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 ap2-agent-authorizationgit 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/ap2-agent-authorization)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-agent-authorization"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-agent-authorization/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/ap2-agent-authorization"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-agent-authorization.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 | $0.00067 | $0.00949 |
| Opus 5.5 | $0.00027 | $0.00380 |
| Sonnet 5.5 | $0.00013 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
ap2-agent-authorization 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AP2 Agent Authorization Framework
Before writing code
Fetch live docs:
- Fetch
https://ap2-protocol.org/ap2/agent_authorization/for the framework itself — this is the foundational model everything else sits on. - Fetch
https://ap2-protocol.org/ap2/specification/for the current mandate types and their schemas. - Fetch
https://ap2-protocol.org/glossary/— AP2's terminology has changed across releases and the glossary is the fastest way to catch a rename. - Web-search
site:github.com google-agentic-commerce AP2 mandate open closedfor reference types undercode/.
Terminology warning: AP2 renamed and restructured core objects between releases. Confirm the current names against the live glossary before writing any type. Never carry an object name forward from an older tutorial, blog post, or this skill.
Conceptual Architecture
The problem it solves
Even well-behaving agents need to have their behavior tightly constrained above what a normal authorization model would require of human users.
A human authenticating to a site is authorizing themselves. An agent acting for a human is a delegation, and delegation needs an explicit, verifiable, bounded grant. The Agent Authorization Framework is that grant.
Mandates are the authorization objects
Mandates represent user-approved permissions delegated to an agent, and they chain cryptographically to prove authorization end to end. The framework defines two states:
| State | Bound to a transaction? | Contains | Bound to |
|---|---|---|---|
| Open | No | Constraints on what a valid closed mandate may contain | A particular agent |
| Closed | Yes — via Key Binding JWT | The specific action being authorized | A specific transaction, presented to a verifier |
Open and closed are not two different objects; they are two states of the same authorization, and the open→closed transition is where the agent's discretion gets spent.
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 · 65 lines · 67 tokens per session scan A 550af3645dae
ap2-agent-authorization is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 949 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 2026-09-15.
Other skills, from other repositories
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.
archestra-dev-frontend
Use when modifying Archestra frontend Next.js/React code, UI components, forms, TanStack Query hooks, generated API client usage, frontend copy, or documentation links.
archestra-dev-testing
Use for test selection and quality across backend, frontend, and e2e; load its backend reference for Vitest projects, mocking, DB fixtures, and performance.
managing-archestra-releases
Runs rolling beta releases, stable patches, and complete stable-line cutovers. Use when backporting fixes, cutting or retiring release branches, configuring release protections, testing artifacts, recovering failed runs, or approving releases.
migrate-to-archestra
Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance. Use when the user wants to move, port, or convert an existing agentic setup into an Archestra pilot.
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.…