A payment tool for AI agents that uses funded virtual debit cards. It can create single-use or subscription cards, provide their details for checkout, and track transactions at supported merchants.

Use it when buying products or paying for supported APIs and software services, with the user's explicit approval for each money movement.

It lets an agent pay without directly using the user's personal card, while keeping spending tied to funded cards and limits.

agentcard — Skill for Claude Code and Codex by tiny-agent-company

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.

Any agent

npx skills add tiny-agent-company/agentcard-skills --skill agentcard

Clone the repo

git clone --depth 1 https://github.com/tiny-agent-company/agentcard-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tiny-agent-company/agentcard-skills/agentcard/github.svg)](https://agentmods.dev/skills/tiny-agent-company/agentcard-skills/agentcard)

Your own site

<a href="https://agentmods.dev/skills/tiny-agent-company/agentcard-skills/agentcard"><img src="https://agentmods.dev/badge/skills/tiny-agent-company/agentcard-skills/agentcard/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tiny-agent-company/agentcard-skills/agentcard"><img src="https://agentmods.dev/badge/skills/tiny-agent-company/agentcard-skills/agentcard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,198 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.01198
Opus 5.5	$0.00033	$0.00479
Sonnet 5.5	$0.00017	$0.00240
Haiku 4.5	$0.00008	$0.00120

Measured 2mo ago against content hash a059c611dbe2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentcard 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 2mo 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.

agentcard/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentcard: cards you can pay with

Agentcard gives you a real payment method without ever holding the user's own card. The user funds a wallet; you mint a virtual debit card sized to one purchase, pay, and the card closes itself after the first approved charge. Subscriptions use multi-use cards with a hard total limit. Every money move needs the user's explicit go-ahead.

VOCABULARY: the user's WALLET is their cards; their BALANCE is their cash. Cards are funded from the balance.

Setup (once per computer)

Install the CLI on your computer; it stays installed:

npm install -g agent-cards   # or: npx -y agent-cards@latest <command>
agent-cards whoami           # signed in? shows the account. Otherwise: sign in below

Each person connects their own Agentcard account. Never sign one person's agent into another person's account.

agent-cards login --email <their email> sends a one-time code to that email.
Ask them to read the code back to you in chat (if they have connected their inbox to you and ask you to, you may fetch it yourself).
agent-cards login --email <their email> --code <code> completes sign-in. The session persists in your $HOME across turns.

Headless alternative: if $AGENT_CARDS_JWT is set in your environment (for example vended through the keychain), the CLI uses it directly; no login needed. New users can create an account at https://agentcard.sh, or login walks them through it by email.

Driving it

The CLI is an agent-first tool catalog (the same catalog as the Agentcard MCP server). Load the canonical guide into context once per session, then follow it:

agent-cards api --agent-help          # read this fully, once per session
agent-cards api search <regex>        # find tools (balance, create_card, buy, ...)
agent-cards api describe <tool>       # schema before first use; never guess
agent-cards api call <tool> '<json>'  # invoke; JSON result on stdout

Tools that move money refuse to run without --confirm. That flag is your attestation that the user confirmed the exact action in chat, so ask first, every time: amount, merchant, and what it is for.

Read the full file on GitHub · 102 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.

2mo ago First seen · 102 lines · 83 tokens per session scan A a059c611dbe2

Subscribe to this mod's changes

agentcard is a skill published in the GitHub repository tiny-agent-company/agentcard-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 1,198 once invoked, about $0.0003 per session on Opus 5.5. 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.

E-commerce Finance and fintech

agentcard next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentcardtiny-agent-company/agentcard-skills	Skill	2	3mo ago	MIT	A	83	Claude Code, Codex
asc-ppp-pricingrorkai/app-store-connect-cli-skills	Skill	1.1k	today	MIT	A	45	Claude Code
snaplii-cliSnaplii-Inc/agent-to-merchant-payments	Skill	812	2d ago	Apache-2.0	A	184	Claude Code
stripeCraftOS-dev/CraftBot	Skill	405	2d ago	MIT	A	79	Claude Code, Codex
ai-slopwaybarrios/opencode-power-pack	Skill	551	5d ago	MIT	A	61	Claude Code
stripemagnus919/agent-skills	Skill	166	2d ago	MIT	A	116	Claude Code, Codex
asc-ppp-pricinghanamizuki/solopreneur	Skill	156	4d ago	MIT	A	45	Claude Code