token-diet
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 when each pays, and the never-diet list.
npx skills add mohitagw15856/pm-claude-skills --skill token-diet --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Token Diet Skill Most of an LLM's output is grammatical scaffolding the reader's brain (or the next model in the pipeline) reconstructs for free: articles, hedges, pleasantries, "it's worth noting that." Strip it and the facts survive in 30–60% of the tokens — output reads like a telegram, and models parse telegrams fine. But the diet has real economics: output tokens cost 3–5× input, so dieting *output* pays disproportionately — while in single-shot calls the mode instruction itself costs more than it saves, and human-facing prose dieted into fragments just transfers the reading cost to a person. This skill installs the three levels, the switch lines, and the judgment about when each pays. ## What This Skill Produces - **The mode blocks** — paste-ready instruction text for each diet level, tuned to the use case - **The three levels with examples** — the same content shown at each level, so the trade is visible - **The economics** — where the diet pays (multi-turn, pipelines, agent-to-agent) and where it costs (single shots, human deliverables) - **The never-diet list** — the content classes where scaffolding IS the content ## Required Inputs Ask for these if not provided: - **Th
- What This Skill Produces
- Required Inputs
- Framework: The Three Levels and the Economics
- Output Format
- The Mode Block (paste this)
- The Same Content, Three Ways
- The Economics Here
- Never Diet
- Quality Checks
- Anti-Patterns
- Based On
What does the token-diet skill do?
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 when each pays, and the never-diet list.
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill token-diet --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.