Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From claude-perms
Analyze Claude Code permission usage patterns and generate commands to apply frequently-used permissions
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-perms:permsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Launches a TUI to analyze permission usage across your Claude Code sessions.
Launches a TUI to analyze permission usage across your Claude Code sessions.
Run the TUI:
~/.claude/plugins/cache/b-open-io/claude-perms/*/bin/perms
| Key | Action |
|---|---|
j/k or ↓/↑ | Navigate list |
Enter | Open apply modal for selected permission |
Tab | Switch between Frequency/Matrix views |
/ | Filter permissions |
u | Copy user-level apply command |
p | Copy project-level apply command |
Esc | Close modal / clear filter |
q | Quit |
The analyzer reads from:
~/.claude/projects/*/sessions-index.json)~/.claude/settings.local.json).claude/settings.local.json)When you select a permission and press u or p, the tool copies a command to add that permission to either:
~/.claude/settings.local.json): Applies across all projects.claude/settings.local.json): Applies only to current projectnpx claudepluginhub b-open-io/claude-plugins --plugin claude-permsExtracts safe Bash commands from Claude Code session history and auto-updates settings.json allowlist to minimize permission prompts.
Analyzes permission denial patterns and generates optimized alwaysAllow and alwaysDeny rules to reduce prompt fatigue.
Reviews, summarizes, and edits opencode permission configs including always-allow lists, skill permissions, and wildcard patterns. Recommends safe read-only commands for auto-approval and audits for security.