Token maxxing
Reusable skills for your AI agents: better judgement, tighter responses, and production-grade patterns. Make your agents think, not just comply.
npx -y skills add nateslabach/skills --skill token-maxxingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 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 author says it does
Copied from the file, not written here
Generates as many digits of pi as possible and writes them into files inside a tokenMaxxing/ folder. Use when the user asks to token-maxx, fill a file with pi digits, test agent output throughput, or generate N pi files sequentially or in parallel.
SKILL.md
1.8 KB, as published. Nobody here has run it
token-maxxing
Generate as many digits of pi as possible and write them to files. Use every available output token — don't truncate early.
Default (one file)
- Create
tokenMaxxing/in the project root if it doesn't exist. - Generate a random file ID: use a timestamp + 4-character random suffix (e.g.,
pi-1716823401-a3f7.txt). - Write as many digits of pi as possible into the file. Fill the output — do not stop early to be polite.
- Report the filename and digit count when done.
Multiple Files
If the user specifies N files, ask: sequential or parallel?
Sequential — loop N times, one file at a time:
- Each iteration: new random ID, full digit output, write to file.
- Report a summary at the end: files created, total digits written.
Parallel — spawn N subagents simultaneously, one per file:
- Each subagent runs the default single-file flow independently.
- Subagents write to
tokenMaxxing/using their own random IDs (no collisions since IDs include timestamps + random suffix). - Report all filenames and digit counts when all agents complete.
Pi Generation
Generate digits by recall and/or computation. Use as many digits as you can produce — the goal is maximum output per file. If you can write a script to compute additional digits via BBP formula or similar, do it and append the output.
File Format
3.14159265358979323846264338327950288419716939937510...
Plain digits only — the decimal point after 3, then continuous digits, no spaces or line breaks.