Skip to content
Back to skills

Tokens

ASecurity

Show token usage and estimated cost per model from your local AKA store

  • 11 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added August 31, 2026
ai-agentsbashnode

Works with

  • cli

Security analysis

A100/100

Scanned August 31, 2026

npx -y skills add akasecurity/ai-tc --skill tokens --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tokens?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Tokens
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/akasecurity-tokens/badge)](https://www.skillsdirectory.com/skills/akasecurity-tokens)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: aka-tokens
description: Show token usage and estimated cost per model from your local AKA store
---

# AKA tokens

Run the read script and show the user its output **exactly as printed**. The
script already prints its content inside a Markdown code fence — reproduce that
verbatim and do **not** add another code fence, strip the fence, or reformat it.
The fence is required: it is space-aligned monospace (a per-model usage table)
that Markdown would otherwise collapse. Do not reformat or summarize the table;
you may add at most one short sentence of context after it.

```bash
node "${PLUGIN_ROOT}/scripts/query.js" tokens
```

This reads the local store at `~/.aka/data/aka.db` (token counts reconciled from
your Antigravity CLI rollout files, grouped by provider/model, with estimated USD cost).
It is read-only. Token counts are exact; cost is **derived** at read time — a `—`
means unknown pricing (a local or non-OpenAI model/gateway), so a `≥` total is a
lower bound, not an understatement. If the store is empty, the script says so —
relay that as-is; nothing is wrong.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.