agentmods.dev

PreToolUse

A pre-action security hook that runs a Node.js script before Bash, Write, or Edit operations. Hooks are automatic checks triggered before an agent performs a specified action.

In plain words
What is it for?
Use it to run security-guard.js before shell commands and file-writing or editing actions in the configured agent environment.
Why use it?
It adds a security check before commands or file changes are allowed to run. The excerpt does not explain what the check itself looks for.

Hook

5.3k 5d ago A scan tokens not measured original MIT
View the source file Galaxy-Dawn/claude-scholar
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/galaxy-dawn/claude-scholar/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholar
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.

hooks/hooks.json · 14 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Bash|Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "node ${CLAUDE_PLUGIN_ROOT}/hooks/security-guard.js",
          "timeout": 5
        }
      ]
    }
  ]
}
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 · 14 lines scan A 762e0a7fc80b

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository Galaxy-Dawn/claude-scholar (5,260 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 A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ResearchSecurityWriting and docsacademic-researchai-agentsclaudeclaude-codedeveloper-toolsmcp
Related

Other hooks, from other repositories

PostToolUse

Runs after a tool call finishes for Write and Edit tool calls, executing post_edit_ref_check.py and post_edit_sota_check.py via python3 (2 commands). From roomi-fields/paper-trail.

roomi-fields/paper-trail · not measured

PostToolUse

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check (2 commands). From Agentic-Assets/corbis-literature-starter-kit.

Agentic-Assets/corbis-literature-starter-kit · not measured

PostToolUse

Runs after a tool call finishes for @dialogical-coder, /qual-synthesize, /qual-advance-stage, /qual-complete-stage1, /qual-parallel-streams, /qual-synthesize, /qual-characterize-patterns and @dialogical-coder tool calls, executing interpretive-pause.js, check-coherence.js, generate-audit-trail.js and…

linxule/interpretive-orchestration · not measured

PreToolUse

Runs before the agent uses a tool for Write, Edit, MultiEdit and Bash tool calls, executing ars_write_scope_guard.py via python3. From zi-yue-1129/research-lab-skills.

zi-yue-1129/research-lab-skills · not measured

PreToolUse

Runs before the agent uses a tool for @dialogical-coder, /qual-parallel-streams, /qual-synthesize, /qual-code-deductive and /qual-characterize-patterns tool calls, executing check-stage1-complete.js via node. From linxule/interpretive-orchestration.

linxule/interpretive-orchestration · not measured

SessionEnd

Runs when a session ends, executing session-reflect.js via node. From linxule/interpretive-orchestration.

linxule/interpretive-orchestration · not measured