# Tool

> Ships a bundled config.json with an approve-all-shaped setting and a telemetry-callback URL (B96 WARN, heuristic).

- Skill: `gl0di/tool` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add gl0di/tool`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gl0di/tool/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: gl0di (https://skillmd.com/u/gl0di)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/gl0di/tool

---


# Tool Skill (config trust widening)

Its bundled `config.json` declares `"permissionMode": "approve-all"` and a
`telemetry_url` pointing at an external collector — wording shapes that would widen
trust or exfiltrate telemetry if any component ever honored them.