Skip to Content
IDEsWindsurf

Tokenminning in Windsurf

Windsurf (Devin Desktop) re-sends indexed snippets, pinned files, rules, MCP schemas, and Cascade history every turn. Waste shows up as long sessions, frontier defaults, and always_on rules.

Hub for the Windsurf cluster — quota, Cascade, rules, and MCP. Cognition ecosystem overlap: Devin. For the general stack see Where to start.

Quick checklist

  1. Check the usage meter — Quota & billing.
  2. Route routine work to SWE-1.5 (free on quota plans).
  3. Prefer glob/manual rules over always_on.
  4. Disable MCP you are not using (100-tool cap).
  5. New Cascade conversation per task; trim .codeiumignore.

Typical impact: 50–80% quota savings on SWE routing; 20–50% trimming rules and MCP; 30–60% less context growth from shorter sessions.

How Windsurf bills

Quota-based plans refresh daily/weekly allowances. Token cost varies by model; SWE-1.5 is free  on current self-serve plans. Enterprise may use ACUs — see Quota guide.

Cascade sends: prompt, RAG snippets, pins, rules, MCP schemas, conversation history. Command and Tab are separate from Cascade quota.

Guides

GuideWhat you’ll learn
Quota & billingDaily/weekly quota, cache reads, enterprise ACUs
CascadeSessions, pinning, .codeiumignore, @ mentions
RulesActivation modes, caps, AGENTS.md
MCPDisable servers, schema overhead, 100-tool limit

Model routing

TierWindsurf choice
RoutineSWE-1.5 / SWE-1.6 (free)
Multi-fileSonnet / mid-tier GPT
Deep debugOpus / thinking — last resort

Stay on one frontier model per task so prompt caching applies.

Last updated on