ap2-dispute-accountability

ap2-dispute-accountability is a skill for Claude Code from OrcaQubits/agentic-commerce-skills-plugins. It costs 48 tokens per session (996 once invoked), scanned A, original, MIT.

A guide to handling disagreements and assigning responsibility in AP2 payments, using signed records and an audit trail. An audit trail is a history of events and approvals used to investigate what happened.

In plain words
What is it for?
Use it to build dispute handling, chargeback investigations, fraud reviews, evidence collection, and compliance records for agent payments.
Why use it?
It helps determine whether the user, an AI agent, or a merchant is responsible when a payment or order is disputed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the ap2-agentic-payments plugin — 18 skills, 1 agent shipped together

Good fit Use it to build dispute handling, chargeback investigations, fraud reviews, evidence collection, and compliance records for agent payments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dispute-accountability
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 ap2-dispute-accountability
Clone the repo
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-plugins

Made for: Claude Code.

Or install ap2-agentic-payments, the plugin that ships this one along with the rest of its 18 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 ap2-dispute-accountability

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dispute-accountability/github.svg)](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dispute-accountability)
Your own site
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dispute-accountability"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dispute-accountability/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.

agentmods 80×15 button for ap2-dispute-accountability

Your own site · 80×15
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dispute-accountability"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dispute-accountability.svg" alt="Reviewed on agentmods" width="80" 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 996 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 $0.00048 $0.00996
Opus 5 $0.00024 $0.00498
Sonnet 5 $0.00010 $0.00199
Haiku 4.5 $0.00005 $0.00100

Measured 10d ago against content hash 8a1ea6d923b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ap2-dispute-accountability 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 10d 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.

ap2-agentic-payments/skills/ap2-dispute-accountability/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AP2 Dispute Resolution and Accountability

Before writing code

Fetch live docs:

  1. Fetch https://ap2-protocol.org/specification/ for the accountability model
  2. Fetch https://ap2-protocol.org/topics/core-concepts/ for dispute resolution details
  3. Web-search ap2 protocol dispute accountability liability mandate evidence for accountability framework
  4. Web-search ap2 protocol chargeback fraud resolution for dispute handling patterns

Conceptual Architecture

Why Accountability Matters

In agentic commerce, the traditional dispute model breaks down:

  • Who's responsible when an AI agent buys the wrong item?
  • How do you prove the user authorized a purchase?
  • What evidence settles a dispute between a user, agent, and merchant?

AP2's VDC-based accountability model provides cryptographic evidence for every dispute scenario.

Liability Allocation Table

Scenario Key Evidence Accountability
First-party misuse User-signed Cart/Intent Mandate User — signature proves authorization
Agent mispick (user approved cart) Cart Mandate shows item, user signed User — they approved the specific cart
Agent mispick (unapproved) Intent Mandate vs cart discrepancy Shopping Agent/Platform — exceeded intent
Merchant non-fulfillment Valid mandate + payment confirmation vs absent delivery Merchant — committed via signature
Account takeover Authentication signals during session CP/User — depends on auth strength evidence
Man-in-the-middle Digital signature verification Attack prevented — signatures invalid if tampered
Price discrepancy Merchant-signed Cart Mandate vs charged amount Merchant — signed specific prices
Unauthorized transaction Absence of user signature on mandate Platform/Agent — no valid user authorization

Evidence Chain

For every transaction, AP2 preserves:

  1. User's original intent — Natural language captured in Intent Mandate
  2. User's authorization — Cryptographic signature on the mandate
  3. Merchant's commitment — Merchant entity signature on Cart Mandate
  4. Payment authorization — Payment Mandate with user signature
  5. Challenge completion — Records of 3DS/OTP challenges
  6. Transaction receipt — Payment confirmation from MPP

Read the full file on GitHub · 104 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. 10d ago First seen · 104 lines · 48 tokens per session scan A 8a1ea6d923b3

Subscribe to this mod's changes

ap2-dispute-accountability is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 996 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

nla-arbitrate

Manually arbitrate NLA escrow fulfillments as an alternative to the automated oracle. Use when the user wants to review pending arbitration requests, evaluate demands against fulfillments, and submit on-chain decisions. Supports both interactive and LLM-auto modes.

internet-court/internet-court-skill · 55 tokens

internet-court

Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow…

internet-court/internet-court-skill · 147 tokens

okx-agent-payments-protocol

Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channelid, opening / closing / topping up / settling / refunding a…

internet-court/internet-court-skill · 231 tokens

jupiter-lend

Interact with Jupiter Lend Protocol. Read-only SDK (@jup-ag/lend-read) for querying liquidity pools, lending markets (jlTokens), and vaults. Write SDK (@jup-ag/lend) for lending (deposit/withdraw) and vault operations (deposit collateral, borrow, repay, manage positions).

internet-court/internet-court-skill · 68 tokens

sales-ledger

Provides the Q3 sales ledger workbook for reporting tasks. Use when a task asks you to compute bonuses or totals over the sales ledger; the data lives only in this skill's bundled workbook.

archestra-ai/archestra · 42 tokens

okx-dapp-discovery

Plugin router for 20 third-party DeFi protocols (Polymarket, Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, pump.fun, Uniswap) and their protocol-native tokens (HYPE, HLP, eETH, weETH, stETH, wstETH, LDO, GHO, CAKE, CRV, COMP, RAY, ETHFI…

internet-court/internet-court-skill · 351 tokens