Security hooks

jvm-skills/jvm-skills

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing git-guardrails.sh. From jvm-skills/jvm-skills.

dcb/homeassistant-claude-kit

Hook Claude Code

Runs before the agent uses a tool for Bash, Read, Glob, Grep and Bash tool calls, executing pretooluse-ha-push-validation.sh and privacy-guard.sh (2 commands). From dcb/homeassistant-claude-kit.

686f6c61/alfred-dev

Hook

Runs before the agent uses a tool for Write, Edit, Bash, mcp__.*, Bash and Read tool calls, running python3 (3 commands). From 686f6c61/alfred-dev.

dralgorhythm/claude-agentic-framework

Hook Claude Code

Runs before the agent uses a tool for Write, Edit, MultiEdit, NotebookEdit and Bash tool calls, executing pre-tool-use-validator.sh, dangerous-command-guard.sh, pre-commit-verification.sh, pre-push-main-blocker.sh and branch-pr-discipline.sh (6 commands). From dralgorhythm/claude-agentic-framework.

xiaolai/claudepot-app

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From xiaolai/claudepot-app.

001TMF/blatant-why

Hook Claude Code

Runs before the agent uses a tool for mcp__by-adaptyv__adaptyv_confirm_submission tool calls, executing safety-gate.js via node. From 001TMF/blatant-why.

assafkip/kipi-system

Hook Claude Code

Runs before the agent uses a tool for Write, Edit, MultiEdit and Bash tool calls, executing token-guard.py, read-first-gate.py, claude-path-write-guard.py and merge-bypass-gate.py via python3 (4 commands). From assafkip/kipi-system.

jayminwest/kotadb

Hook Claude Code

Runs before the agent uses a tool for Edit, Write, MultiEdit, Edit and Write tool calls, executing pre-edit-context.py and scope-enforcement.ts via python3 (2 commands). From jayminwest/kotadb.

EBISPOT/ols4

Hook Claude Code

Runs before the agent uses a tool for Bash, Read and Glob tool calls, running /Users/haideri/.local/share/uv/tools/graphifyy/bin/graphify (2 commands). From EBISPOT/ols4.

ivo-toby/mcp-picnic

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing claude-protect-main.sh, claude-block-force.sh and claude-secrets-scan.sh (3 commands). From ivo-toby/mcp-picnic.

Szotasz/marveen

Hook Claude Code

Runs before the agent uses a tool for Bash, .*send_email.* and mcp__plugin_telegram_telegram__reply tool calls, executing outgoing-copy-gate.py via python3 (3 commands). From Szotasz/marveen.

josipjelic/orchestrated-project-template

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing guard-destructive.sh. From josipjelic/orchestrated-project-template.

deepklarity/harness-kit

Hook Claude Code

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.

ShipWithAI/claude-code-mastery

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing npm-audit-check.sh. From ShipWithAI/claude-code-mastery.

coleam00/harness-engineering-demo

Hook Claude Code

Runs before the agent uses a tool for Bash, Read, Edit, Write, MultiEdit, NotebookEdit, Glob and Grep tool calls, executing security_guard.py via python. From coleam00/harness-engineering-demo.

ai-sdlc-framework/ai-sdlc

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing enforce-blocked-actions.sh via bash. From ai-sdlc-framework/ai-sdlc.

ai-sdlc-framework/ai-sdlc

Hook Claude Code

Runs when the agent asks permission for an action for Bash tool calls, executing permission-check.sh via bash. From ai-sdlc-framework/ai-sdlc.

90le/worker-rights-cn

Hook

Runs before the agent uses a tool, executing claude_hook_adapter.py via python3 with --event, --audit and --db-path. From 90le/worker-rights-cn.

Clear-Capabilities/agentic-security

Hook

Runs before the agent uses a tool for Edit, Write, MultiEdit and Bash tool calls, executing dispatch-pre-tool.js and pre-bash-guard.js via node (2 commands). From Clear-Capabilities/agentic-security.

jjanczur/tyran

Hook

Runs before the agent uses a tool for Bash, ^(Write, Edit, NotebookEdit, Bash, mcp__.*)$, .+, ^$, .+ and ^$ tool calls, executing secrets-gate.mjs, write-guard.mjs, policy-gate.mjs and usage-gate.mjs (4 commands). From jjanczur/tyran.

justi/claude-code-project-boundary

Hook

Runs before the agent uses a tool for Bash, Edit, Write and MultiEdit tool calls, executing guard.sh via bash (4 commands). From justi/claude-code-project-boundary.

NVIDIA/elements

Hook Claude Code ✓ vendor

Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing pre-tool-use-edit-write.sh and pre-tool-use-bash.sh with --show-toplevel (2 commands). From NVIDIA/elements.

wlsdks/ontology-atlas

Hook Claude Code

Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit and NotebookEdit tool calls, executing block-npm-publish.sh, block-unsafe-git.sh and block-generated-edit.sh (3 commands). From wlsdks/ontology-atlas.

sneg55/agent-starter

Hook

Runs before the agent uses a tool for Bash tool calls, executing block-dangerous-commands.sh. From sneg55/agent-starter.