token-efficiency · superclaude-org — Claude Code skill: compressed output, fewer tokens
Switches the agent into a compressed output mode: bullets, tables, abbreviations. Useful when context runs low or the task is large.
npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -a claude-codeWhat token-efficiency does
The skill turns on ultra-compressed output. The agent drops preamble and prose around code, answering in bullets and tables instead. Common terms get shortened: fn for function, impl for implementation, cfg for config. Status markers are OK, FAIL, WARN and SKIP.
The rules are short: one sentence per concept, code blocks without explanations, no greetings or transitions. The stated target is a 30–50% token reduction against normal output while keeping information quality at 95% or above.
One caveat: compressed answers are harder to read when you are learning unfamiliar code or asking for architecture walkthroughs. This is a mode for routine work and large runs. Install it with a single npx skills add command for your platform.
What it helps with
- fit a long session inside the context window
- cut token spend on bulk edits
- get a bulleted answer instead of a wall of text
- scan statuses of many checks at a glance
- strip preamble and code explanations from replies
Example prompts for the agent
- turn on token-efficiency, context is running low
- stay in token-efficiency mode for the rest of this task
- apply token-efficiency and show the result as a table
How to install token-efficiency
1Skills CLI (Vercel)
npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -a claude-code2Manually: put the files in place
~/.claude/skills/token-efficiency/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/token-efficiency/
1Skills CLI (Vercel)
npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -a codex2Manually: put the files in place
.agents/skills/token-efficiency/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -a cursor2Manually: put the files in place
.cursor/skills/token-efficiency/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SuperClaude-Org/SuperClaude_Framework token-efficiency2Manually: put the files in place
.github/skills/token-efficiency/SKILL.md1Skills CLI (Vercel)
npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -a gemini-cli2Platform CLI
gemini skills install https://github.com/SuperClaude-Org/SuperClaude_Framework --path plugins/superclaude/skills/token-efficiencyManually: put the files in place
.devin/skills/token-efficiency/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about token-efficiency
How do I install token-efficiency in Claude?
Run npx skills add SuperClaude-Org/SuperClaude_Framework --skill token-efficiency -a claude-code. The skill lands in ~/.claude/skills/token-efficiency/SKILL.md.
What does token-efficiency do?
It puts the agent into a compressed output mode: bullets, tables, abbreviations and status markers instead of long paragraphs. The point is saving tokens without losing meaning.
When should I turn this mode on?
When context is running low, when you ask for brevity, or during a large operation with many repetitive steps.
Source text
SKILL.md · MIT
--- name: token-efficiency description: Activate ultra-compressed output mode for maximum token efficiency. Use when context is running low, user requests brevity, or dealing with large-scale operations. --- # Token Efficiency Mode Minimize token usage while preserving information quality (>=95%). ## Rules - Use bullet points and tables, never verbose paragraphs - Abbreviate common terms (fn=function, impl=implementation, cfg=config) - Use symbols for status: OK, FAIL, WARN, SKIP - One sentence per concept - Code blocks only — no prose explanations of code - Skip preamble, greetings, and transitions - Target: 30-50% token reduction vs normal output
© SuperClaude-Org · MIT · SuperClaude-Org/SuperClaude_Framework
Similar skills
All skills for Agent setup: memory, context, orchestration →token-efficiency by other authors comes first.
