agentmods.dev

BeforeTool

BeforeTool is a hook for Claude Code from GigantesHJI/securedact-mcp. Its token cost is not measured, scanned A, original, Apache-2.0.

A safety hook that runs before selected tool calls, including web requests, file changes, shell commands, and text searches. It invokes a Python security check before the tool runs.

In plain words
What is it for?
Use it to enforce security checks around commands that access the web, change files, run Bash, or search project contents.
Why use it?
It adds a checkpoint that can inspect or block risky tool activity before it takes place.

Hook for Claude Code

Written for Claude Code: a Claude Code hooks.json. Also seen: names the NotebookEdit tool.

One of 6 entries in hooks.json — they are configured in one file and arrive together.

not rated 2repo +1 today A scan tokens not measured original Apache-2.0

Good fit Use it to enforce security checks around commands that access the web…

Compare 6 hooks from other repositories ↓
Install with agentmods
npx agentmods add hooks/giganteshji/securedact-mcp/before-tool
View source ↗ GigantesHJI/securedact-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/GigantesHJI/securedact-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for BeforeTool

README.md
[![agentmods](https://agentmods.dev/badge/hooks/giganteshji/securedact-mcp/before-tool.svg)](https://agentmods.dev/hooks/giganteshji/securedact-mcp/before-tool)
Your own site
<a href="https://agentmods.dev/hooks/giganteshji/securedact-mcp/before-tool"><img src="https://agentmods.dev/badge/hooks/giganteshji/securedact-mcp/before-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

BeforeTool scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

hooks/hooks.json · 15 lines

What it actually says

{
  "BeforeTool": [
    {
      "matcher": "^(mcp_.*|.*(http|web|search|fetch|request|api|connect).*|Read|Write|Edit|MultiEdit|NotebookEdit|Bash|Grep|Glob)$",
      "hooks": [
        {
          "name": "securedact-before-tool",
          "type": "command",
          "command": "python -m securedact_enforced.gemini_hook --event BeforeTool",
          "timeout": 20000
        }
      ]
    }
  ]
}
Same file

What else hooks.json configures

This page is one entry in a file that holds 6. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 15 lines scan A 53e89843d22e

Subscribe to this mod's changes

BeforeTool is a hook published in the GitHub repository GigantesHJI/securedact-mcp (2 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Codeai-securityclaudedata-protectiongeminigemini-cli-extension
Related

Other hooks, from other repositories

AfterAgent

Runs on the AfterAgent event, executing phase-gate.js and ralph-retry.js via node (2 commands). From richardcb/oh-my-gemini.

richardcb/oh-my-gemini · not measured

SessionStart

Runs when a session starts on startup, executing session-start.js via node. From richardcb/oh-my-gemini.

richardcb/oh-my-gemini · not measured

BeforeAgent

Runs on the BeforeAgent event, executing before-agent.js via node. From richardcb/oh-my-gemini.

richardcb/oh-my-gemini · not measured

BeforeTool

Runs on the BeforeTool event for write_file, replace, run_shell_command and shell tool calls, executing before-tool.js via node. From richardcb/oh-my-gemini.

richardcb/oh-my-gemini · not measured

AfterTool

Runs on the AfterTool event for write_file and replace tool calls, executing after-tool.js via node. From richardcb/oh-my-gemini.

richardcb/oh-my-gemini · not measured

BeforeToolSelection

Runs on the BeforeToolSelection event, executing tool-filter.js via node. From richardcb/oh-my-gemini.

richardcb/oh-my-gemini · not measured