setup-earl

A setup guide for Earl, a command-line tool that lets an AI agent access outside services through reviewed templates while keeping secrets in the operating system keychain.

In plain words
What is it for?
Use it to install Earl, connect it through MCP, create project instructions, move existing command-line calls into Earl templates, and optionally enforce its use.
Why use it?
It avoids giving agents unrestricted access to tools such as curl, GitHub commands, or Stripe's command-line tool. It also provides a repeatable way to connect Earl to an agent platform and onboard developers.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mathematic-inc/earl/setup-earl
Any agent
npx skills add mathematic-inc/earl --skill setup-earl
Clone the repo
git clone --depth 1 https://github.com/mathematic-inc/earl

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,898 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
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 $0.00067 $0.01898
Opus 5 $0.00034 $0.00949
Sonnet 5 $0.00013 $0.00380
Haiku 4.5 $0.00007 $0.00190

Measured 3d ago against content hash 822777a1ac89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

setup-earl scanned grade D with 3 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

**macOS / Linux (prefer — no sudo required):**

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`earl call provider.command --param value` instead of raw `curl`, `gh`, `stripe-cli`, etc.
skills/development/setup-earl/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup Earl

Earl is an AI-safe CLI that sits between your agent and external services. Agents run earl call provider.command --param value instead of raw curl, gh, stripe-cli, etc. Secrets stay in the OS keychain. Every request follows a reviewed HCL template.

Process

  1. Install — get Earl running
  2. Demo — show a working example immediately
  3. Connect — configure MCP for your agent platform and write CLAUDE.md instructions
  4. Route — migrate existing CLI calls or create a new template
  5. Lock down — optionally enforce Earl usage at the platform level

Phase 1: Install

Check if Earl is already installed:

which earl && earl --version

If installed, print the version and skip to Phase 2.

If not installed, detect the environment and install:

macOS / Linux (prefer — no sudo required):

cargo install earl

This requires the Rust toolchain and Node.js + pnpm (Earl embeds web playground assets at compile time). If either is missing, fall back to the install script:

curl -fsSL https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.ps1 | iex

After install, verify:

earl doctor

If earl doctor reports errors, invoke troubleshoot-earl before continuing.


Phase 2: Quick Demo

Import the no-auth system template and run it so the user sees Earl work immediately. First check if it's already imported to avoid overwriting any customizations:

earl templates list | grep -E "^system\." || earl templates import https://raw.githubusercontent.com/mathematic-inc/earl/main/examples/bash/system.hcl
earl call --yes --json system.list_files --path .

This lists files in the current directory. The user now has a mental model: templates define commands, earl call runs them.

Show available templates:

earl templates list

Read the full file on GitHub · 235 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. 3d ago First seen · 235 lines · 67 tokens per session scan D 822777a1ac89

Subscribe to this mod's changes

setup-earl is a skill published in the GitHub repository mathematic-inc/earl (113 stars, last pushed 6d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,898 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

api-design-patterns

Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.

aAAaqwq/AGI-Super-Team · 29 tokens

api-design

Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…

ericrisco/rsc-harness · 105 tokens

api-designer

Designs production-grade APIs — REST, GraphQL, gRPC, and AsyncAPI patterns including pagination, versioning, error handling, rate limiting, and API governance. Use when the user asks to design APIs, create endpoints, build an API layer, write OpenAPI specs, or needs help with REST/GraphQL/gRPC service design.

buiphucminhtam/forgewright · 73 tokens

api-design

Design and implement RESTful APIs with proper routing, validation, error handling, and documentation. Use when building new API endpoints, designing API architecture, or improving existing APIs.

asgarovf/locusai · 37 tokens

api-design

RESTful, GraphQL, gRPC, and API best practices.

miles990/claude-software-skills · 16 tokens

api-design-first

Design-first API development skill. Generates OpenAPI 3.1 specifications, enforces REST design best practices, validates endpoints, handles versioning, pagination, error formatting, authentication patterns, rate limiting, and idempotency. Activates when users say "design an API", "create OpenAPI spec", "API endpoint"…

JPeetz/agent-skills · 117 tokens