Borrowing it
Nothing to install: this file belongs to 0xSoftBoi/suwappubot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xSoftBoi/suwappubot/main/.claude/skills/ethglobal-goal/SKILL.mdgit clone --depth 1 https://github.com/0xSoftBoi/suwappubotWrote 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/0xsoftboi/suwappubot/ethglobal-goal)<a href="https://agentmods.dev/skills/0xsoftboi/suwappubot/ethglobal-goal"><img src="https://agentmods.dev/badge/skills/0xsoftboi/suwappubot/ethglobal-goal/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/0xsoftboi/suwappubot/ethglobal-goal"><img src="https://agentmods.dev/badge/skills/0xsoftboi/suwappubot/ethglobal-goal.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 | $0.00089 | $0.02137 |
| Opus 5.5 | $0.00036 | $0.00855 |
| Sonnet 5.5 | $0.00018 | $0.00427 |
| Haiku 4.5 | $0.00009 | $0.00214 |
Grade A, and why
ethglobal-goal 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ethglobal-goal — Ship the Agent Swap Passport hackathon entry
Standing goal: every phase of docs/plans/ethglobal-tokyo2026-agent-passport.md implemented and
live-verified against real sandbox/testnet endpoints — not just code that parses. This targets
three ETHGlobal Tokyo 2026 sponsor tracks (World IDKit+AgentKit, Intercepta, ENSv2) by extending
Suwappu's existing agent link/claim flow (api-ts/src/routes/agent.ts), not building identity
from scratch.
How to use
/ethglobal-goal— pick the next unchecked item in phase order, re-verify its file:line anchor against current code (things drift), implement it, run the phase's live verification (not justbun run check— an external API call actually succeeding), check it off./ethglobal-goal <phase|item>— jump to a specific phase (e.g./ethglobal-goal 1or/ethglobal-goal 2.2).- "Done" for this goal means: tested live against the real World/Intercepta/ENS sandbox+testnet endpoints, not mocked. A unit test with a stubbed HTTP client does not close an item — only a real round-trip response (or a documented, unresolvable external blocker) does.
- If an item is blocked on credentials/access this session doesn't have, mark it BLOCKED ON USER with the exact secret/access needed, and move to the next unblocked item instead of spinning. Never fabricate a credential, contract address, or API response to make an item look done — that produces a demo that fails live in front of judges, which is worse than an honest blocked item.
- Goal is DONE when every box is checked or explicitly accepted as blocked-and-reported to the user; then archive this skill (delete the directory in a final commit noting completion/handoff).
Phase 0 — Credentials & unresolved API mechanics (must clear before Phase 1-3 can go live)
BLOCKED ON USER — needs secrets/access this session does not have:
- 0.1 BLOCKED (needs World Developer Portal access) — Create a World App ID + action ID at developer.world.org for IDKit; obtain sandbox verification credentials for AgentKit.
- 0.2 BLOCKED (needs a byte-level source read) — Read
./x402/DOCS.mdingithub.com/worldcoin/agentkit(orMust-be-Ash/world-x402-agentkit-examplesource directly) to confirm the exactagentkitheader payload schema. Prior research only confirmed the header name and round-trip shape. - 0.3 BLOCKED (needs Intercepta sandbox key) — Obtain an Intercepta/Web3Antivirus
X-API-KEYand the event's demo clean/risky addresses (reportedly distributed via event Discord/booth, not self-serve). - 0.4 BLOCKED (needs a funded Sepolia wallet + ENSv2 registrar access) — Register/acquire an
ENSv2 parent name on Sepolia (e.g. a
suwappu.eth-style test namespace) for subname issuance, and confirm the actual ENSv2 subname-creation call fromdocs.ens.domains/ensv2/registry+/ensv2/permissionsdirectly (NOT the ENSv1NameWrapper.setSubnodeOwnerpattern — confirmed wrong API for v2). - 0.5 Confirm current
agents.ownerUserId/POST /v1/agent/link/codeflow still matchesapi-ts/src/routes/agent.ts:4173-4236before extending it (re-verify line anchors — this plan is a point-in-time read).
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 · 114 lines · 89 tokens per session scan A 93594548dcc4
ethglobal-goal is a skill published in the GitHub repository 0xSoftBoi/suwappubot (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 89 tokens to every session and 2,137 once invoked, about $0.0004 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 2026-09-27.
Other skills, from other repositories
oneinch-aggregator
1inch DEX aggregator skill — swap tokens across 400+ DEXes, get quotes, check token approvals, Fusion+ cross-chain swaps, portfolio tracking. Requires API key from 1inch Developer Portal.
across-bridge
Bridge ETH and ERC-20 tokens across EVM chains via Across Protocol v3. One function for a quote, one function for the entire end-to-end bridge (approval + deposit + arrival verification). Use when the user wants to move tokens between chains (e.g. "bridge 50 USDC from Base to Arbitrum", "send ETH from Ethereum to…
defi-protocols
DeFi protocol authority — flashloans, AMM design, lending markets, concentrated liquidity, MEV, triangular and cross-DEX arbitrage, stablecoin depeg dynamics, and on-chain capital routing across Uniswap V3, Aerodrome, Balancer, Curve, and Aave V3 on Ethereum, Base, Arbitrum, Optimism, and Polygon.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
pump-swarm
Coordinated multi-wallet trading on Pump.fun.
trading-solana
Trade tokens on Solana DEXes - Jupiter, Raydium, Orca, Meteora, Pump.fun.