/permission-tuner

Analyze permission prompts and auto mode denials, then generate permission rules and autoMode entries that reduce prompt fatigue

BOOST

rohitg00@rohitg00

GitHub

From plugin

pro-workflow

2.9k23 skills8 agents23 commands22 hooks

> /plugin marketplace add rohitg00/pro-workflow
> /plugin install pro-workflow@pro-workflow

Command definition

permission-tuner.md

description: Analyze permission prompts and auto mode denials, then generate permission rules and autoMode entries that reduce prompt fatigue

/permission-tuner - Permission Optimization

Find out why Claude Code keeps prompting or denying, and fix the cause.

Quick Start

Run this command to: 1. Read your permission rules and `autoMode` config 2. Count denials by kind from recent session transcripts 3. Separate hook false positives, classifier blocks, and ask-rule prompts 4. Present recommended changes for your approval

What It Does

**Ask rules you always approve**: suggests removing them, since ask rules prompt even in auto mode
**Classifier blocks on routine work**: suggests `autoMode.environment` or `autoMode.allow` entries
**Hook false positives**: names the hook script that blocked harmless commands, since each block counts toward auto mode's fallback to prompts
**Dangerous operations**: keeps them in deny or ask

Usage

/permission-tuner

After running, review the suggested changes and apply the ones you want. `autoMode` entries belong in `~/.claude/settings.json`.

Read it on GitHub ↗

Stats

TypeScript JavaScript HTML Bash SQLite Git GitHub Markdown Anthropic OpenAI Gemini MCP

2,950

Stars

300

Forks

Maintained

Maintenance

JavaScript

Language

1mo ago

Last commit

9mo ago

Created

Repo: rohitg00/pro-workflow

Ships withpro-workflow

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

2.9k41 skills8 agents

Get the whole plugin

Stars on GitHub