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 rezearcher/x402-data-api --skill x402-defi-data-skillgit clone --depth 1 https://github.com/rezearcher/x402-data-apiWrote 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/rezearcher/x402-data-api/x402-defi-data-skill)<a href="https://agentmods.dev/skills/rezearcher/x402-data-api/x402-defi-data-skill"><img src="https://agentmods.dev/badge/skills/rezearcher/x402-data-api/x402-defi-data-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/rezearcher/x402-data-api/x402-defi-data-skill"><img src="https://agentmods.dev/badge/skills/rezearcher/x402-data-api/x402-defi-data-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 | $0.00168 | $0.02018 |
| Opus 5.5 | $0.00067 | $0.00807 |
| Sonnet 5.5 | $0.00034 | $0.00404 |
| Haiku 4.5 | $0.00017 | $0.00202 |
Grade A, and why
x402-defi-data scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://x402-data-api.sigrunner.workers.dev/defi/yields/preview How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision-tagged DeFi & trading data an agent can pay for by the call
Most market feeds hand an agent a wall of numbers and leave the judgment to it: is this 40% APY real yield or a decaying emission that collapses next week? Is this funding spread a carry trade or noise inside one thin venue? This skill calls a hosted x402 API that returns the data already scored — every yield row carries a verdict, every funding set carries an arb verdict — so the agent acts on a decision, not a feed.
No API key, no account, no SDK required. Free previews and a small daily trial are keyless; the full paid call settles inline in USDC on Base via x402.
The four routes
| Route | Price | What it returns |
|---|---|---|
GET /defi/yields |
$0.001 | DeFi pool yields, each row tagged verdict (SUSTAINABLE / DECAYING / OUTLIER / AVOID) + risk_score, risk-adjusted APY, and a provenance trajectory (how the APY has actually moved since first tracked). Filter with ?chain=arbitrum etc. Returns each pool's DefiLlama pool id — feed it to the next route. |
GET /defi/yield-entry-verdict?pool=<id> |
$0.01 | The deep go/no-go for one pool you're about to enter: a packaged SUSTAINABLE / DECAYING / OUTLIER / AVOID verdict + 0-100 risk_score, field-cited reasons, a predicted class with probability, risk-adjusted APY, IL risk, and σ. This is the "should I put capital in this LP" answer, not a list to re-judge. |
GET /crypto/funding |
$0.004 | Perp funding across Hyperliquid, OKX, dYdX, Binance, Bybit, Gate — with open_interest_usd per venue, an OI-weighted funding_spread_bps, best_long_venue / best_short_venue, and a signal (LONGS_PAY / SHORTS_PAY). Thin venues are excluded from the arb verdict, not silently averaged in. |
GET /crypto/prices |
$0.001 | Token spot prices with a confidence, 24h change, and a provenance block (tracked-since, tick count, and the recent value trajectory) so a price is auditable, not a bare number. |
What ships with it
1 file 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 · 128 lines · 168 tokens per session scan A fbbb7d5c8944
x402-defi-data is a skill published in the GitHub repository rezearcher/x402-data-api (0 stars, last pushed today), licensed MIT. It adds 168 tokens to every session and 2,018 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.
x402-defi-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| x402-defi-datarezearcher/x402-data-api | Skill | 0 | today | MIT | A | 168 | Claude Code, Codex |
| pantheon-stakingBankrBot/skills | Skill | 1.2k | 2d ago | none | A | 59 | Claude Code, Codex |
| delu-oracleBankrBot/skills | Skill | 1.2k | 2d ago | none | A | 87 | Claude Code, Codex |
| CTRLaaronjmars/aeon-agent | Skill | 12 | 22d ago | MIT | A | 46 | Claude Code, Codex |
| aero-vote-radararaxis33/aero-vote-radar | Skill | 3 | yesterday | MIT | A | 84 | Claude Code, Codex |
| base-agent-treasurygblinproject/gblin-treasury-risk-regime | Skill | 1 | yesterday | MIT | A | 62 | Claude Code, Codex |
| jit-redemption-patterngblinproject/gblin-treasury-risk-regime | Skill | 1 | yesterday | MIT | A | 60 | Claude Code, Codex |