Agent skill · marketing growth · jeremylongshore
lindy-cost-tuning
Optimize Lindy AI costs through credit management, model selection,
Why this skill is useful
Provides specific strategies for optimizing costs in a credit-based AI model, which the AI wouldn't reliably generate on its own.
What it needs
Requires lindy account access. About 4k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Lindy Cost Tuning Overview Lindy uses a credit-based pricing model. Every task costs credits based on model size, step count, premium actions, and duration. Cost tuning targets: model right-sizing, agent consolidation, trigger optimization, and credit monitoring. Prerequisites Lindy workspace with billing access Multiple active agents to evaluate Dashboard access to review per-agent task history Credit Cost Reference Factor Credits -------- --------- Basic model task (Gemini Flash) 1-2 Mid-tier model (GPT-4o-mini, Claude Haiku) 2-5 Large model task (GPT-4, Claude Sonnet) 5-10 Premium model (Claude Opus) ~10+ Phone call (US/Canada) ~20/minute Phone call (international) 21-53/minute Premium actions (webhooks) Additional per action Minimum per task 1 credit Plan Costs Plan Monthly Credits Per Extra Seat ------ --------- --------- ---------------- Free $0 400 N/A Pro $49.99 5,000 $19.99 Business $299.99 30,000 Included Enterprise Custom Custom Custom Instructions Step 1: Audit Agent Credit Consumption For each active agent, collect: 1. Task count (last 30 days) — from Tasks tab 2. Average credits per task — total credits / task count 3. Model used — from agent settings 4. Trigger frequency — how often the agent fires Create a cost audit table: Agent Tasks/Month Credits/Task Model Monthly Credits % of Total ------- ------------ ------------- ------- ---------------- ----------- Support Bot 500 5 Claude Sonnet 2,500 50% Lead Router 200 2 GPT-4o-mini 400 8% Report Gen 30 10 GPT-4 300 6% Step 2: Right-Size Models The highest-impact optimization. For each agent, ask: "Does this task actually need GPT-4/Claude, or would Gemini Flash work?" Current Setup Optimized Savings -------------- ----------- --------- Email classify with Claude Sonnet (5 cr) Gemini Flash (1 cr) 80% Data extract with GPT-4 (10 cr) GPT-4o-mini (3 cr) 70% Simple routing with Claude Opus (10 cr) Gemini Flash (1 cr) 90% Test the downgrade: Run 10 tasks with the smaller model. Compare output quality. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/lindy-cost-tuning