token-saver
Skill0 starsChanged 4 months agoNo licenceView on GitHub
עוזר לצרוך פחות טוקנים ומכסה ב-Claude Code וב-claude.ai. שני מצבים: ביקורת (בודק גודל CLAUDE.md, מספר שרתי MCP והרגלי עבודה, ומחזיר תוכנית חיסכון מדורגת לפי אימפקט) וליווי (כללי עבודה חסכוניים לסשן הנוכחי). הפעל כשמבקשים לחסוך טוקנים, לבדוק צריכה, או כשנגמרה המכסה. Helps reduce token and quota usage on Claude Code and claude.ai. Two modes: audit (checks CLAUDE.md size, MCP server count, work habits, returns a ranked savings plan) and coach (lean working rules for the current session). Trigger on "חסוך טוקנים", "אכלתי את המכסה", "בדוק לי את הצריכה", "token audit", "save tokens", "hit my limit", "reduce token usage".
24 other projects use a version of this.
Adopted by
Most recently taken up by
- swap-cameroon/kuro-antigravity-configtheir own version, first seen Nov 15, 2026
- cyberspezie/Token-Savertheir own version, first seen Nov 1, 2026
- taro1037-design/claude-skillstheir own version, first seen Oct 20, 2026
- chidekina/aria-superpowerstheir own version, first seen Oct 13, 2026
- otnc/agent-skillstheir own version, first seen Sep 27, 2026
- otnc/skills_ai-agent-saving-techtheir own version, first seen Sep 27, 2026
Other versions24 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 24
- lokikill123/codex-token-skills★ 119same name
- 4pixeltechBR/token_saver_ClaudeCode★ 14same name
- 4pixeltechBR/Token-Saver★ 14same name
- SiruGao/token-saver★ 9same name
- caiolocateli46-cell/skills-caio★ 4same name
- otnc/skills_ai-agent-saving-tech★ 3same name
- chidekina/aria-superpowers★ 2same name
- OpenWorkai/claude-token-saver★ 2same name
- otnc/agent-skills★ 2same name
- swap-cameroon/kuro-antigravity-config★ 2same name
14 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- notebooklm-py/AGENTS.mdAGENTS.md
- AI-research-SKILLs/CLAUDE.mdCLAUDE.md
- notebooklm-py/CLAUDE.mdCLAUDE.md
- find-skillsSkill
- llm-councilSkill
- notebooklmSkill
- remotion-best-practicesSkill
- rtl-hebrew-docsSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

