Skip to main content
skill CX Codex

permission-tuner — Claude Code skill: configure permissions

The permission-tuner skill reads permission prompts and auto mode denials from your session logs, then suggests permission rules and autoMode entries to reduce interruptions.

MIT ★ 2,966 updated 2026-09-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow
Open on GitHub

What permission-tuner does

permission-tuner scans your project's denial logs and identifies which permissions can be safely granted upfront and which benefit from autoMode tuning. The skill checks all settings files (global, project, local), categorizes denial types (permission-rule, automode-blocked, user-rejected), and recommends specific changes: remove ask rules you always approve; add autoMode.environment entries for trusted repositories and services; add autoMode.allow entries for routine operations.

Inside is a bash script that collects data from ~/.claude/settings.json, local files, and denial history; a symptom-to-fix table; a JSON template with example allow, ask, and deny rules; and a report estimating how many prompts you'll save per session. The skill never writes to project settings—only presents changes for your review.

What it helps with

  • Cut permission prompts without making auto mode blindly allow unsafe operations
  • Identify which ask rules block routine work and how to restructure them
  • Add trusted environments (repositories, registries) to autoMode without manual mapping
  • Spot hook and rule false positives that flag safe commands as risky

Example prompts for the agent

  • Review the last 50 sessions of permission denials and suggest rules for permission-tuner
  • Add autoMode permissions for npm commands I approve in every project
  • Check why auto mode prompts on git push to my personal repo and fix it

How to install permission-tuner

1Plugin marketplace

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

This installs the whole pro-workflow plugin with all its skills

2Skills CLI (Vercel)

npx skills add rohitg00/pro-workflow --skill permission-tuner -a claude-code

3Manually: put the files in place

~/.claude/skills/permission-tuner/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/permission-tuner/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about permission-tuner

How do I install permission-tuner in Claude Code?

Run /plugin marketplace add rohitg00/pro-workflow, then /plugin install pro-workflow@pro-workflow. Alternatively, use npx skills add rohitg00/pro-workflow --skill permission-tuner -a claude-code. Then open ~/.claude/skills/permission-tuner/SKILL.md.

What does permission-tuner do?

The skill reads permission denial logs from your projects and proposes rule changes so auto mode interrupts less. It does not modify settings itself—only shows what to add or remove.

What's the difference between an ask rule and autoMode.allow?

An ask rule always triggers a prompt, even in auto mode. autoMode.allow lets the classifier grant permission without prompting, subject to other conditions. The skill recommends replacing ask rules with autoMode entries for permissions you always approve.

Source text

SKILL.md · MIT
---
name: permission-tuner
description: Analyze permission prompts and auto mode denials, then generate permission rules and autoMode entries that cut prompt fatigue. Use when prompts keep interrupting, auto mode falls back to prompting, or after sessions with many denials.
user-invocable: true
---

# Permission Tuner

Reduce permission prompts by fixing their causes, not by piling up rules.

## Trigger

Use when:
- Permission prompts interrupt flow repeatedly
- Auto mode keeps blocking routine work or falls back to prompting everything
- Starting a new project and want to configure permissions

## How Prompts Happen

- Rules resolve first: deny > ask > allow. A matching ask rule prompts even in auto mode, and a PreToolUse hook returning `allow` cannot override it.
- In auto mode, anything no rule resolves goes to a classifier. After 3 blocks in a row or 20 in a session, auto mode pauses and prompts for everything until you approve one.
- Auto mode drops broad allow rules: `Bash(*)`, wildcarded interpreters like `Bash(node *)`, package-manager run commands, `Agent`, and `Monitor`.
- Hooks that exit 2 on harmless commands count as denials and push the session toward that fallback.

## Workflow

### Step 1: Gather data

Rules merge across scopes, so check every file that exists, not only the user file. `/permissions` shows the rules Claude Code actually loaded, and `claude auto-mode config` shows the effective `autoMode` (the classifier ignores `autoMode` in `.claude/settings.local.json`).

```bash
for f in ~/.claude/settings.json .claude/settings.json .claude/settings.local.json; do
  [ -f "$f" ] && jq --arg f "$f" '{file: $f, mode: .permissions.defaultMode, allow: (.permissions.allow|length), ask: (.permissions.ask|length), deny: (.permissions.deny|length), autoMode: (.autoMode != null)}' "$f"
done
claude auto-mode config
ls -t ~/.claude/projects/*/*.jsonl | head -20 | xargs grep -ho '"toolDenialKind":"[^"]*"' | sort | uniq -c | sort -rn
```

`toolDenialKind` values seen in transcripts (undocumented, may change): `permission-rule` (rule or hook), `automode-blocked` (classifier), `automode-parsing-error` and `automode-unavailable` (no verdict, not tunable), `user-rejected` (you said no).

