agentleFS
Sign inStart free
DeepusleepyDeepusleepy/t3-tots/skills/t3-usage/SKILL.md

t3-usage

Skill110 starsChanged 17 days agoMITView on GitHub

Estimated T3 token usage and cost by provider, model and day. Only when the user asks: "usage", "costs", "what did I spend", "how many tokens", or the Weekly usage estimate routine. Never include it in digests or unprompted reports.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md).

    line 8
  2. Very specific:

    If it prints NO_USAGE_CACHE, ask the user to open T3's Usage view once.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md). Steps that use the box, ListMachines, routines, cards or SendToUser are Grok Bot only; other agents follow t3-tots-rules "Grok Bot only". Read-only.

  1. Run t3q.py usage on every computer. T3_DAYS defaults to 7. T3_WEEK=1 gives the calendar week from Monday. The script reads the newest usage-scan-cache*.json and usage-model-rates.json, counts each request once, and uses the cost recorded with the request when there is one, else prices it at API list rates, using the fast and ultra-fast tier rates the way T3 does.
  2. If it prints NO_USAGE_CACHE, ask the user to open T3's Usage view once. If the cache is over 12 hours old, say so first and suggest opening the Usage view to refresh it.
  3. Per computer and combined, give total tokens and the estimated cost, then by provider, the top 10 models and by day. Mark every figure as an estimate, because subscriptions aren't billed per token, and it doesn't apply custom prices set in T3. T3's Usage view has the exact figures. List the models that have no price.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free