Menu

Individual skill

token-diet

0upvotes

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.

plugins/pm-tokens/skills/token-diet/SKILL.md

Read pinned source

Source commit f7c90bc09ee05dc25cf257bdb1826f2c2552c2cb

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,539
Repository last updated
Nov 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# 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:
Back to top