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.
npx skills add ashray/claude-permissions-wizard --skill configure-permissionsgit clone --depth 1 https://github.com/ashray/claude-permissions-wizardWrote 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.
[](https://agentmods.dev/skills/ashray/claude-permissions-wizard/configure-permissions)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.02460 |
| Opus 5.5 | $0.00026 | $0.00984 |
| Sonnet 5.5 | $0.00013 | $0.00492 |
| Haiku 4.5 | $0.00006 | $0.00246 |
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 2mo 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.
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
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.
- 2mo ago First seen · 224 lines · 65 tokens per session scan F 3605b45c19fb
configure-permissions is a skill published in the GitHub repository ashray/claude-permissions-wizard (1 stars, last pushed 8mo ago), licensed MIT. It adds 65 tokens to every session and 2,460 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
test-driven-development
Strict red-green-refactor TDD workflow for implementing features, fixing bugs, or changing behavior in Rails applications. Enforces the discipline of writing a failing test before any production code. Use whenever you want to implement with TDD — whether a new feature, a bugfix, a refactor, or any behavior change.
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…
prior-art
Discover how a codebase already handles a specific concern — search broadly, find every instance, and assess consistency. The "how does this app do X?" tool.
challenge
Pressure-test an assumption, decision, or inherited constraint — Socratic cross-examination that forces you to defend or abandon your position.