### Step 2: Pick the right fix

| Symptom | Fix |
|---------|-----|
| Prompt on something you always approve | Remove or narrow the ask rule |
| `permission-rule` on a harmless command | Fix the hook false positive or narrow the deny rule |
| Classifier blocks work in your own repos, registries, local services | Add an `autoMode.environment` entry |
| Classifier blocks one routine pattern | Add an `autoMode.allow` entry |
| Want outward actions only when you asked | Add an `autoMode.soft_deny` entry |
| Want a human check every time | Keep a short `permissions.ask` rule |

### Step 3: Generate rules

```json
{
  "permissions": {
    "allow": [
      "Bash(git status)",
      "Bash(npm test)",
      "Bash(npm run lint)"
    ],
    "ask": [
      "Bash(git push --force*)",
      "Bash(git push * main)",
      "Bash(git push * main *)",
      "Bash(git push *:main)",
      "Bash(git push *:main *)",
      "Bash(git push * master)",
      "Bash(git push * master *)",
      "Bash(git push *:master)",
      "Bash(git push *:master *)",
      "Bash(gh pr merge *)",
      "Bash(npm publish*)"
    ],
    "deny": [
      "Bash(rm -rf *)",
      "Read(**/.env)",
      "Read(**/.env.*)"
    ]
  },
  "autoMode": {
    "environment": [
      "$defaults",
      "Source control: repositories under github.com/your-org are trusted; feature-branch pushes are routine."
    ],
    "allow": ["$defaults"],
    "soft_deny": [
      "$defaults",
      "Merging a pull request needs the user's approval for that specific merge."
    ]
  }
}
```

`autoMode` only takes effect in `~/.claude/settings.json`, managed settings, or `--settings`. Keep `"$defaults"` in each list. Check the result with `claude auto-mode config` and review custom rules with `claude auto-mode critique`.

## Output

```text
PERMISSION TUNER REPORT

Mode: [mode]   Rules: [X] allow, [Y] ask, [Z] deny   autoMode: [yes/no]
Denials: [n] permission-rule, [n] classifier, [n] no verdict, [n] you rejected

Remove (ask rules you always approve):
  - Bash(...) -- approved [n]x

Add to autoMode.environment:
  + "..." -- clears [n] blocks

Add to autoMode.allow / soft_deny:
  + "..."

Fix hooks:
  ! [script] blocked [n] harmless commands

Keep asking:
  ~ force push, merge, publish, deploy

Estimated prompts saved per session: ~[N]
```

## Rules

- Prefer `autoMode` entries over new ask rules
- Destructive operations stay in deny or ask
- Always present changes for user approval before applying
- Never write `autoMode` into project settings
- Include estimated prompt savings

© Rohit Ghumare · MIT · rohitg00/pro-workflow

Similar skills

All skills for Agent setup: memory, context, orchestration →
permission-auditor UseAI-pro permission-auditor — a skill for Claude Code, Codex, Cursor and other platforms: checks what permissions another skill requests, explains risks and suggests minimal access. Runs before installing a new skill. CX Codex +1 477installs dx-org-permission-set-assign forcedotcom dx-org-permission-set-assign assigns Salesforce permission sets to org users via sf org assign permset. Handles default admins, target org aliases, and batch assignments. CX Codex +1 5,900installs applying-a-permission-policy mvschwarz applying-a-permission-policy is a Claude Code skill that sets OpenRig permissions before a team launch. It activates during command-permission setup or when native approval prompts interrupt work. CX Codex +1 ★ 8,928repo stars permission-check pedrohcgs permission-check diagnoses why Claude Code asks for approval or ignores bypass mode. It checks project and global configuration layers without editing files. CX Codex +1 ★ 1,729repo stars service-omni-supervisor-permset-assign forcedotcom service-omni-supervisor-permset-assign — a skill for Claude Code that automates assigning the ContactCenterSupervisor permission set to users. Runs a verification and assignment script for Salesforce supervisor provisioning. CX Codex +1 102installs geofeed-tuner official Sid Mathur geofeed-tuner is a GitHub Copilot skill that validates and refines CSV IP geolocation feeds against RFC 8805 for network operators and cloud providers publishing geofeeds. CX Codex +1 1,300installs

From the same set83

The whole set →
wiki wiki is a Claude Code command that builds and maintains persistent research wikis. It stores markdown files, indexes them in SQLite FTS5, and retrieves context via BM25. CX Codex +1 ★ 2,966repo stars wiki-viewer wiki-viewer writes a pro-workflow wiki out as a single HTML file with pages, sources, claims, a seed queue, a link graph and search. Useful for handing research state to someone else. CX Codex +1 ★ 2,966repo stars llm-council llm-council runs multi-model deliberation in three stages: parallel drafts, anonymous peer rankings, and final synthesis by a designated chairman. CX Codex +1 ★ 2,966repo stars design-engineering The design-engineering skill guides interface animation choices and UI reviews. Use it when refining a component, transition, modal, or other interactive state. CX Codex +1 ★ 2,966repo stars batch-orchestration batch-orchestration decomposes large codebase changes into independent units and runs parallel agents in isolated git worktrees. CX Codex +1 ★ 2,966repo stars insights insights turns your pro-workflow history into numbers: edits per session, rules you actually apply, mistakes that keep coming back. Useful when you want to see where the agent keeps slipping. CX Codex +1 ★ 2,966repo stars doctor doctor scans your pro-workflow and Claude Code setup: checks hooks, database, context usage, MCP servers, and git state. Spots broken hook scripts and settings conflicts before they cause problems. CX Codex +1 ★ 2,966repo stars thoroughness-scoring thoroughness-scoring rates implementation choices from 1 to 10 and prompts the agent to pick thorough solutions with tests and typing over brittle shortcuts. CX Codex +1 ★ 2,966repo stars

Project sponsors

Companies that keep this analytics open