lev-os/agents/authorize

Claude Code and agent skill by lev-os/agents

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Manage persistent allowlist for pre_tool_use hook bypass

Install

npx vskill@latest install lev-os/agents/authorize

SKILL.md

The same SKILL.md was published earlier as majiayu000/claude-skill-registry-data/authorize.

Authorize

Manage the persistent allowlist at ~/.claude/authorized-paths.txt that bypasses pre_tool_use.py security checks.

Commands

CommandAction
/authorize add <pattern>Add path pattern to allowlist
/authorize remove <pattern>Remove pattern from allowlist
/authorize listShow current allowlist
/authorize clearClear all authorized paths

Usage

bash
# Allow a specific file
/authorize add ~/.secrets/api-keys.json
# Allow a directory pattern
/authorize add ~/.config/myapp/*
# Allow by extension
/authorize add *.local
# Remove authorization
/authorize remove ~/.secrets/api-keys.json
# View all authorized paths
/authorize list

Implementation

When user invokes /authorize:

add <pattern>
bash
echo "<pattern>" >> ~/.claude/authorized-paths.txt
sort -u ~/.claude/authorized-paths.txt -o ~/.claude/authorized-paths.txt

Confirm: "✓ Added <pattern> to authorized paths"

remove <pattern>
bash
grep -v "^<pattern>$" ~/.claude/authorized-paths.txt > /tmp/auth.tmp
mv /tmp/auth.tmp ~/.claude/authorized-paths.txt

Confirm: "✓ Removed <pattern> from authorized paths"

list
bash
cat ~/.claude/authorized-paths.txt 2>/dev/null || echo "(empty)"

Display as formatted list.

clear
bash
rm -f ~/.claude/authorized-paths.txt

Confirm: "✓ Cleared all authorized paths"

Pattern Matching

The hook uses these matching rules:

  • Exact match: /path/to/file.txt
  • Glob patterns: *.local, ~/.config/*
  • Directory prefix: /path/to/dir/ (trailing slash = all children)

Security Notes

  • Authorizations persist across sessions
  • Review periodically with /authorize list
  • Use narrow patterns (specific files > broad globs)
  • .env files have built-in allowlist in hook (.env.local, .env.sample, .env.example)

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/lev-os/agents/authorize/badge)](https://verified-skill.com/skills/lev-os/agents/authorize)

Something wrong with this skill or its page? Tell us.