token-maxxing — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited token-maxxing (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Generate as many digits of pi as possible and write them to files. Use every available output token — don't truncate early.
tokenMaxxing/ in the project root if it doesn't exist.pi-1716823401-a3f7.txt).If the user specifies N files, ask: sequential or parallel?
Sequential — loop N times, one file at a time:
Parallel — spawn N subagents simultaneously, one per file:
tokenMaxxing/ using their own random IDs (no collisions since IDs include timestamps + random suffix).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.
3.14159265358979323846264338327950288419716939937510...Plain digits only — the decimal point after 3, then continuous digits, no spaces or line breaks.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.