capsul: minimize the tokens you send to Claude & Codex

# capsul > A command-line tool that sends Claude Code and Codex CLI only what a task needs, under a token budget you set, so an existing Claude or ChatGPT subscription lasts longer. Commercial product, not open source. Runs on macOS, Linux and Windows with Node 20 or newer. capsul drives the agent CLI you are already signed into, so your existing subscription is what answers: no API key required, no second model bill. Install with `npm i -g @penra/capsul`. ## What it is not - Not a model, not a proxy, and not a replacement for Claude Code or Codex CLI. It drives them. - Not a way to raise a usage limit. It lowers what each turn spends against one. - Not open source. There is no public source repository; npm is the distribution channel. ## Commands - `capsul` — interactive session: pick the agent, then chat. - `capsul doctor` — which agent CLIs are detected, which credentials are configured, where things are stored. - `capsul context '<task>'` — assemble the context for a task and report what it costs, without calling a model and without spending quota. - `capsul ask '<task>'` — assemble, then hand the request to the agent CLI you are signed into. - `capsul stats` — tokens saved over time, from a plain ledger file on your own disk. - `capsul burn` — local spend by agent, model and project. Useful flags: `--budget <n>` (hard ceiling on context tokens), `--open <files...>` (include named files whole), `--model <name>`, `--json`. ## Pricing - Free: 10 prompts on your own repository. No card. - Pro: EUR 5.99 per month, unlimited prompts, one person. - Team: from EUR 20.99 per month, 15 seats included, up to 30 at EUR 3.50 per extra seat; beyond that, on quote. ## Measured results Twelve models on the Claude side, five short tasks each, two arms (`claude -p` alone against capsul), 3 repetitions averaged, 360 cells measured and 0 discarded (2026-10-13), on cache-weighted input. Per-model gains run from x1.99 to x4.88, with x3.06 in the middle. Codex