Antigravity
yuting0624/antigravity-for-claude-code
Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle.
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…
Install Token Diet
$ npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills token-diet --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/token-diet .claude/skills/token-diet && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "token-diet" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/token-diet into .claude/skills/token-diet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-diet", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/token-dietType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills token-diet --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/token-diet .agents/skills/token-diet && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "token-diet" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/token-diet into .agents/skills/token-diet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-diet", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills token-diet --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/token-diet .cursor/skills/token-diet && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "token-diet" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/token-diet into .cursor/skills/token-diet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-diet", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/token-diet--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills token-diet --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/token-diet .gemini/skills/token-diet && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "token-diet" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/token-diet into .gemini/skills/token-diet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-diet", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills token-dietInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/token-diet .github/skills/token-diet && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "token-diet" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/token-diet into .github/skills/token-diet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-diet", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills token-diet --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/token-diet .opencode/skills/token-diet && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "token-diet" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/token-diet into .opencode/skills/token-diet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-diet", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
token-diet- GitHub stars
- 1.4k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 744 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- Works in 5 steps: Level 1 — No filler (safe everywhere):… → Level 2 — Compressed prose: short… → Level 3 — Telegraphic (the caveman… → …
- Asked make the model respond tersely
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Three Levels… and Output Format, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Token Diet is an agent skill from mohitagw15856/pm-claude-skills. 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…
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Project scaffolding and LLM cost and token optimization. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked make the model respond tersely
- Cut output token costs
- Compress agent-to-agent messages
Example prompts
- “/token-diet”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Level 1 — No filler (safe everywhere): strip pleasantries, hedges, meta-commentary ("Certainly! It's worth noting that…"), restatements of…
- Level 2 — Compressed prose: short declaratives, no transitions, minimal articles where clarity survives. "Deploy failed. Cause: expired…
- Level 3 — Telegraphic (the caveman register): facts only, grammar reconstructed by the reader. "deploy fail. cert expired api-gw. rotate +…
- The economics, honestly: output tokens price at 3–5× input, so output dieting is the highest-leverage compression per effort — but the…
- The never-diet list: legal/contractual text, user-facing documents, teaching content (the scaffolding is the pedagogy), anything quoted…
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Token Diet loads about 1.5k tokens when it runs. Until then it costs about 138 tokens; SKILL.md has 744 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 744 words, ~1,467 tokens.
Download SKILL.mdSave it as
.claude/skills/token-diet/SKILL.md (or your agent's skills folder).- name
- 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 when each pays, and the never-diet list.
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:
- The use case — interactive session, agent pipeline, logging/intermediate output, or human-facing deliverable — the level (or the refusal) follows from it
- The reader — a model, a developer skimming, or an end user; models tolerate level 3, humans stop at level 1–2
- The volume shape — many turns (mode instruction amortizes; diet pays) vs. one call (it usually doesn't — say so)
Framework: The Three Levels and the Economics
- Level 1 — No filler (safe everywhere): strip pleasantries, hedges, meta-commentary ("Certainly! It's worth noting that…"), restatements of the question. ~15–25% output reduction, zero information loss, readable by anyone. This level is just good writing and has no never-diet list.
- Level 2 — Compressed prose: short declaratives, no transitions, minimal articles where clarity survives. "Deploy failed. Cause: expired cert on api-gw. Fix: rotate cert, redeploy. ETA 20min." ~30–50% reduction; fine for status updates, intermediate reasoning, developer-facing output.
- Level 3 — Telegraphic (the caveman register): facts only, grammar reconstructed by the reader. "deploy fail. cert expired api-gw. rotate + redeploy. 20min." ~50–70% reduction; for agent-to-agent messages, pipeline intermediates, and logs — places where no human reads unassisted.
- The economics, honestly: output tokens price at 3–5× input, so output dieting is the highest-leverage compression per effort — but the mode instruction rides input on every call (cheap, cacheable) and only amortizes across turns. Single-shot: skip it. And a dieted output a human must re-expand mentally didn't save tokens, it moved the cost off the bill and onto the reader — which is why deliverables stay at level 1.
- The never-diet list: legal/contractual text, user-facing documents, teaching content (the scaffolding is the pedagogy), anything quoted verbatim later, and safety-relevant instructions — ambiguity introduced by compression is a bug, and these are where ambiguity bites. The diet compresses transport, never meaning-bearing form.
