# Estimate Tokens

> Use this skill to approximate the LLM token count of a text before an API call, for cost/budget guarding. Averages two estimators (~4 chars/token and ~0.75 tokens/word). Deterministic, offline, no tokenizer dependency. Not exact, but reliable for gating oversized prompts.

- Skill: `ncreighton/estimate-tokens` (Agent Skill, multi-file: 10 files)
- Install (CLI): `npx skillmds@latest add ncreighton/estimate-tokens`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ncreighton/estimate-tokens/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: ncreighton (https://skillmd.com/u/ncreighton)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/ncreighton/estimate-tokens

---


# estimate-tokens

Use this skill to approximate the LLM token count of a text before an API call, for cost/budget guarding. Averages two estimators (~4 chars/token and ~0.75 tokens/word). Deterministic, offline, no tokenizer dependency. Not exact, but reliable for gating oversized prompts.

- **Kind**: analyzer  |  **Niche**: ai  |  **Cost tier**: free  |  **Version**: 0.1.0

## Empire Integration
```python
import sys
sys.path.insert(0, r'C:\D\Claude Code Projects\_SHARED')
import empire_bootstrap  # wires all shared paths
```

## Usage

**As a CLI:**
```bash
python run.py --text <string>
```

**From a Python agent (ATEN runtime):**
```python
from skill_library import executor
result = executor.execute("estimate-tokens", {text=...})
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `text` | string | yes | Text to estimate |

## Returns

`object` — `{"status": "ok"|"error", "result": ...}`