PreCompact
25Hook Claude Code
One of 7 in settings.json
Runs before the context is compacted, executing sage-pre-compact.sh via bash. From l33tdawg/sage.
351 tagged agentic-ai, measured the same way as everything else here.
Browse within: agentic-workflow 204agentic-coding 133agentic-engineering 84ai-coding 65claude-code-plugin 49ai-coding-assistant 40hooks 30claude-ai 29agent-framework 28agentic-development 27audit 27chatgpt 27ai-governance 26context-engineering 26
Hook Claude Code
One of 7 in settings.json
Runs before the context is compacted, executing sage-pre-compact.sh via bash. From l33tdawg/sage.
Hook Claude Code
One of 7 in settings.json
Runs when a session ends, executing sage-session-end.sh via bash. From l33tdawg/sage.
Hook Claude Code
One of 7 in settings.json
Runs when a session starts on startup, resume and compact, executing sage-session-start.sh via bash (3 commands). From l33tdawg/sage.
Joonghyun-Lee-Frieren/oh-my-antigravity
Hook
One of 2 in hooks.json
Runs on the BeforeModel event, executing hook-bootstrap.js via node. From Joonghyun-Lee-Frieren/oh-my-antigravity.
Joonghyun-Lee-Frieren/oh-my-antigravity
Hook
One of 2 in hooks.json
Runs on the AfterAgent event, executing hook-bootstrap.js via node. From Joonghyun-Lee-Frieren/oh-my-antigravity.
Hook Claude Code
One of 3 in settings.json
Runs before the context is compacted, running bd prime. From Zettelgarden/Zettelgarden.
Hook Claude Code
One of 3 in settings.json
Runs when a session starts, running bd prime. From Zettelgarden/Zettelgarden.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts on startup, executing cloud_agent_setup.sh. From tilework-tech/nori-skillsets.
Hook Claude Code
One of 3 in settings.json
Runs before the agent uses a tool for Edit, Write, Edit and Write tool calls, running an inline shell check (2 commands). From deepklarity/harness-kit.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From deepklarity/harness-kit.
Hook Claude Code
One of 9 in settings.json
Runs when you submit a prompt, before the agent sees it, executing genesis_urgent_alerts.py, review_enforcement_prompt.py, proactive_memory_hook.py, skill_injection_hook.py, contribution_offer_hook.py and session_activity_touch.sh (6 commands). From WingedGuardian/GENesis-AGI.
Hook Claude Code
One of 9 in settings.json
Runs before the context is compacted, executing genesis_precompact.py. From WingedGuardian/GENesis-AGI.
Hook Claude Code
One of 9 in settings.json
Runs when a tool call fails for Edit and Write tool calls, executing edit_failure_sensor.py. From WingedGuardian/GENesis-AGI.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From vstorm-co/memv.
Hook Claude Code
One of 3 in settings.json
Runs when the agent sends a notification for permission_prompt tool calls, running afplay /System/Library/Sounds/Ping.aiff. From vstorm-co/memv.
hoangsonww/AI-Agents-Orchestrator
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 hoangsonww/AI-Agents-Orchestrator.
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.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Bash, PowerShell, Write and Edit tool calls, executing lint-chain-guard.sh and dispatch.sh via bash (2 commands). From alfadur7/llm-wiki-newsroom.
Hook Claude Code
One of 3 in settings.json
Runs before the agent uses a tool for Write, Edit, Bash and PowerShell tool calls, executing dispatch.sh via bash (2 commands). From alfadur7/llm-wiki-newsroom.
MuhammadUsmanGM/claude-code-best-practices
Hook Claude Code
One of 3 in settings.json
Runs before the agent uses a tool for Write and Edit tool calls, executing block-secrets.sh via bash. From MuhammadUsmanGM/claude-code-best-practices.
MuhammadUsmanGM/claude-code-best-practices
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Write and Edit tool calls, executing format-on-write.sh via bash. From MuhammadUsmanGM/claude-code-best-practices.
Hook Claude Code
One of 2 in settings.json
Runs before the agent uses a tool for Edit, MultiEdit and Write tool calls, executing validate_disorder_hook.py (2 commands). From monarch-initiative/dismech.
Hook Claude Code
One of 3 in settings.json
Runs when the agent finishes a response, executing stop-check.sh via bash. From LiorCohen/sdd.
Hook Claude Code
One of 3 in settings.json
Runs when you submit a prompt, before the agent sees it, executing skill-activate.sh via bash. From LiorCohen/sdd.
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: