agentic-discovery

A tool for finding services and products through InFlow's directory and then inspecting the catalogs those services publish. It can search collections and offerings, show product details, and resolve an action before enrollment or payment.

In plain words
What is it for?
Use it to search for a service, browse its collections, find offerings, inspect product details, or identify an action to perform next.
Why use it?
It avoids assuming that a service or catalog operation exists and handles the service documents, schemas, pagination, and requests needed to inspect available offerings.

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/inflowpayai/inflow-cli/agentic-discovery
Any agent
npx skills add inflowpayai/inflow-cli --skill agentic-discovery
Clone the repo
git clone --depth 1 https://github.com/inflowpayai/inflow-cli

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,152 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00057 $0.02152
Opus 5 $0.00028 $0.01076
Sonnet 5 $0.00011 $0.00430
Haiku 4.5 $0.00006 $0.00215

Measured 3d ago against content hash 2021a3e309c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agentic-discovery scanned grade C with 2 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.

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.

| macOS/Linux hosted installer | `curl -fsSL https://inflowcli.ai/install.sh \| bash` |

Makes network callslowCapability

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

allowed-tools: ['Bash(inflow:*)', 'Bash(brew:*)', 'Bash(curl:*)']
skills/agentic-discovery/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Discovery

Find Services through the InFlow directory, then query each selected Service's Offering Discovery Protocol catalog directly. Let the InFlow CLI validate Service documents, enforce advertised operations, follow pagination, resolve supporting schemas, and compose authenticated requests. Do not assume that the directory contains a Service's products or that every Service supports every catalog command.

Setup

Install the signed native CLI through one of these channels:

Channel Command
macOS Homebrew brew tap inflowpayai/tap && brew install --cask inflow
macOS/Linux hosted installer curl -fsSL https://inflowcli.ai/install.sh | bash
Windows PowerShell installer irm https://inflowcli.ai/install.ps1 | iex
Cross-platform shell compatibility curl -fsSL https://inflowcli.ai/cli | bash

Use structured output for programmatic work:

inflow odp directory search gpu --format json

The CLI is self-describing. Query the installed version instead of guessing parameters:

inflow odp --help
inflow odp offerings search --schema
inflow --llms-full

Choose the command

Goal Command
Find Services inflow odp directory search
Complete a directory keyword inflow odp directory suggest
Inspect one Service and its operations inflow odp inspect
Browse or search Collection groupings inflow odp collections list/search/get
Browse, search, or retrieve products inflow odp offerings list/search/get
Find Offerings across directory Services inflow odp offerings discover
Resolve an Offering Action without invoking it inflow odp actions resolve

Understand the discovery model

Discovery has two stages:

  1. The canonical directory searches Service metadata such as name, description, keywords, supported operations, enrollment, and payment protocols.
  2. The selected Service supplies its own Collections, Offerings, product attributes, and Actions.

Read the full file on GitHub · 225 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 · 225 lines · 57 tokens per session scan C 2021a3e309c2

Subscribe to this mod's changes

agentic-discovery is a skill published in the GitHub repository inflowpayai/inflow-cli (9 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 2,152 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

verify-before-checkout

Pre-checkout verification for shopping agents. Before transacting with any storefront the user didn't explicitly type, fetch Ed25519-signed merchant facts (domain age, TLS age, brand-lookalike score, price deviation) from the Onyx oracle over x402, verify the signature, and surface the facts to the buyer. Use whenever…

dimitrilaouanis-tech/onyx-mcp · 89 tokens

seller-research

Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.

cinderline/northcinder · 46 tokens

lucid-agents

Build, modify, review, debug, or deploy TypeScript services made with the Lucid Agents SDK. Use whenever a project imports @lucid-agents packages or the user asks about Lucid runtimes, entrypoints, adapters, payments, MPP, identity, wallets, A2A tasks, service UI, scaffolding, or deployment.

daydreamsai/lucid-agents · 75 tokens

write-contract

Write production-quality GenLayer intelligent contracts. Always pins concrete GenVM runner version hashes and never uses local-only test/latest runner aliases. Covers equivalence principles, storage rules, LLM resilience, and cross-contract interaction.

internet-court/internet-court-skill · 46 tokens

intelligent-oracle

Design, deploy, and monitor a GenLayer Intelligent Oracle prediction market from any coding agent. Use when a user wants to create a settled-by-web-evidence prediction market without opening the web UI.

internet-court/internet-court-skill · 44 tokens

jupiter-lend

Interact with Jupiter Lend Protocol. Read-only SDK (@jup-ag/lend-read) for querying liquidity pools, lending markets (jlTokens), and vaults. Write SDK (@jup-ag/lend) for lending (deposit/withdraw) and vault operations (deposit collateral, borrow, repay, manage positions).

internet-court/internet-court-skill · 68 tokens