# Token Budget Check

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-everyone-needs-a-copilot-claude-copilot-token-budget-check`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Everyone-Needs-A-Copilot](https://agentstack.voostack.com/s/everyone-needs-a-copilot)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Everyone-Needs-A-Copilot](https://github.com/Everyone-Needs-A-Copilot)
- **Source:** https://github.com/Everyone-Needs-A-Copilot/claude-copilot/tree/main/templates/skills/token-budget-check
- **Website:** https://ineedacopilot.com

## Install

```sh
agentstack add skill-everyone-needs-a-copilot-claude-copilot-token-budget-check
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Token Budget Check

Analyze markdown files to ensure they comply with token budget guidelines.

## Purpose

Knowledge Copilot files have token budgets to optimize AI ingestion. This skill checks files against those budgets and suggests optimizations when over budget.

## Token Budgets by Document Type

| Document Type | Max Tokens | Max Words |
|---------------|------------|-----------|
| Skill (SKILL.md) | 2,000 | 1,400 |
| Product overview | 800 | 560 |
| Product architecture | 1,200 | 840 |
| Product API summary | 1,000 | 700 |
| Product integration | 800 | 560 |
| Operational guide | 4,000 | 2,800 |
| Agent profile | 2,000 | 1,400 |
| Index/navigation | 400 | 280 |

## Procedure

### 1. Identify Target Files

If a specific file is provided, check that file. Otherwise, scan the directory:

```bash
find . -name "*.md" -type f | head -20
```

### 2. Calculate Token Estimate

For each file, estimate tokens (words × 1.4):

```bash
file="path/to/file.md"
words=$(wc -w < "$file" | tr -d ' ')
tokens=$((words * 14 / 10))
echo "$file: ~$tokens tokens ($words words)"
```

### 3. Determine Document Type

Infer type from:
- Filename: `SKILL.md` → skill, `00-overview.md` → overview
- Path: `02-products/` → product doc, `03-ai-enabling/02-profiles/` → agent profile
- Frontmatter: `doc_type` field if present

### 4. Compare Against Budget

| Status | Condition | Action |
|--------|-----------|--------|
| OK | Under budget | Report as compliant |
| WARNING | 80-100% of budget | Suggest review |
| OVER | Exceeds budget | Analyze and suggest cuts |

### 5. If Over Budget, Analyze Content

Identify optimization opportunities:
- Prose that could be tables (30-50% savings)
- Redundant explanations
- Examples that could be shortened
- Content that belongs in linked docs

## Output Format

```markdown
## Token Budget Report

### Summary
- Files checked: N
- Compliant: N
- Warnings: N
- Over budget: N

### Details

| File | Type | Tokens | Budget | Status |
|------|------|--------|--------|--------|
| path/to/file.md | skill | 1,850 | 2,000 | OK |
| path/to/doc.md | overview | 950 | 800 | OVER (+150) |

### Recommendations

#### path/to/doc.md (950 tokens, budget 800)
- Lines 45-60: Convert feature list to table (-80 tokens)
- Lines 72-85: Remove redundant introduction (-50 tokens)
```

## Efficiency Patterns Reference

| Pattern | Token Savings |
|---------|---------------|
| Tables over prose | 30-50% |
| Bullet points over paragraphs | 20-30% |
| Omit articles in table cells | 5-10% |
| Use abbreviations (env, config, auth) | 5-10% |
| Remove redundant headers | 5-10% |

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Everyone-Needs-A-Copilot](https://github.com/Everyone-Needs-A-Copilot)
- **Source:** [Everyone-Needs-A-Copilot/claude-copilot](https://github.com/Everyone-Needs-A-Copilot/claude-copilot)
- **License:** MIT
- **Homepage:** https://ineedacopilot.com

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-everyone-needs-a-copilot-claude-copilot-token-budget-check
- Seller: https://agentstack.voostack.com/s/everyone-needs-a-copilot
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.