Edit, MultiEdit…

not rated 80 +2 changed 16d ago A tokens not measured original MIT

Stop

10

DekaPrayoga/AurixAgent

Hook Claude Code

One of 7 in hooks.json

Runs when the agent finishes a response, executing run-with-flags.js via node (6 commands). From DekaPrayoga/AurixAgent.

not rated 62 +1 2mo ago A tokens not measured

SessionStart

11

kochetkov-ma/claude-brewcode

Hook Claude CodeCodex

Runs when a session starts on startup, resume, clear and compact, executing session-start.mjs via node. From kochetkov-ma/claude-brewcode.

not rated 32 today A tokens not measured original MIT

SessionStart

12

akougkas/zulipchat-mcp

Hook Claude Code

One of 8 in settings.json

Runs when a session starts on startup and resume, running uvx --from zulipchat-mcp zulipchat-mcp-hook --zulip-config-f. From akougkas/zulipchat-mcp.

not rated 32 +1 changed 6d ago A tokens not measured original MIT

SessionStart

13

sgx-labs/statelessagent

Hook Claude Code

One of 5 in settings.json

Runs when a session starts, running same hook session-bootstrap (3 commands). From sgx-labs/statelessagent.

not rated 24 +1 today A tokens not measured

PostToolUse

14

onurpolat05/ALBA

Hook Claude Code

One of 10 in settings.json

Runs after a tool call finishes for Bash tool calls, executing error-logger.sh via bash. From onurpolat05/ALBA.

not rated 23 +1 2mo ago A tokens not measured original MIT

SessionStart

15

LYAKAKOY/Hermes-Codex-Plugin

Hook Claude Code

One of 4 in hooks.json

Runs when a session starts on startup, resume, clear and compact, executing session_start.py via python3. From LYAKAKOY/Hermes-Codex-Plugin.

not rated 19 4mo ago A tokens not measured

Stop

16

daeryundf2-prog/LAZYANTIGRAVITY

Hook Claude Code

Runs when the agent finishes a response, executing cli.js via node. From daeryundf2-prog/LAZYANTIGRAVITY.

not rated 14 3d ago A tokens not measured original MIT

BeforeTool

17

itallstartedwithaidea/google-ads-gemini-extension

Hook Claude Code

One of 2 in hooks.json

Runs on the BeforeTool event for run_gaql tool calls, executing validate-gaql.js via node. From itallstartedwithaidea/google-ads-gemini-extension.

not rated 9 3mo ago A tokens not measured original MIT

PreToolUse

19

ldilov/harness-forge

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool, executing pre-tool-use.sh. From ldilov/harness-forge.

not rated 6 5mo ago A tokens not measured GPL-3.0

PreToolUse

20

yushiran/Academic-Figure-Figma-CC-Skills

Hook Claude Code

Runs before the agent uses a tool for mcp__.*[Ff]igma.*__use_figma tool calls, executing figma_preflight.py. From yushiran/Academic-Figure-Figma-CC-Skills.

not rated 5 12d ago A tokens not measured

SessionStart

21

masa-san-jp/Agent-Aiko

Hook Claude Code

One of 3 in hooks.json

Runs when a session starts, executing aiko-session-context.mjs via node. From masa-san-jp/Agent-Aiko.

not rated 3 6d ago A tokens not measured original MIT

SessionStart

22

lastmindforever36/agent-grounded-infrastructure

Hook Claude CodeCodex

One of 3 in hooks.json

Runs when a session starts on startup and resume, executing session_start_autonomy.py via python3. From lastmindforever36/agent-grounded-infrastructure.

not rated 1 2mo 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: