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 tiny-agent-company/agentcard-skills --skill agentcardgit clone --depth 1 https://github.com/tiny-agent-company/agentcard-skillsWrote 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/tiny-agent-company/agentcard-skills/agentcard)<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.
<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>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 | $0.00042 | $0.00599 |
| Sonnet 5 | $0.00017 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
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 9d 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.
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
Sign in (once per person)
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$HOMEacross 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.
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.
- 9d ago First seen · 102 lines · 83 tokens per session scan A a059c611dbe2
agentcard is a skill published in the GitHub repository tiny-agent-company/agentcard-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,198 once invoked, about $0.0004 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.
Other skills, from other repositories
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
stripe
Stripe API integration with managed OAuth. Manage customers, subscriptions, invoices, products, prices, and payments. Use this skill when users want to process payments, manage billing, or handle subscriptions with Stripe. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).…
etsy-pricing-strategy
Etsy pricing — cost calculation, competitor pricing, perceived value, shipping cost integration, sales and coupons.
amazon-wholesale-sourcing
Wholesale product sourcing — supplier discovery, negotiation, MOQ optimization, margin analysis.
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…
payment-processor
Skill "payment-processor" from Signal-Execution-Labs/forex-trading-ai-agent, covering payment processor skill, supported services, capabilities, view balances and get all balances.