agentmods.dev

PreToolUse

A group of hooks that runs state tracking before tool use, checks for secrets before file edits, and screens shell commands for dangerous patterns.

In plain words
What is it for?
Use it as a project-wide preflight layer for Write, Edit, and Bash calls.
Why use it?
It adds automatic checks around edits and commands to help prevent secret exposure and destructive operations.

Hook

11 16d ago A scan tokens not measured copy · 80% MIT
View the source file pillip/claude-dev-kit
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/pillip/claude-dev-kit/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/pillip/claude-dev-kit
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 80% copy Near-identical to another mod 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.

Origin

This is a copy

80% identical to SubagentStart — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

hooks/hooks.json · 31 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "*",
      "hooks": [
        {
          "type": "command",
          "command": "bash -c '[ -f \"$CLAUDE_PLUGIN_ROOT/project/.claude/hooks/agent_state.py\" ] && HOOK_ROOT=\"$CLAUDE_PROJECT_DIR\" python3 \"$CLAUDE_PLUGIN_ROOT/project/.claude/hooks/agent_state.py\" || true'"
        }
      ]
    },
    {
      "matcher": "Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "bash -c '[ -f \"$CLAUDE_PLUGIN_ROOT/project/.claude/hooks/secret_guard.py\" ] && python3 \"$CLAUDE_PLUGIN_ROOT/project/.claude/hooks/secret_guard.py\" || true'"
        }
      ]
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "bash -c '[ -f \"$CLAUDE_PLUGIN_ROOT/project/.claude/hooks/dangerous_command_guard.py\" ] && python3 \"$CLAUDE_PLUGIN_ROOT/project/.claude/hooks/dangerous_command_guard.py\" || true'"
        }
      ]
    }
  ]
}
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 · 31 lines scan A ad41e70f0fc5

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d 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. It is 80% identical to SubagentStart, differing in 20 lines, and is treated as a copy.

Code Generationai-agentsautonomous-codingclaudeclaude-codedeveloper-tools
Related

Other hooks, from other repositories

SessionStart

Runs when a session starts, executing session-start.sh via bash. From darrenhinde/OpenAgentsControl.

darrenhinde/OpenAgentsControl · not measured

PostToolUse

Runs after a tool call finishes for Write and Edit tool calls, executing dsp-track-write.sh. From k-kolomeitsev/data-structure-protocol.

k-kolomeitsev/data-structure-protocol · not measured

Stop

Runs when the agent finishes a response, running an inline shell check. From mits-pl/wove.

mits-pl/wove · not measured

SessionStart

Runs when a session starts on startup, clear and compact, running an inline shell check. From voidvec/drogon-claude-plugin.

voidvec/drogon-claude-plugin · not measured

Stop

Runs when the agent finishes a response, running an inline shell check. From openplanr/planr-pipeline.

openplanr/planr-pipeline · not measured

SessionStart

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From baixinghao/intent-gate.

baixinghao/intent-gate · not measured