Token Efficiency

If you've watched Claude burn through tokens with "Great question!" openers and unnecessary file re-reads, this skill codifies the discipline to stop it. It enforces anti-sycophancy rules (no preambles, no closing fluff), sets hard budgets on tool calls by task type, and mandates read-before-write so you're not paying for the same file three times. The one-pass coding rules are especially sharp: read everything including tests first, write the complete solution, run tests once, and if they pass, stop immediately. No polishing, no refactoring passing code. Adapted from drona23's token-efficient patterns, this is less about prompt tricks and more about operational discipline that actually cuts 40-60% waste if you enforce it.

skills.sh installs: 239
GitHub stars: 2.9K
last updated: Jun 8, 2026

View on GitHub

Install

$ npx -y skills add rohitg00/pro-workflow --skill token-efficiency --agent claude-code

Installs into .claude/skills of the current project.

Files

Token Efficiency

Reduce output token waste and prevent iteration cycles that consume context.

Trigger

Use when:

Sessions feel expensive or slow
Output is verbose with filler text
Claude is re-reading files or iterating unnecessarily
Setting up a new project for token-efficient work

Anti-Sycophancy Rules

These patterns waste 30-60% of output tokens:

Pattern	Example	Fix
Sycophantic opener	"Sure! Great question!"	Delete. Lead with answer.
Prompt restatement	"You're asking about X..."	Delete. Answer directly.
Closing fluff	"Let me know if you need anything!"	Delete. Stop after the answer.
Unsolicited suggestions	"You might also want to..."	Delete unless asked.
AI disclaimers	"As an AI model..."	Delete entirely.
Verbose preambles	"I'll help you with that..."	Delete. Start with the action.