acp-capability-negotiation

acp-capability-negotiation is a skill for Claude Code from OrcaQubits/agentic-commerce-skills-plugins. It costs 43 tokens per session (751 once invoked), scanned A, original, MIT.

A guide for ACP capability negotiation, where an AI agent and a merchant compare the features each one supports. The checkout session then uses only features both sides understand.

In plain words
What is it for?
Use it when implementing the capabilities exchanged during ACP checkout requests and responses, including major features, extensions, payment handlers, and other supported options.
Why use it?
It prevents incompatible features from being used during a purchase. This lets one merchant server adapt its behavior to different agents and supported payment or checkout options.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the acp-agentic-commerce plugin — 15 skills, 1 agent shipped together

Good fit Use it when implementing the capabilities exchanged during ACP checkout requests and responses, including major features, extensions, payment handlers, and other supported options.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/acp-capability-negotiation
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 OrcaQubits/agentic-commerce-skills-plugins --skill acp-capability-negotiation
Clone the repo
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-plugins

Made for: Claude Code.

Or install acp-agentic-commerce, the plugin that ships this one along with the rest of its 15 skills, 1 agent.

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.

agentmods badge for acp-capability-negotiation

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/acp-capability-negotiation.svg)](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/acp-capability-negotiation)
Your own site
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/acp-capability-negotiation"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/acp-capability-negotiation.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 751 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00751
Opus 5 $0.00022 $0.00376
Sonnet 5 $0.00009 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 8d ago against content hash 29bc428e76c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

acp-capability-negotiation 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 8d 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.

acp-agentic-commerce/skills/acp-capability-negotiation/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ACP Capability Negotiation

Before writing code

Fetch live docs:

  1. Web-search site:github.com agentic-commerce-protocol rfcs capability_negotiation for the capability negotiation RFC
  2. Fetch https://developers.openai.com/commerce/specs/checkout/ for how capabilities appear in checkout requests/responses
  3. Web-search site:github.com agentic-commerce-protocol spec json-schema capabilities for the capabilities JSON schema

Conceptual Architecture

What Capability Negotiation Does

ACP agents and merchants may support different features. Capability negotiation allows them to dynamically discover what they both support, so the session uses only mutually available features.

How It Works

  1. Agent sends capabilities — In the create request, the agent includes a capabilities object listing what it supports
  2. Merchant responds with capabilities — The merchant intersects with its own capabilities and returns what's active for this session
  3. Intersection governs the session — Only mutually supported features are used

Capabilities Object Structure

The capabilities object contains:

  • capabilities — Major features (checkout, orders, etc.)
  • extensions[] — Optional add-ons (discount, intent traces, affiliate attribution)
  • payment_handlers[] — Supported payment methods
  • interventions — Structured object with sub-fields: supported, required, enforcement, display_context, redirect_context, max_redirects, max_interaction_depth

Extension Pruning

Extensions declare a parent capability via extends. If the parent capability is not in the negotiated intersection, the extension is automatically pruned — no extra logic needed.

Interventions

Interventions are actions that require human involvement. They are represented as a structured object (not a flat array) with sub-fields including supported, required, enforcement, display_context, redirect_context, max_redirects, and max_interaction_depth.

Read the full file on GitHub · 76 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. 8d ago First seen · 76 lines · 43 tokens per session scan A 29bc428e76c5

Subscribe to this mod's changes

acp-capability-negotiation is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 751 once invoked, about $0.0002 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 2026-08-30.

Related

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.

internet-court/internet-court-skill · 45 tokens

seller-research

Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.

cinderline/northcinder · 46 tokens

design-taste-frontend

Use for visual design direction on greenfield, user-facing surfaces — marketing and landing pages, generated apps, portfolio-style or standalone pages. NOT for routine Archestra platform UI work (dashboards, data tables, settings, forms, existing components) — use archestra-dev-frontend for that. Upstream intent…

archestra-ai/archestra · 0 tokens

lucid-agents

Build, modify, review, debug, or deploy TypeScript services made with the Lucid Agents SDK. Use whenever a project imports @lucid-agents packages or the user asks about Lucid runtimes, entrypoints, adapters, payments, MPP, identity, wallets, A2A tasks, service UI, scaffolding, or deployment.

daydreamsai/lucid-agents · 75 tokens

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-ai/archestra · 73 tokens

archestra-dev-backend-tests

Use when writing or modifying Archestra backend unit tests (platform/backend/src//.test.ts) — mocking modules, stubbing globals, database fixtures, vitest projects/isolation, or test performance.

archestra-ai/archestra · 46 tokens