Live survey286 models · 13 providers · 17,592 auditsAudited Using Git Worktrees · SAFE →What changedHow we verifyllms.txt

Publisher · agent skills

Agent skills by alexgreensh

alexgreensh publishes 3 audited skills on 1 repository: 2 SAFE, 0 CAUTION, 1 BLOCK.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “Agent skills by alexgreensh”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/alexgreensh

Verdicts across 3 skills

✓SAFE2!CAUTION0✕BLOCK1

Repositories

3 skills by alexgreensh · ranked by trust score, then stars

Token Dashboard

alexgreensh/token-optimizer

✓SAFE B

Answers what a past session cost ("the Garden session yesterday", a session id) with a priced number, and opens the Token Optimizer dashboard when asked to see it.

★ 2.6k89/100

Token Coach

alexgreensh/token-optimizer

✓SAFE B

Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing a slow or costly setup, or deciding which workflow steps need a model.

★ 2.6k89/100

Token Optimizer

alexgreensh/token-optimizer

✕BLOCK F

Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the saving. Use when context feels tight, sessions degrade, or costs climb.

★ 2.6k52/100

Questions about alexgreensh's skills

Are alexgreensh's skills safe?
2 of 3 are SAFE, 0 CAUTION and 1 BLOCK. Each skill is audited on its own, so check the page of the one you want.
Where do alexgreensh's skills come from?
1 repository: alexgreensh/token-optimizer (3 skills).

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.