agentmods.dev

PreToolUse

A pre-action hook that runs a Node.js mode check before the agent uses Write or Edit operations. It is part of the pi-delegate development workflow.

In plain words
What is it for?
Use it to enforce a mode rule before agents write to or edit project files.
Why use it?
It can stop file changes that do not match the current working mode before they are made. The input does not describe any other checks or behavior.

Hook

Part of the pi-delegate plugin — 9 skills, 3 hooks, 1 MCP server shipped together

2 9d ago A scan tokens not measured original MIT
View the source file LarryStanley/pi-delegate
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.

agentmods
npx agentmods add hooks/larrystanley/pi-delegate/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/LarryStanley/pi-delegate

Or install pi-delegate, the plugin that ships this one along with the rest of its 9 skills, 3 hooks, 1 MCP server.

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. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

PreToolUse 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 2d 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 · 14 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/mode-guard.mjs\"",
          "timeout": 10
        }
      ]
    }
  ]
}
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. 2d ago First seen · 14 lines scan A feb23568a4c4

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository LarryStanley/pi-delegate (2 stars, last pushed 9d ago), licensed MIT. 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.

agentic-aiai-agentsanthropicclaudeclaude-codeclaude-code-hooks
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit and NotebookEdit tool calls, executing run-python-hook.cmd. From karlkfi/claude-bouncer.

karlkfi/claude-bouncer · not measured

PreToolUse

Runs before the agent uses a tool, executing chrome-multi-instance-warn.sh via bash. From didvc/claude-chrome-multi-instance-warn.

didvc/claude-chrome-multi-instance-warn · not measured

PreToolUse

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.

frmoretto/hardstop · not measured

PreToolUse

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From Kanevry/session-orchestrator.

Kanevry/session-orchestrator · not measured

PreToolUse

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.

deepklarity/harness-kit · not measured

PostCompact

Runs after the context is compacted, running bar-hook PostCompact. From bar181/bar-observatory.

bar181/bar-observatory · not measured