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 OOBE-PROTOCOL/sap-mcp --skill sap-perpspad-toolsgit clone --depth 1 https://github.com/OOBE-PROTOCOL/sap-mcpWrote 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/oobe-protocol/sap-mcp/sap-perpspad-tools)<a href="https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-perpspad-tools"><img src="https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-perpspad-tools/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/oobe-protocol/sap-mcp/sap-perpspad-tools"><img src="https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-perpspad-tools.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 | $0.00000 | $0.01757 |
| Opus 5.5 | $0.00000 | $0.00703 |
| Sonnet 5.5 | $0.00000 | $0.00351 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
sap-perpspad-tools 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PerpsPad Launchpad Tools
Use this skill for sap_perpspad_* tools: the PerpsPad permissionless
launchpad where every coin is backed by a live leveraged perp position. The
token is the wrapper — the treasury holds the backing perp for the life of
the token and its PnL + fees drive buybacks and burns. No API key: the
creator wallet is the identity.
First Steps
- All reads are FREE — call directly, no x402 challenge. The launch builder
is BUILDER tier (run
sap_estimate_tool_costfirst for paid runtimes). - Check available markets and leverage caps before building a launch:
sap_perpspad_get_markets(e.g. BTC 1-40x, SOL/ETH 1-25x, OIL 1-20x, XRP 1-15x, HYPE/ZEC/BNB 1-10x, memecoins 1-3x). - Platform health check:
sap_perpspad_get_statsreturns SOL price, live / graduated counts, OI, raised USD, burn events, leaderboards.
Launch Flow (canonical)
sap_perpspad_get_markets— pick the underlying market, verify its leverage cap.sap_perpspad_build_launch— returns tokenId, mint, configAddress, poolAddress, protocolFeeSol, and the TWO UNSIGNED transactions (config+pool, base64). This tool does NOT broadcast.- Sign and send BOTH transactions from the creator wallet — config first,
then pool. The wallet pays rent, the dev-buy, and the 0.01 SOL protocol
fee; it is also the dev-buy recipient. Hosted runtimes: pair with
sap_payments_finalize_transaction. Sponsored/Steve-OS runtimes sign locally with the user wallet. - Poll
sap_perpspad_get_launch_statuswith tokenId untilstatus: live. The launch is promoted server-side when the pool confirms on-chain — no callback, and a signed transaction alone does NOT mean the launch is live.
Tools — full parameter reference
sap_perpspad_get_markets (FREE)
No parameters. Returns {markets: [{symbol, minLeverage, maxLeverage}]} —
60 markets live at integration time (BTC 40x, ETH/SOL 25x, OIL 20x,
XRP 15x, HYPE/ZEC/BNB 10x, ANSEM 3x).
sap_perpspad_get_tokens (FREE)
| Param | Type | Required | Notes |
|---|---|---|---|
| sort | enum | no | newest (default), oldest, raised (most SOL raised first) |
| limit | number | no | page size |
| offset | number | no | paging |
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.
- 1mo ago First seen · 140 lines · 0 tokens per session scan A d5f0833d5304
sap-perpspad-tools is a skill published in the GitHub repository OOBE-PROTOCOL/sap-mcp (3 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,757 tokens. 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 2026-09-16.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
marginfi
MarginFi — Solana lending and borrowing.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.