agentmods.dev

PreToolUse

A pre-tool hook configuration that runs checks before the agent writes or edits files or executes Bash commands. It checks file-write safety with a prompt and validates Bash commands with a shell script.

In plain words
What is it for?
Controlling Write, Edit, and Bash tool calls in Claude Code through pre-action safety and command-validation hooks.
Why use it?
It adds a safety gate before potentially risky tool actions. The provided checks specifically look for path traversal and sensitive-file access and validate Bash commands.

Hook

2 yesterday A scan tokens not measured original MIT
View the source file imbflool/cc-plugin-eval
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/imbflool/cc-plugin-eval/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/imbflool/cc-plugin-eval
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 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.

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.

tests/fixtures/valid-plugin/hooks/hooks.json · 24 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Write|Edit",
      "hooks": [
        {
          "type": "prompt",
          "prompt": "Validate file write safety. Check for path traversal and sensitive files. Return 'approve' or 'deny'.",
          "timeout": 30
        }
      ]
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "bash ${CLAUDE_PLUGIN_ROOT}/scripts/validate-bash.sh",
          "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. yesterday First seen · 24 lines scan A 1e6f55b579e8

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository imbflool/cc-plugin-eval (2 stars, last pushed yesterday), 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.

Data and AITestingai-testinganthropicclaudeclaude-agent-sdkclaude-codecli
Related

Other hooks, from other repositories

PostToolUse

Runs after a tool call finishes, running an inline shell check. From goondocks-co/open-agent-kit.

goondocks-co/open-agent-kit · not measured

Stop

Runs when the agent finishes a response, running an inline shell check. From goondocks-co/open-agent-kit.

goondocks-co/open-agent-kit · not measured

SessionEnd

Runs when a session ends, running an inline shell check. From goondocks-co/open-agent-kit.

goondocks-co/open-agent-kit · not measured

SubagentStart

Runs when a subagent starts, running an inline shell check. From goondocks-co/open-agent-kit.

goondocks-co/open-agent-kit · not measured

SubagentStop

Runs when a subagent finishes, running an inline shell check. From goondocks-co/open-agent-kit.

goondocks-co/open-agent-kit · not measured

Stop

Runs when the agent finishes a response, executing guardrail-e2e-gate.sh, guardrail-terminal-gate.sh, guardrail-watch-gate.sh, guardrail-walkthrough-gate.sh, guardrail-comment-reply-gate.sh, guardrail-stage-gate.sh, guardrail-debug-path-gate.sh and guardrail-capability-claim.sh via bash (8 commands). From…

multiplex-ai/muggle-ai-works · not measured