calibrating-token-estimates
Use when estimated token counts differ systematically from provider-reported usage across models, content classes, languages, or tool schemas.
Profile →npx skills add casioreview20-glitch/forge-os --skill calibrating-token-estimates --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Calibrating Token Estimates ## Core principle Record estimated and actual usage with model version and content class. Increase safety margin when uncertainty or model drift rises. The runtime owns deterministic scope, coverage, policy, and evidence checks; the agent owns only the judgment that cannot be reduced safely to code. ## Do not activate when - the provider exposes an exact offline token
What does the calibrating-token-estimates skill do?
Use when estimated token counts differ systematically from provider-reported usage across models, content classes, languages, or tool schemas.
How do I install it?
Run `npx skills add casioreview20-glitch/forge-os --skill calibrating-token-estimates --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From casioreview20-glitch/forge-os, a repository with 11 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.