agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/discovery/skills/token-estimator-mvp/SKILL.md

token-estimator-mvp

Skill286 starsChanged 6 months agoMITView on GitHub

Estimate AI planning ranges from a work description or explicitly authorized safe project context. Provides coarse class ranges or conditional planning bases without requiring token guesses.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for first-pass AI planning guidance.

    line 8
  2. Distinctive:

    Use only the bundled CLI or API with calibration and profiles.

    line 11
  3. Distinctive:

    Leave unknown facts unknown.

    line 21
  4. Distinctive:

    Run the estimator with sanitized JSON:

    line 24

≈ “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

Token estimator MVP

Use this skill for first-pass AI planning guidance. It is not a scientific execution service.

Use only the bundled CLI or API with calibration and profiles. Never invent formulas or ask users for token budgets.

Procedure

  1. Identify the deliverable from the request. Context is optional.
  2. Map to the input guide and contract, version 1.2.0.
  3. Leave unknown facts unknown. Provide conditional bases when supported.
  4. For "run an existing workflow," use existing-workflow-operation.
  5. Count shared setup/checks once. Separate independent review as its own task.

  6. Run the estimator with sanitized JSON:

    node scripts/estimate.js --input examples/coarse-prediction.json
  7. Report status, mapping, assumptions, uncertainty and exclusions.

Package notes

Copy this entire directory to skills/token-estimator-mvp/ in the target repository. Keep files relative and project-local. No installs, credentials, network access, or external authoring workspace are required.

See examples for supported scenarios.

Run tests:

node --test tests/model.test.js tests/phases.test.js tests/operations.test.js tests/behavior.test.js tests/packaging.test.js tests/skill-guidance.test.js

This package ships provisional community reference ranges. They are planning heuristics requiring broader community validation and are not statistical bounds or evidence of customer outcomes.

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