Stats
Actions
Tags
From prompt-engineer
Count tokens in strings or files. Trigger on: how many tokens, measure prompt length, context window fit, token budget, per-section breakdown.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prompt-engineer:token-counterThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Script: `scripts/token-count.py`
Script: scripts/token-count.py
token-count.py "some text"
token-count.py -f prompt.md
token-count.py "v1" "v2" -f base.md
token-count.py "v1" "v2" -m claude-opus-4-6 -m gpt-5-mini
token-count.py -f SKILL.md -s
| Flag | Description |
|---|---|
| (positional) | Strings to count (repeatable) |
-f FILE | File to count (repeatable) |
-m MODEL | Model or tiktoken encoding (repeatable). Default: claude-opus-4-6 |
-s | Per-section breakdown (YAML frontmatter + ## headings) |
Multiple inputs or models print a comparison table.
npx claudepluginhub 123jimin-llm/marketplace --plugin prompt-engineerEstimates input token count and response complexity, then offers a menu to choose response depth (brief, detailed, exhaustive) before answering. Use to control token consumption in Claude Code.
Estimates token usage, costs across Haiku/Sonnet/Opus, complexity levels, and time for features by analyzing codebase files/lines via Glob/Read/Grep. Use for pre-implementation planning.
Optimizes Gemini CLI token usage for bulk operations via caching, batch queries, Flash/Pro model selection, and cost tracking with bash monitoring.