Skip to main content
skill CX Codex

allow — Claude Code skill: what it does, how to install

The allow skill for Claude Code manages consent for sending codebase data to Cheap Agent worker models. It runs to configure repository access and data retention parameters.

MIT ★ 341 updated 2026-11-16

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add muaaz9329/cheap-ag
/plugin install cheapag@cheap-agent
Open on GitHub

What allow does

This utility registers authorization to share project files with Cheap Agent models. Users can restrict data sharing to models with zero-retention policies using the --zdr-only flag or specify particular providers and model versions.

The skill requires network access to execute via npx. It is designed to run only once to establish consent without redundant changes. If no command output appears, the agent executes the registration process manually using the provided arguments.

What it helps with

  • configure access to Cheap Agent models
  • restrict data transmission to zero-retention models
  • select specific models for agent operations

Example prompts for the agent

  • /plugin:allow --zdr-only
  • allow --models openai/gpt-4o

How to install allow

1Plugin marketplace

/plugin marketplace add muaaz9329/cheap-ag
/plugin install cheapag@cheap-agent

This installs the whole cheapag plugin with all its skills

2Skills CLI (Vercel)

npx skills add muaaz9329/cheap-ag --skill allow -a claude-code

3Manually: put the files in place

~/.claude/skills/allow/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/allow/

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

Questions about allow

How to install allow in Claude Code?

Run /plugin marketplace add muaaz9329/cheap-ag, then /plugin install cheapag@cheap-agent, and finally add the skill using npx skills add muaaz9329/cheap-ag --skill allow -a claude-code.

What does allow do?

It records user consent for sending repository code to Cheap Agent models with specific privacy settings.

What is required for allow to work?

Node.js for npx execution and network connectivity to run the consent command.

Source text

SKILL.md · MIT
---
name: allow
description: Opt this repository in to sending code to Cheap Agent's worker models - all models, --zdr-only (zero-retention only), or --models provider/model,...
argument-hint: "[--zdr-only | --models provider/model,...]"
disable-model-invocation: true
allowed-tools: Bash(npx -y [email protected] allow) Bash(npx -y [email protected] allow *)
---

!`npx -y [email protected] allow $ARGUMENTS`

The developer ran this consent command themselves; its output is above. Report it in one line.

Only because the user invoked this skill: If no output appears above (Codex): run that command yourself once, exactly as written, with `$ARGUMENTS` replaced by whatever the user typed after the skill name (or nothing). It needs network for npx; ask for that if the sandbox blocks it. Do not run `cheapag allow` again or change consent in any other way.

© muaaz9329 · MIT · muaaz9329/cheap-ag

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set8

Project sponsors

Companies that keep this analytics open