PreToolUse
01Hook
Runs before the agent uses a tool, executing cc-safety-net.js via node with --coding-cli. From kenryu42/cc-safety-net.
93 tagged ai safety, measured the same way as everything else here.
Browse within: ai-governance 33python 11Guardrails 10Autonomous Agents 8agent-guard 8ai-security 8beginner-friendly 6circuit-breaker 6linux 6macos 6process-management 6Autonomous 5agent-governance 5agent-reliability 5
Hook
Runs before the agent uses a tool, executing cc-safety-net.js via node with --coding-cli. From kenryu42/cc-safety-net.
Hook Claude Code
Runs before the agent uses a tool for Bash, Edit, MultiEdit and Write tool calls, executing pre-tool-use.js via node (5 commands). From pegasi-ai/reins.
Hook Claude Code
Runs after a tool call finishes for Bash, Edit, MultiEdit and Write tool calls, executing post-tool-use.js via node (5 commands). From pegasi-ai/reins.
Hook Claude Code
Runs after a tool call finishes for Edit, Write and NotebookEdit tool calls, executing ruff_on_edit.py via python3. From guardana/guardana.
Hook
Runs before the agent uses a tool for Bash, PowerShell and Read tool calls, executing pre_tool_use.py and pre_read.py via python (3 commands). From frmoretto/hardstop.
Hook
Runs before the agent uses a tool, running gnt hooks check-action. From gnt-ai/gnt.
Hook Claude Code
Runs when the agent finishes a response, executing hook-stop-self-score.sh, hook-stop-verify-deploy.sh, hook-stop-pr-thread-check.sh, hook-stop-anti-claim.js and meta-agent-loop.js via bash (5 commands). From IgorGanapolsky/ThumbGate.
Hook Claude Code
Runs after a tool call finishes for mcp__thumbgate__feedback_stats and mcp__thumbgate__dashboard tool calls, executing cli.js via node. From IgorGanapolsky/ThumbGate.
Hook Claude Code
Runs when a session starts, executing cli.js and revenue-truth.sh via node (2 commands). From IgorGanapolsky/ThumbGate.
Hook
Runs after a tool call finishes for Edit and Write tool calls, executing context-monitor.sh, session-start-marker.sh, tmp-cleanup.sh, syntax-check.sh and activity-logger.sh (5 commands). From yurukusa/claude-code-hooks.
Hook
Runs when the agent sends a notification, executing no-ask-human.sh. From yurukusa/claude-code-hooks.
Hook
Runs when the agent finishes a response, executing proof-log-session.sh. From yurukusa/claude-code-hooks.
Hook
Runs when a session starts on startup, executing scanner-hook.js via node. From core0-io/nio.
Hook
Runs when you submit a prompt, before the agent sees it, executing collector-hook.js via node. From core0-io/nio.
Hook
Runs before the agent uses a tool, executing guard-hook.js and collector-hook.js via node (2 commands). From core0-io/nio.
datumbrain/claude-code-privacy-guard
Hook
Runs when you submit a prompt, before the agent sees it, executing prompt-guard.js via node. From datumbrain/claude-code-privacy-guard.
Hook Claude Code
Runs when a session starts, executing session_start.rb. From sane-apps/SaneProcess.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing sane_catastrophic_guard.rb, sanetools.rb and sane_bash_guards.rb via ruby (3 commands). From sane-apps/SaneProcess.
Hook Claude Code
Runs after a tool call finishes for Write, Edit, Write and Edit tool calls, executing sanetrack.rb, swift_format.rb and mini_build_async.rb (3 commands). From sane-apps/SaneProcess.
Hook Claude Code
Runs when a session starts, running an inline shell check. From johnnichev/selectools.
Hook Claude Code
Runs after the context is compacted, running an inline shell check. From johnnichev/selectools.
Hook Claude Code
Runs before the agent uses a tool for Bash and Bash tool calls, running an inline shell check (2 commands). From johnnichev/selectools.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing consent_gate_grant.mjs via node. From friedbotstudio/baseline.
Hook Claude Code
Runs when a session starts, executing memory_session_start.mjs via node. From friedbotstudio/baseline.