acp-dev-patterns

acp-dev-patterns is a skill for Claude Code, Codex from OrcaQubits/agentic-commerce-skills-plugins. It costs 48 tokens per session (1,186 once invoked), scanned A, original, MIT.

A set of design patterns for building reliable Agentic Commerce Protocol (ACP) services, including safe retries, error handling, payment checks, request signing, rate limits, monitoring, and security.

In plain words
What is it for?
Use it when designing an ACP service or fixing production concerns such as retries, 3D Secure payment flows, authentication, rate limiting, and monitoring.
Why use it?
It helps prevent duplicate operations, unsafe requests, confusing failures, and production problems when an ACP service handles real traffic and payments.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/acp-dev-patterns
Any agent
npx skills add OrcaQubits/agentic-commerce-skills-plugins --skill acp-dev-patterns
Clone the repo
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-plugins

Made for: Claude Code, Codex.

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-dev-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/acp-dev-patterns.svg)](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/acp-dev-patterns)
Your own site
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/acp-dev-patterns"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/acp-dev-patterns.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,186 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.01186
Opus 5 $0.00024 $0.00593
Sonnet 5 $0.00010 $0.00237
Haiku 4.5 $0.00005 $0.00119

Measured 3d ago against content hash d8a060cf3cb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acp-dev-patterns 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 3d 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-dev-patterns/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ACP Development Patterns

Before writing code

Fetch live docs:

  • Checkout spec: Fetch https://developers.openai.com/commerce/specs/checkout/ for error codes and idempotency rules
  • Production guide: Fetch https://developers.openai.com/commerce/guides/production/ for operational requirements
  • Stripe integration: Web-search site:docs.stripe.com agentic-commerce for PSP-side patterns
  • Changelog: Web-search site:github.com agentic-commerce-protocol CHANGELOG for latest changes

Pattern: Idempotency

Every POST request MUST include Idempotency-Key (UUID v4, max 255 chars).

Server-side implementation:

  • Store key → response mapping for minimum 24 hours
  • Same key + identical body = replay original response, add Idempotent-Replayed: true header
  • Same key + different body = 422 idempotency_conflict
  • Key in flight = 409 idempotency_in_flight with Retry-After header
  • 5xx responses are NOT cached — retries treated as fresh requests

Client-side implementation:

  • Generate UUID v4 for each logical operation
  • Reuse the same key when retrying a failed request
  • Generate a new key for a genuinely new operation
  • Handle 409 by waiting per Retry-After then retrying

Pattern: Error Handling

ACP uses a flat error structure:

{type, code, message, param}
  • type: invalid_request | processing_error | service_unavailable
  • code: Well-known identifier (e.g., idempotency_conflict, invalid_card, rate_limit_exceeded)
  • message: Human-readable description
  • param: JSONPath (RFC 9535) to the offending field

Retry strategy:

  • 429 rate_limit_exceeded — Exponential backoff with jitter
  • 409 idempotency_in_flight — Wait per Retry-After header
  • 5xx — Retry with same idempotency key, exponential backoff
  • 4xx (except 429) — Do not retry, fix the request

Pattern: 3D Secure Authentication

When complete returns authentication_required:

  1. Extract 3DS challenge from the response
  2. Present challenge to the buyer (redirect or modal)
  3. Buyer completes authentication
  4. Call complete again with authentication_result:
    • three_ds_cryptogram
    • electronic_commerce_indicator
    • transaction_id
    • version
  5. Merchant processes the authenticated payment

Read the full file on GitHub · 133 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. 3d ago First seen · 133 lines · 48 tokens per session scan A d8a060cf3cb2

Subscribe to this mod's changes

acp-dev-patterns is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (38 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,186 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

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

store-listing-localizer

Automate Microsoft Store (Partner Center) listing localization for Intelligent Terminal (Store ID 9NMQC2SSJX24). Use when asked to export/import Store listings, localize release notes / descriptions / captions / features into 80+ languages, update listingData CSV, or push Store listing translations without manually…

microsoft/intelligent-terminal · 97 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

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

archestra-dev-rust-napi

Use when editing Rust in this repo — the NAPI crates under platform/archestra-rs (app-runtime, image, and sandbox core/-rs crate pairs plus napi-loader, with their generated TypeScript bindings) or the standalone ai-labs Rust workspace (core/runner/cli/analyzer/dashboard) — including Rust build/test checks.

archestra-ai/archestra · 76 tokens

archestra-dev-testing

Use when deciding whether a change needs a test and at which level — unit, backend route-level integration, MSW-backed frontend integration, or e2e — or when reviewing tests for the "fluff test" anti-pattern. Start here before archestra-dev-backend-tests or archestra-dev-e2e.

archestra-ai/archestra · 68 tokens