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-intent-tracesgit 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-intent-traces)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/acp-intent-traces"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/acp-intent-traces.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00806 |
| Opus 5 | $0.00019 | $0.00403 |
| Sonnet 5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
acp-intent-traces 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACP Intent Traces
Before writing code
Fetch live docs:
- Web-search
site:github.com agentic-commerce-protocol rfcs intent_tracesfor the intent traces RFC - Fetch
https://developers.openai.com/commerce/specs/checkout/for how intent traces integrate with checkout - Web-search
site:github.com agentic-commerce-protocol spec json-schema intentfor the schema
Conceptual Architecture
What Intent Traces Are
Intent traces are a built-in ACP extension that provides structured cart abandonment signals. When a buyer abandons a checkout, the agent sends a trace explaining why — enabling merchants to understand conversion barriers and automate recovery.
10 Reason Codes
| Code | Meaning |
|---|---|
price_sensitivity |
Total was too expensive |
shipping_cost |
Shipping cost was a barrier |
shipping_speed |
Delivery time was too slow |
product_fit |
Product didn't match buyer's needs |
trust_security |
Buyer didn't trust the merchant/payment |
returns_policy |
Return/refund policy was inadequate |
payment_options |
Preferred payment method unavailable |
comparison |
Buyer is comparison shopping |
timing_deferred |
Buyer wants to purchase later |
other |
Doesn't fit other categories |
How It Works
- Buyer initiates checkout but doesn't complete
- Agent detects abandonment (session timeout, explicit cancellation, navigation away)
- Agent sends intent trace via
POST /checkout_sessions/{id}/cancel, including a singlereason_code(required enum string, exactly one per trace) - Merchant receives the trace and can:
- Aggregate for analytics
- Trigger automated recovery (email, discount offer)
- Adjust pricing/shipping strategy
Privacy Considerations
- Intent traces contain behavioral signals — handle per GDPR/CCPA
- Only collect traces when the buyer has consented to data collection
- Don't store personally identifiable information in trace metadata
- Aggregate traces for analytics rather than individual tracking
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.
- 8d ago First seen · 89 lines · 39 tokens per session scan A be276caf6959
acp-intent-traces is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 806 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.
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.
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.
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…
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.
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.
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.