Security hooks

482 tagged Security, measured the same way as everything else here.

Browse within: ai-security 14hooks 13agent-memory 9agentic 9agentic-workflow 9code-quality 9codex-cli 9gemini-cli-extension 8Guardrails 7Multi-Agent 7ai-governance 7gemini 7gemini-cli 7plugin 7

PostToolUse

193

timothywarner-org/ai901-cert-buddy-claude

Hook Claude Code

Runs after a tool call finishes for mcp__ai901buddy-mslearn__.* tool calls, executing citation-audit.py via python. From timothywarner-org/ai901-cert-buddy-claude.

9 2mo ago A tokens not measured original MIT

PreToolUse

194

huzaifa525/claude-code-optimizer

Hook Claude Code

Part of claude-code-optimizer

Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing protect-files.sh and block-dangerous.sh via bash (2 commands). From huzaifa525/claude-code-optimizer.

9 5mo ago A tokens not measured original MIT

PreToolUse

195

leMaur/livewire-flux-mcp

Hook Claude Code

Runs before the agent uses a tool for Edit tool calls, running an inline shell check. From leMaur/livewire-flux-mcp.

9 6d ago A tokens not measured original MIT

PreToolUse

196

gitmem-dev/gitmem

Hook

Part of gitmem-hooks

Runs before the agent uses a tool for Bash, Read, Write and Edit tool calls, executing credential-guard.sh and recall-check.sh via bash (5 commands). From gitmem-dev/gitmem.

9 24d ago A tokens not measured original MIT

PreToolUse

197

benshapyro/cadre-devkit-claude

Hook

Part of cadre-devkit-claude

Runs before the agent uses a tool for Bash, Edit, Write and Read tool calls, executing dangerous-command-blocker.py and sensitive-file-guard.py (2 commands). From benshapyro/cadre-devkit-claude.

9 9mo ago A tokens not measured original MIT

PreToolUse

201

ScopeBlind/scopeblind-gateway

Hook

Part of protect-mcp

Runs before the agent uses a tool, running curl -s -X POST http://127.0.0.1:9377/hook -H 'Content-Type:. From ScopeBlind/scopeblind-gateway.

9 1mo ago B tokens not measured fork MIT

PreToolUse

202

whenpoem/aiscientist

Hook Claude Code

Runs before the agent uses a tool for Read, Write, Edit, Bash and Bash tool calls, executing leakage_guard.py and destructive_bash_guard.py via uv with --no-sync (2 commands). From whenpoem/aiscientist.

8 1mo ago A tokens not measured original MIT

PreToolUse

203

MrBinnacle/azimuth

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing validate-azimuth.sh via bash. From MrBinnacle/azimuth.

8 2mo ago A tokens not measured original MIT

PreToolUse

205

QBall-Inc/the-bulwark

Hook

Part of the-bulwark

Runs before the agent uses a tool for Read, Edit and Bash tool calls, executing bulwark-permission-hook.sh. From QBall-Inc/the-bulwark.

8 3d ago A tokens not measured original MIT

PreToolUse

206

geniro-io/geniro-claude-harness

Hook

Part of geniro

Runs before the agent uses a tool for Bash tool calls, executing block-force-push.sh and block-secret-commit.sh (2 commands). From geniro-io/geniro-claude-harness.

8 3d ago A tokens not measured copy · 66% Apache-2.0

PreToolUse

207

Sungmin-Cho/deep-suite

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing denylist-guard.sh (13 commands). From Sungmin-Cho/deep-suite.

8 3d ago E tokens not measured original MIT

PreToolUse

208

plinde/claude-plugins

Hook

Part of github-webfetch-blocker

Runs before the agent uses a tool for WebFetch and Bash tool calls, executing block-github-webfetch.sh and suggest-gh-subcommands.sh (2 commands). From plinde/claude-plugins.

8 3mo ago A tokens not measured

PostToolUse

209

evolplus/talos

Hook

Part of talos

Runs after a tool call finishes for Bash tool calls, running node. From evolplus/talos.

8 29d ago A tokens not measured original Apache-2.0

BeforeTool

210

Benknightdark/neo-skills

Hook

Runs on the BeforeTool event, executing secret-guard.js via node. From Benknightdark/neo-skills.

7 3d ago A tokens not measured original MIT

PreToolUse

211

cdeust/zetetic-team-subagents

Hook

Part of zetetic-team-subagents

Runs before the agent uses a tool for Read, Bash, Grep, Edit, Write, NotebookEdit, Bash, Bash, Bash, Edit, Write, Edit, Write, Edit and Write tool calls, executing run-python.sh, pre-commit-zetetic.sh, pre-push-review.sh, pre-push-provenance.sh, pre-edit-layer-check.sh and pre-tool-claim-gate.sh (7 commands). From…

7 11d ago A tokens not measured original MIT

MessageDisplay

212

steve-magne/hookstack

Hook Claude Code

Runs when a message is displayed, executing message-display-redact-secrets.mjs and message-display-redact-pii.mjs via node (2 commands). From steve-magne/hookstack.

7 9d ago A tokens not measured original MIT

PreToolUse

213

lx-wnk/Agent-Context

Hook Claude Code

Runs before the agent uses a tool for Write, Edit and MultiEdit tool calls, executing pre-protect-secrets.sh. From lx-wnk/Agent-Context.

7 14d ago A tokens not measured original MIT

PostToolUse

214

cfgaudit/cfgaudit

Hook

Part of cfgaudit

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From cfgaudit/cfgaudit.

7 6d ago A tokens not measured original Apache-2.0

PreToolUse

215

wookiya1364/scv-claude-code

Hook

Part of scv

Runs before the agent uses a tool for Skill, Bash, Write, Edit, MultiEdit and NotebookEdit tool calls, executing guard.sh (3 commands). From wookiya1364/scv-claude-code.

7 5d ago A tokens not measured original MIT

PreToolUse

216

andreasasprou/agent-skills

Hook

Part of safety-net

Runs before the agent uses a tool for Bash tool calls, executing safety-net.js via bun. From andreasasprou/agent-skills.

7 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: