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 runxhq/runx --skill paygit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/pay)<a href="https://agentmods.dev/skills/runxhq/runx/pay"><img src="https://agentmods.dev/badge/skills/runxhq/runx/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/runxhq/runx/pay"><img src="https://agentmods.dev/badge/skills/runxhq/runx/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 | $0.00027 | $0.00463 |
| Opus 5.5 | $0.00011 | $0.00185 |
| Sonnet 5.5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
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 today.
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.
What it actually says
Pay
pay is the buyer contract. settle pays the exact requirement once, and
readback performs one observation of that durable payment and the resource it
paid for. The default pay runner composes both and requires immediate terminal
readback, while durable callers compose settle once and re-enter readback
through Runx's external-job scheduler.
The payment method is a connector the payer holds. Today that is wallet/evm:
an x402 V2 challenge on an HTTPS resource, paid from the payer's EVM wallet in
USDC on Base. Other methods join as connectors when they are implemented.
Runx Hosted owns challenge validation, authority attenuation and reservation,
wallet credentials, payload signing, settlement recovery, finality, and the
private ledger. The connector never sleeps or polls; durable continuation
cadence belongs to Runx scheduling. pay never buys a runx paid skill: a
paid skill is bought by running it, and the kernel asks its buyer for that
purchase itself.
Operator guide
Use this skill for one exact HTTPS resource already named by a hosted wallet grant. The resource request carries bounded inline control data or artifact references; large documents and media never travel as oversized graph values. The hosted payer accepts external x402 V2 only, signs and stages the payload before the paid POST, and reuses those exact bytes after an uncertain response.
Stop on malformed or expired requirements, amount, currency, payee or resource drift, incomplete authority, missing approval, or inconsistent paid-resource readback. Never pass wallet keys, seed phrases, bearer tokens, or facilitator credentials in skill input. A 2xx response is not finality: a complete readback needs the transaction confirmed on chain and a 2xx answer from the resource. It never waits on the resource's own product state.
Use charge to take a payment as the seller, refund to reverse one, and
settle-invoice when an invoice needs validating before it is paid.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 42 lines · 27 tokens per session scan A daae94e450c4
pay is a skill published in the GitHub repository runxhq/runx (103 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 463 once invoked, about $0.0001 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 2026-10-16.
Other skills, from other repositories
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
money
Skill "money" from Hmbown/Codewhale, covering money, when to use, setup, workflow and non-goals.