Show full SKILL.md (271 more words)Show less
Output Format
Token Diet: [use case] — level [1/2/3]
The Mode Block (paste this)
[The instruction text, e.g. L2: "Respond in compressed prose: short declaratives, no filler, no hedges, no restating the question. Facts and actions only. Full grammar where ambiguity threatens."]
The Same Content, Three Ways
[One realistic paragraph at L0/L1/L2/L3 with token counts — the trade made visible]
The Economics Here
[This use case's volume × the level's reduction × output pricing — worth-it verdict in one sentence; measure with token-cost]
Never Diet
[The exclusions relevant to this user's context, named]
Quality Checks
- The level matches the reader (models get 3, humans get 1–2)
- The single-shot case was checked — and refused when the diet costs more than it saves
- The example shows the same content at multiple levels with counts
- The never-diet exclusions are stated, not implied
- Facts survive verbatim at every level — compression touched form only
Anti-Patterns
- Do not diet single-shot calls — the instruction outweighs the saving; the skill says no
- Do not ship level-3 output to humans — that's cost-shifting, not saving
- Do not let compression create ambiguity — where two readings appear, grammar returns
- Do not diet the never-diet list — legal text in telegraphese is a liability with a good ratio
- Do not confuse terse with rude in interactive use — level 1 removes filler, not courtesy where courtesy is content
Based On
The output-compression register pattern — telegraphic prompting for output-token reduction (as in Caveman and the caveman-compression method) — systematized here into levels, economics, and exclusions.
Example Trigger Phrases
- "Make the model respond tersely."
- "Cut our output token costs."
- "Switch to a compact output mode for this pipeline."
- "Strip the filler from agent-to-agent messages."
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/token-diet of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Token Diet next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Token Diet this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Antigravityyuting0624/antigravity-for-claude-code | 375 | — | ~9.1k | Automated safety check: Pass | MIT | |
| LobeHub Alint Rule Set Maintenancelobehub/lobehub | 83k | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Levyra Context EfficiencyLUC4N3X/Levyra-deepsound | 590 | — | ~1.3k | Automated safety check: Notes | GPL-3.0 | |
| Template Devlbedner/aegis-stack | 143 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Google Agents CLI Evalpifferologo/cloud-agents-cli | 129 | 1 repos | ~6.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
LobeHub Alint Rule Set Maintenance
lobehub/lobehub
Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.
Levyra Context Efficiency
LUC4N3X/Levyra-deepsound
A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…
Template Dev
lbedner/aegis-stack
A skill your agent uses when developing or modifying Copier templates in aegis/templates, or backporting a change from a generated project (e.g.
Google Agents CLI Eval
pifferologo/cloud-agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs…
Hipfire Arch Port
warpfront/hipfire
Port hipfire compute kernels to a new RDNA / CDNA architecture (gfx1201/gfx1200/gfx94x/gfx1150/etc.).
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Related
Categories
Questions about Token Diet
What does Token Diet 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…. Token Diet is an agent skill from mohitagw15856/pm-claude-skills. 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.
When should I use Token Diet?
Token Diet fits situations like: asked make the model respond tersely; cut output token costs; compress agent-to-agent messages.
How do I install Token Diet in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a claude-code`. Or copy the skill folder (skills/token-diet in mohitagw15856/pm-claude-skills) into .claude/skills/token-diet in your project. Claude Code loads it when a task matches its description.
How do I install Token Diet in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a codex`. Or copy the skill folder (skills/token-diet in mohitagw15856/pm-claude-skills) into .agents/skills/token-diet in your project. Codex loads it when a task matches its description.
Can I use Token Diet in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill token-diet -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/token-diet, .gemini/skills/token-diet, .github/skills/token-diet and .opencode/skills/token-diet in your project.
What does Token Diet need to run?
SKILL.md names no scripts, command-line tools or credentials: Token Diet is instructions for the agent only.
Does Token Diet access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Token Diet safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Token Diet use?
Token Diet is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Token Diet use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Token Diet?
Skills that share tags, products or a category with Token Diet: Antigravity (yuting0624/antigravity-for-claude-code, 375 stars), LobeHub Alint Rule Set Maintenance (lobehub/lobehub, 83k stars), Levyra Context Efficiency (LUC4N3X/Levyra-deepsound, 590 stars) and Template Dev (lbedner/aegis-stack, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Token Diet?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.