Prismer Cloud is an infrastructure layer for AI agents that provides shared learning, compressed context, persistent memory, collaboration, messaging, tasks, identity, and workspaces. It is for agents and the people building or using long-running agent systems that need information and outcomes to persist across sessions. The catalogue entries provide skills, hooks, agents, instructions, and a plugin for using Prismer Cloud.
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 Prismer-AI/PrismerCloud --skill wechat-paygit clone --depth 1 https://github.com/Prismer-AI/PrismerCloudWrote 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/prismer-ai/prismercloud/wechat-pay)<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/wechat-pay"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/wechat-pay/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/prismer-ai/prismercloud/wechat-pay"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/wechat-pay.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 | $0.00122 | $0.00755 |
| Opus 5.5 | $0.00049 | $0.00302 |
| Sonnet 5.5 | $0.00024 | $0.00151 |
| Haiku 4.5 | $0.00012 | $0.00076 |
Grade A, and why
wechat-pay 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 28d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Pay (收款) in a session
This skill lets you collect a real WeChat Pay payment from a participant of the current conversation. The platform is a platform-direct merchant using Native (扫码) payment: you create an order, the cloud renders a QR card into the session, the bridge fans that QR out to the session's bound WeChat users, they scan & pay, and the cloud posts a settlement message + flips the card to 已支付.
⛔ Guardrails — real money
- Only on explicit user request with an explicit amount. Never invent a price, never round, never "helpfully" collect more. If the amount is unclear, ASK in the conversation first.
- Never alter the amount the user agreed to.
- One order per intent. Don't re-issue a QR for the same charge — poll the
existing order with
cloud pay statusinstead. - This is online-only. If the cloud is unreachable the command fails — surface that to the user, do NOT fake a confirmation.
When to use
- A user says "帮我下单 / 付款 / 收款 ¥X" or agrees to a quoted price.
- You're a 客服 / 销售 / 咨询 agent closing a paid action.
CLI
# Create an order + post the QR card (amount in YUAN on the CLI)
cloud pay create --conversation <conversationId> --amount 9.9 --desc "咨询费"
# → prints orderId + status=pending; the QR is now visible in the session.
# Poll until paid (the cloud also posts a "✅ 已收款" message when it lands)
cloud pay status <orderId>
# → status: pending | succeeded | expired | closed
--conversation is the current session id. Get it from your dispatch context; if you
don't have it, you are not in a session that can collect payment.
Flow
- Confirm the amount + purpose with the user (in YUAN).
cloud pay create --conversation <id> --amount <yuan> --desc "<purpose>".- Tell the user the QR is posted and to scan it in WeChat.
- Poll
cloud pay status <orderId>(or wait for the settlement message). Onsucceeded, confirm to the user and continue your task. - The Native QR expires in ~2h. If it expires before payment, create a new order.
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.
- 28d ago First seen · 60 lines · 122 tokens per session scan A 57d64f00132c
wechat-pay is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,364 stars, last pushed 5d ago), licensed MIT. It adds 122 tokens to every session and 755 once invoked, about $0.0005 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 2026-09-29.
Other skills, from other repositories
billing-stripe
Work with Stripe billing — subscriptions, plans/prices, the Customer Portal, credits, usage metering, invoices, and webhook events. Use when changing plans, handling a new Stripe webhook, debugging a payment/subscription flow, or touching credit balances and usage.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
Aperture Wallet Guide
Answer Aperture Wallet questions from first-party product, security, network, release, app-screen, and Journal sources while enforcing explicit wallet-secret and no-transaction safety boundaries.
performing-container-image-hardening
This skill covers hardening container images by minimizing attack surface, removing unnecessary packages, implementing multi-stage builds, configuring non-root users, and applying CIS Docker Benchmark recommendations to produce secure production-ready images.
ai-pricing
When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use when the user mentions 'AI pricing,' 'usage-based pricing,' 'consumption pricing,' 'outcome pricing,' 'BYOK,' 'bring your own key,' 'per-seat pricing,' 'pricing tiers,' 'AI margins,' 'cost per…
biofuels-biodiesel-technology-manager
Use when a task needs the judgment of a Biofuels/Biodiesel Technology and Product Development Manager — deciding whether a lab/bench-scale process is ready to scale up, evaluating feedstock flexibility tradeoffs in process design, pricing a technology's value against regulatory credit pathways (RFS RIN, LCFS CI…