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 PaulieB14/payql --skill skillgit clone --depth 1 https://github.com/PaulieB14/payqlWrote 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/paulieb14/payql/skill)<a href="https://agentmods.dev/skills/paulieb14/payql/skill"><img src="https://agentmods.dev/badge/skills/paulieb14/payql/skill/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/paulieb14/payql/skill"><img src="https://agentmods.dev/badge/skills/paulieb14/payql/skill.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 | $0.00134 | $0.01083 |
| Opus 5.5 | $0.00054 | $0.00433 |
| Sonnet 5.5 | $0.00027 | $0.00217 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
payql 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 2mo 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.
PayQL — pay-per-query data from The Graph
Get live on-chain data from The Graph's subgraphs (DeFi, DEX pools, NFTs, ENS, tokens, governance — 15,000+ subgraphs across 20+ chains), paying ~$0.01 USDC per query over x402. No API key, no account, no ETH for gas — the payment is the auth, and it's gasless (EIP-3009 transferWithAuthorization on Base).
💸 This spends real USDC. Every paid query is a live on-chain micropayment (~$0.01) from your wallet — it is not a free, read-only API, and the payment is visible on-chain and to the x402 facilitator. Quote the price first (free), and fund a dedicated, low-balance wallet — see Wallet & safety.
The loop: discover → price → query
- Discover the right live subgraph for a protocol — ranked by on-chain curation signal, so you skip dead forks.
- Price it — preflight the
402challenge to read the exact USDC cost before paying (free). - Query — send GraphQL, pay the
402from your wallet, get the data + a receipt back.
Two ways to run it
A. PayQL MCP server (turnkey)
Install and wire into your harness (Claude Desktop / Code / Cursor):
{
"mcpServers": {
"payql": {
"command": "npx",
"args": ["-y", "payql"],
"env": { "PAYQL_NETWORK": "base", "PAYQL_PRIVATE_KEY": "0xYOUR_BASE_WALLET_KEY" }
}
}
}
⚠️
PAYQL_PRIVATE_KEYcan spend its wallet's USDC. Use a dedicated, low-balance Base wallet — never a primary, valuable, or reused key. It sits in your harness config (which can be logged, synced, or screenshotted), so treat it like any secret: don't commit it or paste it in shared chats. Don't want a raw key here? Use option B (your harness's own wallet) or an Ampersend-managed wallet with spend caps.
Tools: search_subgraphs, get_payment_info (free price quote), query_subgraph (paid), get_subgraph_schema, wallet_status. Full recipe + example queries in references/gateway.md.
What ships with it
2 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.
- 2mo ago First seen · 60 lines · 134 tokens per session scan A 361934f49123
payql is a skill published in the GitHub repository PaulieB14/payql (0 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 1,083 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 2026-08-31.
payql compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| payqlPaulieB14/payql | Skill | 0 | 3mo ago | MIT | A | 134 | Claude Code, Codex |
| hyperliquidalsk1992/CloddsBot | Skill | 3.1k | yesterday | MIT | A | 19 | Claude Code, Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | yesterday | MIT | A | 13 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | yesterday | MIT | A | 11 | Claude Code, Codex |
| agentic-streetLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 91 | Claude Code, Codex |
| token-pickaeonfun/aeon | Skill | 789 | 2d ago | MIT | A | 25 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |