agentmods.dev

inflow-cli AGENTS.md

Repository guidance for InFlow, a command-line tool for people and AI agents to make payments through MPP and x402. It also describes its pnpm and Turborepo monorepo, meaning one repository containing multiple related packages.

In plain words
What is it for?
Use it to navigate the monorepo, understand the core client and its payment-related command groups, and check changes before merging.
Why use it?
It explains the package roles and project rules so changes fit the shared command-line and client design.

Instructions file for CodexOpenCode

9 3d ago A scan 3,854 tokens original MIT
View the source file inflowpayai/inflow-cli
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 instructions/inflowpayai/inflow-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/inflowpayai/inflow-cli

Made for: Codex, OpenCode.

Per session 3,854 This file is loaded in full into every session.
When invoked 3,854 The same file — it is already loaded in full.
Security scan A 0 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 $0.03854 $0.03854
Opus 5 $0.01927 $0.01927
Sonnet 5 $0.00771 $0.00771
Haiku 4.5 $0.00385 $0.00385

Measured 2d ago against content hash d1464b152ee4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

inflow-cli AGENTS.md scanned grade A with 0 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operating notes for working in this repo. If anything below conflicts with the configs (eslint.config.js, typedoc.json, tsconfig.base.json, turbo.json, .changeset/config.json, .prettierrc.json), the configs win — fix the drift, don't paper over it.

What this repo is

inflow is the agent-native and human-accessible command-line entry point to InFlow. It lets agentic buyers perform agent-native payments via MPP and x402, and lets humans hit the same functionality from MCP-integrated assistants or the raw CLI.

A pnpm + Turborepo monorepo with two packages:

  • @inflowpayai/inflow-core (packages/core) — the headless InFlow client. One augmented handle per command group hung off the Inflow instance: inflow.auth (IAuth), inflow.user (IUser), inflow.balances (IBalanceResource), inflow.depositAddresses (IDepositAddressResource), inflow.x402 (IX402), inflow.mpp (IMpp). Each handle carries the typed HTTP primitives plus the command-shaped operations (reducers + async-iterable drivers for the stateful commands). No UI dependencies; an ESLint no-restricted-imports rule scoped to packages/core/src/** enforces this.
  • @inflowpayai/inflow (packages/cli) — the published binary. Consumes the core package; renders Ink/React for TTY mode and structured output for agent mode. The CLI commands are thin render shells over the core flows.

Repo map

  • packages/cli/ — @inflowpayai/inflow, the published binary.
  • packages/core/ — @inflowpayai/inflow-core, the typed HTTP client.
  • plugins/inflow/ — the plugin bundle: .claude-plugin/plugin.json, .cursor-plugin/plugin.json, .codex-plugin/plugin.json, plus symlinks skills → ../../skills, .mcp.json → ../../.mcp.json, assets → ../../assets (so each per-plugin manifest's ./skills/, ./.mcp.json, and ./assets/ paths resolve).
  • skills/agentic-payments/SKILL.md — the single skill file.
  • .claude-plugin/marketplace.json — Claude Code marketplace entry.
  • .cursor-plugin/marketplace.json — Cursor marketplace entry.
  • .agents/plugins/marketplace.json — agents marketplace entry.
  • .codex-plugin/plugin.json — Codex marketplace entry.
  • .mcp.json — raw MCP entry.
  • scripts/ — repo-level dev/CI scripts.
  • .changeset/ — pending version bumps.

Read the full file on GitHub · 218 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. 2d ago First seen · 218 lines · 3,854 tokens per session scan A d1464b152ee4

Subscribe to this mod's changes

inflow-cli AGENTS.md is an instructions file published in the GitHub repository inflowpayai/inflow-cli (9 stars, last pushed 3d ago), licensed MIT. It adds 3,854 tokens to every session, about $0.0193 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agent-skillsagentic-commerceagentic-paymentsai-agentsclihttp-402
Related

Other instructions, from other repositories

lucid-agents AGENTS.md

Instructions for daydreamsai/lucid-agents, covering lucid agents monorepo - ai coding guide, project overview, brand system, architecture overview and package dependencies.

daydreamsai/lucid-agents · 7,789 tokens

mnemopay-sdk CLAUDE.md

Instructions for mnemopay/mnemopay-sdk, covering mnemopay sdk, quick start, architecture, two modes and key flows.

mnemopay/mnemopay-sdk · 1,265 tokens

optifeed-radar CLAUDE.md

Instructions for optifeed/optifeed-radar, covering claude.md - optifeed radar, commands, stack, layout and hard rules (violations = rejected pr).

optifeed/optifeed-radar · 2,446 tokens

lightning-enable-mcp CLAUDE.md

Instructions for refined-element/lightning-enable-mcp, covering claude.md — lightning enable mcp, project overview, bug fix workflow and engineering standards.

refined-element/lightning-enable-mcp · 514 tokens

mnemopay-sdk GEMINI.md

Instructions for mnemopay/mnemopay-sdk, covering mnemopay sdk - context & instructions, project overview, building and running, development conventions and key files.

mnemopay/mnemopay-sdk · 606 tokens

scvd-general-store-repo AGENTS.md

Instructions for seancrecord/scvd-general-store-repo, covering agents.md, what this is, commands, layout and code style.

seancrecord/scvd-general-store-repo · 1,707 tokens