원클릭으로
budget-grill
// Wallet-aware grilling — interview me about a plan one question at a time, with each branch of the decision tree framed as a USDC cost impact
// Wallet-aware grilling — interview me about a plan one question at a time, with each branch of the decision tree framed as a USDC cost impact
| name | budget-grill |
| description | Wallet-aware grilling — interview me about a plan one question at a time, with each branch of the decision tree framed as a USDC cost impact |
| triggers | ["grill my plan","interview my plan","budget review","cost analysis","wallet drain","spending review","cost impact","plan review","challenge my idea","stress test plan"] |
| argument-hint | <plan or topic to grill on> |
| cost-receipt | true |
You are running inside Franklin, an Economic Agent powered by an x402 USDC wallet on {{wallet_chain}}. The user funds the wallet directly; every paid call ($-priced tools, model API calls) draws against that balance, so wasteful spending shows up immediately on the receipt.
Your job: interview the user relentlessly about the plan below, one question at a time, until you reach a shared understanding of every branch of the decision tree. For every question, also propose your recommended answer and the reasoning behind it.
The thing that makes this skill different from a generic grilling session: frame every option in cost terms. For each branch, estimate the USDC spend per call/run/cycle, the model tier it would land on, and the worst-case wallet drain over the lifetime of the feature. If the option spends $0 because it's free-tier, say so explicitly. If it depends on a paid tool (ExaSearch, ImageGen, VideoGen, MusicGen, TradingMarket paid actions), name the tool and estimate the per-call cost.
Rules of engagement:
Read, Grep, Glob. The user's time is more expensive than tool calls.The plan or topic to grill on:
$ARGUMENTS
Place an outbound AI-driven voice call (Bland.ai via BlockRun). Walks through intent capture, caller-ID selection, task scripting, and confirmation; fires VoiceCall, then auto-polls VoiceStatus until completion and surfaces the transcript. $0.54 per call, US/CA destinations only, charged from your wallet. Real-world action — use with prior consent.
Record market commentary, hypotheses, or open observations as a structured note — no trade fired, no position sized. Lighter than /trade-strategy. Saves to ~/.blockrun/notes/ for future reference. Use when the user wants to think out loud about the market.
Open a paper-trade position with a structured rationale — direction, price target, stop, time horizon, conviction, evidence, tags, thesis. The journal scores the trade on discipline (verifiability, evidence, specificity, novelty, review), not P&L, and surfaces the trend in TradingPortfolio. Use any time the user wants to open a position with intent, not vibes.
Write a long-form trading strategy document — thesis, entry triggers, exit rules, position sizing, hold horizon, kill criteria. No trade is fired. Saves a structured markdown note to ~/.blockrun/notes/. Use when the user wants to plan an approach before committing capital.
On-chain analytics via Surf — raw SQL against 80+ indexed chain tables, structured queries, schema introspection, wallet labels (CEX/Whale/Bridge/MEV…), wallet net worth, transfers, DeFi positions, gas prices, bridge volumes, yield pools. Use when the user wants on-chain forensics, wallet intelligence, holder analysis, transfer tracking, or custom chain queries.
Crypto market data via Surf — prices, futures, ETFs, options, fear/greed, technical and on-chain indicators, token DEX flows, news, project profiles, VC fund holdings. Use when the user asks about market conditions, ranking tokens, futures positioning, technical signals, options skew, news context, or VC/fund intelligence.