Security hooks

llcoolblaze/claude-boris

Hook Claude Code

Runs before the agent uses a tool for [object Object] and [object Object] tool calls, running an inline shell check (2 commands). From llcoolblaze/claude-boris.

sayanarijit/cottage

Hook Claude Code

Runs before the agent uses a tool for Read, Edit, Write, MultiEdit, NotebookEdit and Bash tool calls, executing deny-secrets.py via python3 with --show-toplevel. From sayanarijit/cottage.

26zl/cybersec-toolkit

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing agent-guard.sh via bash. From 26zl/cybersec-toolkit.

wigtn/wigtn-plugins

Hook

Runs before the agent uses a tool for Bash and Bash tool calls, executing gate.sh via bash (2 commands). From wigtn/wigtn-plugins.

martinholovsky/claude-skills-generator

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From martinholovsky/claude-skills-generator.

TheAstrelo/Claude-Pipeline

Hook Claude Code

Runs before the agent uses a tool for Edit and Write tool calls, executing protect-files.sh via bash. From TheAstrelo/Claude-Pipeline.

777genius/social-monitor

Hook Claude Code

Runs before the agent uses a tool for Bash, Read, Edit, Write, MultiEdit, NotebookEdit, Grep, Glob and Agent tool calls, running node. From 777genius/social-monitor.

darkroomengineering/cc-settings

Hook

Runs before the agent uses a tool for Bash tool calls, executing codex-hook.ts via bun (4 commands). From darkroomengineering/cc-settings.

DGouron/review-flow

Hook Claude Code

Runs before the agent uses a tool for Write, Edit, Bash and Agent tool calls, executing no-barrel-exports.sh, enforce-dependency-rule.sh, enforce-gateway-port-purity.sh, enforce-presenter-class.sh, protect-main-branch.sh, pre-commit-gate.sh, verify-spec-updated.sh, protect-main-push.sh and require-spec.sh (9…

lowtidebuild/contract-review

Hook Claude Code

Runs before the agent uses a tool for Write, Edit, MultiEdit, NotebookEdit and Bash tool calls, executing pretooluse-guard.py via python3. From lowtidebuild/contract-review.

railyard-dev/railguard

Hook

Runs before the agent uses a tool, running railguard hook --event PreToolUse. From railyard-dev/railguard.

OrcaQubits/agentic-commerce-skills-plugins

Hook

Runs after a tool call finishes for Write and Edit tool calls, executing check_secrets.py via python. From OrcaQubits/agentic-commerce-skills-plugins.

adrian-d-hidalgo/nestjs-mcp-server

Hook Claude Code

Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit and NotebookEdit tool calls, executing block-destructive.py and write-boundary.py via python3 (2 commands). From adrian-d-hidalgo/nestjs-mcp-server.

TrueCrimeDev/ahk-mcp

Hook Claude Code

Runs before the agent uses a tool for mcp__, mcp__gemini and Task tool calls, executing mcp-security-scan.sh, gemini-context-injector.sh and subagent-context-injector.sh via bash (3 commands). From TrueCrimeDev/ahk-mcp.

theafh/ai-modules

Hook

Runs before the agent uses a tool for Edit, Write, apply_patch and Bash tool calls, executing charter_guardrail.sh (3 commands). From theafh/ai-modules.

netresearch/security-audit-skill

Hook

Runs before the agent uses a tool for Bash tool calls, executing check_risky_command.py via python3. From netresearch/security-audit-skill.

fedec65/bettercallclaude

Hook

Runs before the agent uses a tool for Write, Edit, MultiEdit, Bash, WebFetch and mcp__.* tool calls, executing privacy-check.js via node. From fedec65/bettercallclaude.

tuan3w/obsidian-vault-agent

Hook

Runs before the agent uses a tool for Write, Edit, Write, Edit and Bash tool calls, executing protect-templates.sh and protect-obsidian.sh (2 commands). From tuan3w/obsidian-vault-agent.

skarn-security/agent-guard

Hook

Runs when the agent asks permission for an action for Bash, WebFetch, WebSearch, Write, Edit, MultiEdit, NotebookEdit and mcp__.* tool calls, running skarn guard --agent claude --guard-mode audit. From skarn-security/agent-guard.

skarn-security/agent-guard

Hook

Runs when you submit a prompt, before the agent sees it, running skarn guard --guard-mode audit. From skarn-security/agent-guard.

ScientiaCapital/skills

Hook Claude Code

Runs before the agent uses a tool for Write, Edit, Bash, mcp__claude_ai_Apollo_io__apollo_contacts_create, mcp__claude_ai_Apollo_io__apollo_emailer_campaigns_add_contact_ids and mcp__claude_ai_Clay__find-and-enrich-contacts-at-company tool calls, running an inline shell check. From ScientiaCapital/skills.

tdwhere123/do-it

Hook

Runs before the agent uses a tool for Bash tool calls, executing strict-external-actions.sh (7 commands). From tdwhere123/do-it.

recomposesh/recompose

Hook Claude Code

Runs before the agent uses a tool for Edit, Write, Bash, Edit, Write and NotebookEdit tool calls, executing launch-gate.mjs via node (3 commands). From recomposesh/recompose.

JeongJaeSoon/agent-guard

Hook

Runs before the agent uses a tool for Write, Edit, MultiEdit, NotebookEdit, Read, NotebookRead, Grep, Glob, Bash, WebFetch, WebSearch, apply_patch and mcp__.* tool calls, running an inline shell check. From JeongJaeSoon/agent-guard.