executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
mistral-migration-deep-diveMigrate an existing model workload to Mistral through semantic mapping, dual-run evaluation, bounded canary, and provider rollback. Use when re-platforming from another provider. Trigger with "migrate to Mistral", "move from OpenAI to Mistral", or "compare a workload with Mistral".
Independent GitHub snapshot · Automated classification · Original documentation governs
Treat migration as behavior and operations redesign, not field renaming. Preserve the application contract while re-evaluating models, prompts, streams, tools, safety, state, data, spend, and incidents.
Chat, embeddings, classifiers, files/OCR, audio, batch, Workflows, and Public Preview stateful APIs are provider-specific. No source feature, model, tool, safety result, or state object is automatically equivalent.
Keep source and Mistral credentials in separate secret references with independent owners. Dual-run data must be approved for both providers.
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.
Dual submission, customer data, new spend, preview APIs, production routing, state copying, source shutdown, or credential deletion require approval.
Return source/target contract matrix, gaps, evaluation, data/spend delta, canary, reconciliation, cutover, rollback, and source exit.
Run identical golden, adversarial, timeout, stream, tool, tenant, and outage cases; verify cutover and rollback.