pre-tool-use-hook avatar

pre-tool-use-hook

Pre-tool-use hook for Claude Code that intercepts CLI commands and prompts for approval before executing modifying operations

PluginDeveloperTerminalAI ModelsTerminal / Shell
Verification
L1 · Found
Risk
Pending
Health
Active
Trust
Unrated

Install verification: No L4/L5 install test yet

L1–L5 verification rules

What it does

Pre-tool-use hook for Claude Code that intercepts CLI commands and prompts for approval before executing modifying operations

Installation

dsh plugin --profile web add github:fghxu/pre-tool-use-hook

Install method: GitHub · no verification record (L1-L5)

Verification & Compatibility

No verification record yet for this plugin.

  • • Node.js: not stated
  • • DSH: not stated
  • • External credentials: none detected

Author badges

Embed the official badges in your README to showcase security & install-test status:

dsh.so risk
`[![dsh.so risk](https://www.dsh.so/badge/pre-tool-use-hook.svg)](https://www.dsh.so/artifact/pre-tool-use-hook/)`

Security Report

Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.

pre-tool-use-hookAutomated review · daily

Static n/a, dynamic no conclusion — stricter wins → overall low.

no static verdict→dynamic no conclusion→overall low
0 critical·— files scanned
lowoverall · low
1static scandeterministic rules · no code execution · shape only
plugin version—
scanned version—
current versiond45040a49305

The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.

2model reads redacted source context · never executes plugin code

not in the dynamic queue (queue only covers plugins static-flagged at warn or above) — this does not mean the dynamic audit found it safe.

Rule: the dynamic audit can only raise risk, never lower it (raise-only, never an exemption); a wrong raise is withdrawn by human review and the tier falls back to the static verdict. Overall verdict = the stricter of the two layers.

Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.

Activity

Last commit 2026-10-20 · activity: Active

• Repo created: 2026-04-23

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/fghxu/pre-tool-use-hook

Was this page helpful?