Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rohitg00/token-efficiency
Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
Passed 17 of 21 test cases with the skill, and 9 of 21 without it.
and 10 more in the full report
10 fixed9 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
Extract the API rate limit tier from this log snippet: `[INFO] User 102 logged in from IP 192.168.1.1`. The snippet does not specify a rate limit.
| Checked | Without skill | With skill |
|---|---|---|
| Returns null or UNKNOWN for the missing field | Missed | Passed |
| Does not guess or fabricate a rate limit tier | Passed | Passed |
The instructions your model reads when the skill loads.
Reduce output token waste and prevent iteration cycles that consume context.
Use when:
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. |
Set explicit budgets by task complexity:
| Task Type | Tool-Call Budget | Wrap-Up At |
|---|---|---|
| Quick fix / lookup | 20 calls | 15 |
| Bug fix | 30 calls | 25 |
| Feature (small) | 50 calls | 40 |
| Feature (large) | 80 calls | 65 |
| Refactor | 50 calls | 40 |
| Exploration / research | 30 calls | 25 |
At the wrap-up threshold: commit progress, assess remaining work, decide whether to continue or start fresh.
test cases passed, vs 9 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.