agentleFS
Sign inStart free
inflowpayaiinflowpayai/inflow-cli/skills/skill.md

skills

Skill10 starsChanged 5 months agoMITView on GitHub

Served at https://inflowcli.ai/skill.md - the onboarding entry point for AI agents. InFlow gives your agent a wallet to register, access, and pay for services autonomously across fiat and stablecoins, over MPP and x402. You are an AI agent whose user asked to get set up with InFlow. Follow these steps. macOS or Linux: Windows PowerShell: The compatibility shell endpoint selects the platform installer on macOS, Linux, and Git Bash-like Windows environments: Running as an MCP server? Add an inflow server…

  • Pipes a download into a shell

58 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 37 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check the current state first - the user may already be logged in:

    line 36
  2. Very specific:

    If the response includes an update field, tell the user a newer version is available and share the install instructions at …

    line 42
  3. Very specific:

    If authenticated is false, start the OAuth device flow:

    line 45
  4. Very specific:

    Prefer inflow --skill <name> - it always matches the version you are running.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 37 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

InFlow - Agent Setup

Served at https://inflowcli.ai/skill.md - the onboarding entry point for AI agents. InFlow gives your agent a wallet to register, access, and pay for services autonomously across fiat and stablecoins, over MPP and x402.

You are an AI agent whose user asked to get set up with InFlow. Follow these steps.

1. Install

macOS or Linux:

curl -fsSL https://inflowcli.ai/install.sh | bash

Windows PowerShell:

irm https://inflowcli.ai/install.ps1 | iex

The compatibility shell endpoint selects the platform installer on macOS, Linux, and Git Bash-like Windows environments:

curl -fsSL https://inflowcli.ai/cli | bash

Running as an MCP server? Add an inflow server to your MCP client config that runs inflow --mcp.

2. Authenticate

Public directory search, document discovery through inflow inspect, and OpenAPI discovery, preparation and calls do not require an InFlow login. For those tasks, go directly to the discovery playbook below. Authenticate before payments or AEP operations that require an InFlow account; Service-specific credentials are separate from an InFlow login.

Check the current state first - the user may already be logged in:

inflow auth status

If the response includes an update field, tell the user a newer version is available and share the install instructions at https://inflowcli.ai/, then proceed with the current version.

If authenticated is false, start the OAuth device flow:

inflow auth login --client-name "<your-agent-name>"

Replace <your-agent-name> with a clear, unique, identifiable name for your agent - the user sees it on the approval page in their browser. The response includes a verification_url (present it to the user), a phrase, and a _next.command - run that command immediately to poll until authenticated; do not wait for the user to respond before starting the poll. If your environment can't relay the phrase while a polling command blocks I/O, use inline polling instead:

inflow auth login --client-name "<name>" --interval 5 --timeout 300

Confirm with inflow auth status before proceeding.

3. Load the playbook for your task

Setup alone is not enough. Before performing a task with InFlow, load and follow its playbook:

TaskPlaybook
Discover Services, navigate ODP catalogs, or use OpenAPI operationsrun inflow --skill agentic-discovery, or fetch https://inflowcli.ai/skills/agentic-discovery.md
Enroll with or access an AEP Servicerun inflow --skill agentic-enrollment, or fetch https://inflowcli.ai/skills/agentic-enrollment.md
Pay HTTP 402-protected resources (MPP / x402)run inflow --skill agentic-payments, or fetch https://inflowcli.ai/skills/agentic-payments.md

Prefer inflow --skill <name> - it always matches the version you are running. The web copy reflects the latest release; compare its version: header against inflow --version.

The CLI is self-describing - prefer querying it over static docs: inflow --llms (command index), inflow --llms-full (parameter detail), inflow <command> --schema (JSON Schema for one command).

Links

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free