agentmods.dev

PreToolUse

A pre-tool hook that runs a guard script before the agent uses Bash commands. Hooks are automatic checks that run around agent actions.

In plain words
What is it for?
Running the project’s pre-Bash safety check before command-line tool calls.
Why use it?
It lets the project check or restrict shell commands before they execute.

Hook for Claude Code

96k +21 today A scan tokens not measured no licence
View the source file oven-sh/bun
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/oven-sh/bun/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/oven-sh/bun

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 A 0 findings. Scan, not verified.
Origin unknown 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.

.claude/settings.json · 13 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 13 lines scan A 07e9c6209d6d

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository oven-sh/bun (95,832 stars, last pushed today), with no licence file. 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.

bunbundlerjavascriptjavascriptcorejsxnodejs
Related

Other hooks, from other repositories

SessionStart

Runs when a session starts, executing nvm-path.sh via bash. From TryGhost/Ghost.

TryGhost/Ghost · not measured

PreToolUse

Runs before the agent uses a tool for Glob and Grep tool calls, running an inline shell check. From karmacircleCommunity/KarmaCircle.

karmacircleCommunity/KarmaCircle · not measured

SessionStart

Runs when a session starts, running an inline shell check. From karmacircleCommunity/KarmaCircle.

karmacircleCommunity/KarmaCircle · not measured

PreToolUse

Runs before the agent uses a tool for Write, Edit, MultiEdit, NotebookEdit, Write, Edit, MultiEdit, Write, Edit, MultiEdit, NotebookEdit, Bash and Bash tool calls, executing require-worktree-for-edits.sh, block-raw-htmlelement.sh, block-prose-punctuation.sh, require-tests-with-src.sh, require-docs-with-src.sh…

webjsdev/webjs · not measured

PostToolUse

Runs after a tool call finishes for Write, Edit, MultiEdit, NotebookEdit and Bash tool calls, executing nudge-uncommitted.sh, cleanup-merged-worktree.sh and release-global-update.sh (3 commands). From webjsdev/webjs.

webjsdev/webjs · not measured

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing route-skills.sh. From webjsdev/webjs.

webjsdev/webjs · not measured