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 inflowpayai/inflow-cli --skill agentic-paymentsgit clone --depth 1 https://github.com/inflowpayai/inflow-cliWrote 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/inflowpayai/inflow-cli/agentic-payments)<a href="https://agentmods.dev/skills/inflowpayai/inflow-cli/agentic-payments"><img src="https://agentmods.dev/badge/skills/inflowpayai/inflow-cli/agentic-payments/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/inflowpayai/inflow-cli/agentic-payments"><img src="https://agentmods.dev/badge/skills/inflowpayai/inflow-cli/agentic-payments.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 | $0.00054 | $0.08834 |
| Opus 5.5 | $0.00022 | $0.03534 |
| Sonnet 5.5 | $0.00011 | $0.01767 |
| Haiku 4.5 | $0.00005 | $0.00883 |
Grade C, and why
agentic-payments 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:*)'] How it starts
The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Payments
Pay HTTP 402-protected resources on the user's behalf. InFlow speaks two payment protocols - MPP and x402 - but the flow is the same for both: shared setup (install, run, authenticate), then a router that picks the protocol from the seller's 402 header, then one Paying a 402 resource section that covers both. A per-protocol delta table at the top of that section lists the handful of real differences (header name, credential name, filters, error codes); read your row, then follow the shared steps.
Installing
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 |
Current install instructions live at https://inflowcli.ai/.
Running
InFlow runs as a standalone CLI or an MCP server.
MCP: add an inflow server to your MCP client config that runs inflow --mcp.
MCP mode exposes every CLI command as a tool. Call tools/list on the MCP server for the authoritative inventory; arguments mirror the CLI flags one-to-one.
Common commands / options
The CLI is the source of truth for exact flags, enums, and output shapes - run inflow <command> --schema for one command, or inflow --llms-full for everything. This playbook covers when and why, not exhaustive parameter lists; when you need a precise flag name, value set, or response shape, query the CLI rather than guessing.
inflow --llms(or--llms-fullfor parameter detail) - discover all commands.inflow <command> --schemafor a single command's JSON Schema.inflow --skill- print this playbook (no frontmatter) to stdout. Use it to paste into the system-prompt field of an MCP host that doesn't natively load skills:inflow --skill | pbcopy.- Default output is
toon. Override with--format <fmt>; for programmatic parsing preferjson(single document) orjsonl(line-delimited). - Deferred payments return
_next.tooland_next.inputfor the InFlow MCP server. For shell use, prefix_next.commandwithinflowwhen supplied. Ifrequires_original_request_optionsis true, restore the originaldataandheaderarguments before calling Fetch; they are deliberately omitted from the response. --auth <path>identifies a legacy plaintext credential file for deletion; it is not a credential backend.--api-key <key>orINFLOW_API_KEY=<key>is an alternative to device-flow auth.
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.
- 3d ago Changed 2d54637a31d9
- 7d ago Changed · +6 lines ef5c37613861
- 10d ago Changed · +91 lines 6f5aab523ea3
- 20d ago Changed 4e2075a92b8d
- 23d ago Changed · +24 lines a0ef9ed01228
- 1mo ago Changed d1001efb5629
- 1mo ago First seen · 373 lines · 54 tokens per session scan C c65395913377
agentic-payments is a skill published in the GitHub repository inflowpayai/inflow-cli (10 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 8,834 once invoked, about $0.0002 per session on Opus 5.5. 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.
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.