A command hook that runs before an agent uses a Bash command. It checks the command text for several destructive patterns and can block matching commands.

Inspecting Bash tool calls and stopping commands containing rm -rf, DROP TABLE, or --force.

It adds a safety check against commands such as deleting files or dropping database tables before they run.

PreToolUse — Hook by ambient-code

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/ambient-code/agentready/pre-tool-use

Clone the repo

git clone --depth 1 https://github.com/ambient-code/agentready

Made for: Claude Code.

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 C 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade C, and why

PreToolUse scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"command": "echo \"$CLAUDE_TOOL_INPUT\" | grep -qE 'rm -rf|DROP TABLE|--force' && echo 'BLOCK: destructive command' && exit 1 || true"

.claude/settings.json · 13 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "echo \"$CLAUDE_TOOL_INPUT\" | grep -qE 'rm -rf|DROP TABLE|--force' && echo 'BLOCK: destructive command' && exit 1 || 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.

yesterday First seen · 13 lines scan C 7f7d96899352

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository ambient-code/agentready (151 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review Languages ai-assisted-development assessment-tool code-quality python

PostToolUse

Runs after a tool call finishes for Write, Edit, Bash, Write, Edit, Bash, Read, Write, Edit, Glob, Grep, Task, Bash, Task, Edit, Write, Read and mcp__.* tool calls, executing envrc-guarded-source.sh, dispatch.cjs, tdd-red-failure-tracker.cjs, task-clear-model.cjs and json-toon-projector.cjs (7 commands). From…

nguyenthienthanh/aura-frog · not measured

PreToolUse

Getting it into your agent

Grade C, and why

Recursive force deletehighDestructive command

What it actually says

What this file has done since we first saw it

Other hooks, from other repositories

PostToolUse

SessionStart

Stop

UserPromptSubmit

SubagentStart

PreCompact