Agent skill · software engineering · jeremylongshore
mistral-rate-limits
Control Mistral demand with live workspace limits, token-aware admission, bounded retry, and backpressure. Use when handling throttling or sizing throughput. Trigger with "Mistral rate limits", "fix Mistral 429s", or "design Mistral backpressure".
Why this skill is useful
Adds executable TypeScript scripts for managing Mistral AI API rate limits and retry logic that aren't in public documentation.
What it needs
Requires typescript installed locally. Requires mistral account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Mistral Rate and Backpressure Control Overview Treat provider limits as shared workspace capacity, not constants. Admit work against measured demand, preserve deadlines and fairness, and shed load before retry storms consume remaining budget. Prerequisites Current workspace request, token, and spend limits from the Admin Panel. Per-operation deadline, priority, idempotency, and maximum-attempt policy. Metrics for admitted, queued, throttled, retried, completed, and abandoned work. Current Contract Mistral documents workspace-shared limits across API keys and reports current dimensions in the Admin Panel. Limits vary; never encode a numeric example as a default. Authentication Limit telemetry excludes keys, prompts, responses, and files. Admin inspection requires separate authorized identity. Instructions 1. Capture current workspace limits and evidence time as observations. 2. Measure demand by operation, model, requests, tokens, and concurrency. 3. Define shared admission buckets and bounded queues with tenant fairness. 4. Honor explicit retry timing; otherwise use capped jitter only for safe transient failures. 5. Stop when deadline, attempt, token, or spend budget ends; return typed overload. 6. Load-test locally, then canary approved traffic and compare queue/SLO evidence. Tool Discipline Use Read, Glob, and Grep to inspect code, locks, configuration, tests, and evidence. Use Write and Edit only for approved repository changes. Invocation alone does not authorize network calls, paid usage, uploads, stateful resources, admin mutations, deployments, or deletion. Approval Boundaries Require approval for live load, limit increases, capacity changes, or fallback models. Additional keys do not create independent capacity. Error Handling Per-process limiters oversubscribe shared capacity across replicas. Retries after the user deadline waste tokens and worsen overload. Fallback changes quality, residency, context, and cost. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/mistral-rate-limits