tokenleak

Overview

Every tool result an agent pulls into context is re-sent on every later call until compaction, so a 6k-token log read early in a 60-call session is paid about 55 more times. These rules make the agent let in only what the next decision needs: locate before reading, compute instead of reading data, bound command output, never re-read, batch independent calls. The upstream reports benchmark savings in its source repository; this AAS tree does not bundle those runs. Treat percentages as upstream workload-specific claims, not measured savings in the current task. Billing also depends on actual caching, token accounting and compaction behavior.

When to Use This Skill

• Use on coding tasks that read files, run tests, builds or installs, use git, or search a codebase.
• Use when the user wants to save tokens, reduce cost, or stay under usage limits.
• Use when a session keeps hitting compaction because tool output fills the context.

Rules