Offline & deterministic
Token counts come from gpt-tokenizer — pure JS, no network, no API key.
Same input, same number, every time.
promptsize
size-limit for your LLM prompts. Count the tokens in your prompt and context files, set per-prompt budgets, and fail CI when one quietly grows past its limit.
Prompts and context templates balloon over time — a few extra few-shot examples
here, a longer system prompt there — until you blow a context window or your
per-call cost in production. promptsize treats your prompts like a build
artifact: it measures them on every PR and flags it when one crosses a line you set.
promptsize
agent system prompt Limit: 1 K tokens Size: 214 tokens (o200k_base) ✔ within budget (+38 vs baseline)
few-shot examples Limit: 8 K tokens Size: 9.2 K tokens (o200k_base) ✘ over budget by 1.2 K tokens
1 prompt over budget.Multi-model
Pick an encoding (o200k_base, cl100k_base) or a model name (gpt-4o,
gpt-4, claude-*, gemini-*). The encoding used is always printed.
Globs & grouping
Budget a single file or a whole directory of few-shot examples as one number.
Regression tracking
Snapshot sizes to a committed baseline and see the delta on every run.
Next steps
Section titled “Next steps” Quick start From zero to a working budget check in four steps.
Why promptsize How it differs from a plain token counter.