configure-permissions

configure-permissions is a skill for Claude Code, Codex from ashray/claude-permissions-wizard. It costs 65 tokens per session (2,460 once invoked), scanned A, original, MIT.

An interactive setup wizard for Claude Code permission rules, which control when the agent may run actions without asking.

In plain words
What is it for?
Choosing a permission scope and preset, then saving the rules to Claude Code settings.
Why use it?
It helps reduce repeated approval prompts while keeping permission checks for potentially destructive commands.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Good fit Choosing a permission scope and preset, then saving the rules to Claude Code settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ashray/claude-permissions-wizard/configure-permissions
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ashray/claude-permissions-wizard --skill configure-permissions
Clone the repo
git clone --depth 1 https://github.com/ashray/claude-permissions-wizard

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for configure-permissions

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashray/claude-permissions-wizard/configure-permissions/github.svg)](https://agentmods.dev/skills/ashray/claude-permissions-wizard/configure-permissions)
Your own site
<a href="https://agentmods.dev/skills/ashray/claude-permissions-wizard/configure-permissions"><img src="https://agentmods.dev/badge/skills/ashray/claude-permissions-wizard/configure-permissions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for configure-permissions

Your own site · 80×15
<a href="https://agentmods.dev/skills/ashray/claude-permissions-wizard/configure-permissions"><img src="https://agentmods.dev/badge/skills/ashray/claude-permissions-wizard/configure-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Fable 5.1 · 7 Sept 2026 📄 Read the review
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02460
Opus 5 $0.00032 $0.01230
Sonnet 5 $0.00013 $0.00492
Haiku 4.5 $0.00006 $0.00246

Measured 10d ago against content hash 3605b45c19fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

configure-permissions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/configure-permissions/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configure Permissions Wizard

Interactive wizard that configures Claude Code permission rules. The goal: reach near-skip-permissions convenience while keeping a safety net for destructive commands.

Overview

This skill asks 2 questions for most users (scope + preset), then writes the permissions config. Only the "Custom" preset goes deeper with additional questions.

Permissions are written to a Claude Code settings JSON file. The skill deep-merges — it only replaces the permissions key and preserves everything else (model, env, skipDangerousModePermissionPrompt, etc.).

Round 1: Scope + Preset (always asked)

Question 1 — Scope

Ask the user where permissions should be saved. Use AskUserQuestion with these options:

Option File Description
All my projects ~/.claude/settings.json These permissions apply everywhere, across every repo
This project, for everyone .claude/settings.json Saved in the repo so teammates get the same permissions when they clone it
This project, just me .claude/settings.local.json Only affects you on this machine, invisible to teammates

Question 2 — Preset

Ask the user which preset to use. Use AskUserQuestion with these options:

Option Description
Balanced Dev (Recommended) Common dev tools allowed, destructive commands prompt before running
Full Trust Everything allowed, destructive commands still prompt before running
Read Only Read + web only, everything else prompts
Custom Configure each category yourself (more questions follow)

If a preset is chosen (not Custom): skip straight to writing the file. No more questions. This is the fast path.

Rounds 2-4: Custom Preset Only

Only proceed with these rounds if the user picked "Custom" in Q2.

Round 2 — Core Permissions (3 questions)

Q3 - File operations (multiselect):

  • Read
  • Edit
  • Write
  • NotebookEdit

Read the full file on GitHub · 224 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 224 lines · 65 tokens per session scan F 3605b45c19fb

Subscribe to this mod's changes

configure-permissions is a skill published in the GitHub repository ashray/claude-permissions-wizard (1 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 2,460 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

anatomia-cc

ES: Te dice qué construir en Claude Code y te da el esqueleto de archivos: skill y en qué modo, subagente, hook, servidor MCP, plugin, rutina, artefacto, app con el Agent SDK, una línea en CLAUDE.md, o nada. Corré esto antes del primer archivo. Se dispara con «esto lo hago como skill o como agente», «necesito un MCP o…

Hainrixz/claude-anatomy · 267 tokens

diagrammer

Render a clean blueprint-style SVG diagram from a JSON spec. Use when the user asks to draw, sketch, or diagram a flow, neural net, system architecture, state machine, or any node-and-edge picture they want as an SVG.

Anish-Reddy-K/diagrammer · 51 tokens

launchpad-spec

Spec-driven development framework with iterative refinement. Orchestrates feature development from intent to implementation via structured specs and task breakdown. Triggers on /lp:spec, /lp:refine, /lp:clarify, /lp:tasks, /lp:run-task.

Geono/claude-launchpad · 59 tokens

launchpad

End-to-end development pipeline orchestrator. Guides through spec writing, task breakdown, parallelization planning, and multi-agent execution. Chains launchpad-spec, launchpad-plan, and launchpad-run in sequence. Triggers on /launchpad, build this feature, I want to build.

Geono/claude-launchpad · 60 tokens

launchpad-plan

Analyze a spec's task list and produce a parallelization-aware execution plan. Reads task sections, analyzes dependency chains and file mutation overlaps, determines parallel vs sequential execution, and assigns wave groups. Triggers on /lp:plan.

Geono/claude-launchpad · 50 tokens

launchpad-run

Multi-session autonomous agent runner with progress checkpointing, failure recovery, and task dependency management. Uses a controller + sub-agent architecture: the main agent orchestrates state while sub-agents execute tasks in parallel via worktrees. Triggers on '/lp:run' command, or when a task involves many…

Geono/claude-launchpad · 95 tokens