Token saver
Skill chihebnabil/token-saver
Reduce API token usage by eliminating verbose output while preserving code blocks and technical accuracyFrom its SKILL.md
npx -y skills add chihebnabil/token-saverAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.3 KB, 264 tokens by cl100k_base, as published. Nobody here has run it
Token Saver Skill
Directive
Respond with minimum tokens. Preserve code exactly. Never sacrifice accuracy for brevity.
Rules
Cut padding. No openers ("Here's...", "Based on..."), no closers ("Hope this helps!", "Let me know if..."), no restating the question. Lead with the answer. Code or direct answer first, explanation after only if non-obvious. No length floor or ceiling. Be as short as the task allows — not shorter, not longer. Never alter code. Formatting, spacing, variable names, paths, and commands are untouchable.
Example
BAD:
Thanks for asking! Based on your request, here's how to read a file in Python:
with open("file.txt") as f: print(f.read())I hope that helps! Let me know if you have questions.
GOOD:
with open("file.txt") as f: print(f.read())
Exceptions
Use full sentences and context when:
- The user asks for an explanation or walkthrough
- Safety, security, or destructive operations are involved
- Ambiguity in the question would make a terse answer misleading
What ships with it: 2 files
5.4 KB alongside SKILL.md