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 OrcaQubits/agentic-commerce-skills-plugins --skill acp-cartgit clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-pluginsWrote 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/orcaqubits/agentic-commerce-skills-plugins/acp-cart)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/acp-cart"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/acp-cart/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/orcaqubits/agentic-commerce-skills-plugins/acp-cart"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/acp-cart.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 | $0.00061 | $0.00962 |
| Opus 5.5 | $0.00024 | $0.00385 |
| Sonnet 5.5 | $0.00012 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
acp-cart 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACP Cart API
Before writing code
Fetch live spec — the Cart API arrived in the 2026-04-17 release, so anything older will not describe it:
- Fetch
https://github.com/agentic-commerce-protocol/agentic-commerce-protocol/releasesto identify the current spec version. - Fetch the OpenAPI document for that version:
spec/<version>/openapi/openapi.cart.yamlin the repo. This is authoritative for paths, headers, and status codes. - Fetch
spec/<version>/json-schema/schema.cart.jsonfor the Cart object schema. - Web-search
site:developers.openai.com commerce cartfor narrative guidance.
Never write the request/response shapes from memory — read the OpenAPI document.
Conceptual Architecture
What Cart is for
A lightweight pre-checkout phase for item collection, with:
- no payment configuration,
- no capability negotiation,
- no status lifecycle.
Checkout carries all of that. Cart deliberately carries none of it, so an agent can assemble a basket cheaply while the buyer is still deciding.
Endpoints
| Method | Path | Operation |
|---|---|---|
POST |
/carts |
createCart — returns 201 |
GET |
/carts/{id} |
getCart |
PUT |
/carts/{id} |
updateCart |
POST |
/carts/{id}/cancel |
cancelCart |
Update is full replacement
The agent MUST send the complete desired cart state. The provided
line_itemsreplace the existing cart contents.
This is the single most important behaviour to get right. PUT /carts/{id} is not a patch. Sending one changed line item silently discards the rest of the basket.
Cancel semantics
cancelCart returns the cart state before deletion, so the caller gets a final snapshot. Subsequent operations on that cart ID should return 404.
getCart also returns 404 when the cart does not exist, has expired, or was cancelled — these are indistinguishable to the caller by design.
Headers
Cart uses the standard ACP header set. Authorization (Bearer API key), Content-Type, and API-Version are required; Accept-Language, Idempotency-Key, and Request-Id are optional but you should send them.
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.
- 1mo ago First seen · 81 lines · 61 tokens per session scan A 96412c56c67c
acp-cart is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (40 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 962 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
archestra-dev-llm-providers
Use when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching provider credentials/enums and model constants.
archestra-dev-backend
Use when adding or changing Archestra backend routes, models, services, API request/response schemas, endpoint permissions, or OpenAPI/codegen for the generated API client.
archestra-dev-interactions-migrations
Use BEFORE writing or running any Drizzle migration that touches the interactions table (or any other very large, write-hot table). The interactions table is the platform's biggest, append-heavy table — every LLM proxy call writes a row — so a careless migration can take a write-blocking lock and stall the proxy.…
debridge
Complete deBridge Protocol SDK for building cross-chain bridges, message passing, and token transfers on Solana. Use when building cross-chain applications, bridging assets between Solana and EVM chains, or implementing trustless external calls.
mppx
TypeScript SDK for the Payment HTTP Authentication Scheme. Handles 402 Payment Required flows with Tempo, Stripe, and other payment methods. Use when integrating payments or mppx into a client or server application.
near-intents
Cross-chain token swap integration using NEAR Intents 1Click API. Use when building swap widgets, bridge interfaces, or multi-chain transfers across EVM, Solana, NEAR, TON, Stellar, and Tron.