{"slug":"mohitagw15856-token-diet","source_name":"mohitagw15856/token-diet","name":"Mohitagw15856/Token Diet","description":"Cut LLM output tokens 40–70% by stripping grammatical scaffolding while preserving every fact — telegraphic output modes, when they pay (pipelines, long sessions) and when they don't (single shots, human-facing prose), with the mode lines to switch on demand. Use when asked make the model respond tersely, cut output token costs, caveman mode, or compress agent-to-agent messages. Produces the diet-mode instruction block ready to paste, the three compression levels with examples, the economics of ","version":1,"lift":{"pass_rate_delta_pts":54.55,"pass_rate_pct":68.2,"total_cases":22,"passed_cases":15,"tokens_delta_pct":-22,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-01T19:31:10.584883+00:00"},"skill_score":0.6818,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":54.55,"with_pass_pct":68.2,"without_pass_pct":13.6,"tokens_delta_pct":-22,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-01T19:31:10.584883+00:00","run_id":"bbbc49dd-4c27-4376-9e79-fc38596dc052","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"a86ab2cf9d64dbbe64e9f59e81348828542c394dbf3b566c3409574163c1dc15","raw_url":"https://app.decimal.ai/s/mohitagw15856-token-diet/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/mohitagw15856-token-diet"}