Agent skill · marketing growth · jeremylongshore
clade-load-scale
Scale Claude usage for high-throughput applications \u2014 batches,\
Why this skill is useful
Adds executable scripts and strategies for scaling Claude API usage that are not publicly documented.
What it needs
Requires anthropic account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Anthropic Load & Scale Overview Scale Claude usage for high-throughput applications. Covers four strategies: Message Batches (10K requests, 50% off, no rate limits), request queues with concurrency control via p-limit, tier upgrades (Tier 1-4 + Scale), and model selection for throughput (Haiku is 3-4x faster than Sonnet). Scaling Strategies Instructions Step 1: Message Batches (Best for Bulk) Step 2: Request Queue with Concurrency Control Step 3: Tier Upgrades Increase your spending to unlock higher tiers: Tier RPM Input TPM How to Qualify ------ ----- ----------- ---------------- 1 50 40K Free 2 1,000 80K $40+ total spend 3 2,000 160K $200+ total spend 4 4,000 400K $400+ total spend Scale Custom Custom Contact sales Step 4: Model Selection for Throughput Monitoring at Scale Output Batch processing configured for bulk workloads (50% cheaper, no rate limits) Concurrency-controlled request queue matching rate limit tier Rate limit tier upgraded by increasing cumulative spend Throughput metrics tracked (requests/min, tokens/min) Error Handling Error Cause Solution ------- ------- ---------- API Error Check error type and status code See clade-common-errors Examples See Message Batches example, p-limit concurrency control, Tier Upgrades table, and Monitoring at Scale metrics tracking above. Resources Rate Limits Message Batches Next Steps See clade-reliability-patterns for fault-tolerant high-scale patterns. Prerequisites Completed clade-rate-limits for understanding tier limits High-volume use case requiring more than basic tier throughput For batches: tolerance for async processing (24h SLA)
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/clade-load-scale