agent-wormhole/SKILL.md
Use Agent Wormhole for one-time sealed handoffs between autonomous agents, including encrypted mission briefs, scoped secrets, temporary artifacts, receipts, config drops, CLI/API usage, ECHO holder access, and Bankr x402 paid opens.
npx skillsauth add bankrbot/skills agent-wormholeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Agent Wormhole opens a temporary encrypted passage for agent handoffs. The payload can be claimed once, then the channel collapses.
This skill executes the @builtbyecho/agent-wormhole npm package. Before running any agent-wormhole or npx @builtbyecho/agent-wormhole command for the first time in a session, tell the user:
About to install/run
@builtbyecho/agent-wormhole(v0.1.2) from npm. It is an encrypted one-time-handoff CLI that writes payloads to a local.agent-wormholes/directory and (for holder/paid opens) callsstorage.builtbyecho.xyzand the Bankr x402 endpoint. It does NOT sign transactions or access private keys.Proceed? (y/n)
Wait for explicit confirmation before the first invocation. Subsequent calls in the same session do not need to re-prompt.
Pin the version when invoking via npx:
npx -p @builtbyecho/[email protected] agent-wormhole <args>
https://www.builtbyecho.xyzhttps://www.builtbyecho.xyz/agent-wormhole.htmlhttps://github.com/BuiltByEcho/agent-wormholehttps://www.npmjs.com/package/@builtbyecho/agent-wormholehttps://www.builtbyecho.xyz/skills/agent-wormhole/SKILL.mdUse this skill when a task involves:
agent-wormhole CLI or HTTP APIFrom a project that has the package installed:
agent-wormhole send --text "mission brief" --ttl 10m
agent-wormhole send --file ./artifact.tgz --note "handoff bundle"
agent-wormhole inspect <code>
agent-wormhole receive <code> --out ./received
agent-wormhole cleanup --delete-claimed-older-than 15m
For one-off use without installing globally:
npx -p @builtbyecho/[email protected] agent-wormhole send --text "mission brief"
id.secret.id locates stored metadata.secret derives the AES-256-GCM decrypt key and is not stored.access.path = local.50,000,000 ECHO on Base and record access.path = echo_holder.agent-wormhole-open and record access.path = x402_paid.https://storage.builtbyecho.xyz/agent-wormholehttps://x402.bankr.bot/0x2a16625fad3b0d840ac02c7c59edea3781e340ae/agent-wormhole-openhttp://127.0.0.1:8791From the package root:
npm test
node --check src/cli.js
node --check src/index.js
node --check src/server.js
npm pack --json --dry-run
For live health:
curl -sS https://storage.builtbyecho.xyz/agent-wormhole/health
For Bankr status, check both registry and execution:
bankr --config "$BANKR_OWNER_CONFIG" x402 list
bankr x402 schema https://x402.bankr.bot/0x2a16625fad3b0d840ac02c7c59edea3781e340ae/agent-wormhole-open
bankr --config "$BANKR_PAYER_CONFIG" x402 call -X POST -d '{"payload":"dGVzdA=="}' --max-payment 0.01 -y --raw https://x402.bankr.bot/0x2a16625fad3b0d840ac02c7c59edea3781e340ae/agent-wormhole-open
Set BANKR_OWNER_CONFIG to the endpoint owner/operator config and BANKR_PAYER_CONFIG to a separate payer config. Do not treat registry active status alone as proof that paid x402 execution works. A real paid call from a non-owner wallet is the proof.
tools
HSM-backed secret management for AI agents. Store API keys (including Bankr `bk_` keys), passwords, and credentials in an encrypted vault; retrieve them at runtime via MCP without keeping secrets in chat context. Policy-based access control, secret rotation, sharing, EVM transaction intents (sign/simulate/broadcast), multi-chain signing keys, treasury multisig proposals, OIDC federation for external service auth, built-in prompt injection detection, and optional Shroud TEE LLM proxy. Use when the agent needs secure credential storage, just-in-time secret access, guarded on-chain signing, or security scanning — not for Bankr trading prompts, portfolio checks, or x402 calls (use the bankr skill instead).
testing
Stake $GEM tokens on Gem Miner (gemminer.app) to earn yield and unlock the in-game earn/cashout system. Use when the user wants to stake GEM, check their staking balance or rewards, unstake, claim rewards, or check whether they meet the 25M GEM gate. Base mainnet only.
development
CodeGrid is a native macOS canvas where multiple coding agents (Claude, Codex, Gemini, Cursor, Grok, shells) run side by side in panes and collaborate via a local agent bus — no tmux, no cloud, no account, no stored API keys. Install this skill when an agent should know how to operate inside a CodeGrid pane, drive the workspace from outside (control socket or codegrid:// deep links), spawn or message sibling agents, or coordinate multi-agent work (delegate, review, pipeline, parallel fan-out, monitor, debate). The differentiator: multiple coding agents collaborating on one canvas, addressable by stable session_id, with a read → message → read protocol built for orchestration.
testing
Non-custodial perpetual DEX on Arbitrum. Use when user says buy, sell, trade, long, short, open position, close position, flip trade, set leverage, deposit USDC, withdraw funds, check balance, view positions, cancel order, copy a thesis, publish trade on-chain, check leaderboard, top traders, Rep Score, market intel, crypto news, funding rate, thesis, analyst feed, who's winning on Nexus.