claude-spend-guard bremst entgleisende Claude-Code-Sessions mit Kostenlimit aus
Claude Code meldet seine laufenden Kosten selbst, etwa als total_cost_usd im Stream-JSON-Format. Das Tool claude-spend-guard liest diese Ausgabe, vergleicht sie mit einem gesetzten Limit und stoppt Sessions, bevor das Budget überschritten wird.
Claude Code reports its own running cost. When run with --output-format stream-json, it emits a total_cost_usd value that claude-spend-guard can monitor. The tool reads Claude Code's stdout, parses that field, and compares it with a cap you set.
npx claude-spend-guard --cap 5 -- claude -p "refactor the auth module" Enter fullscreen mode Exit fullscreen mode When reported cumulative cost crosses the cap, the wrapper sends SIGTERM to the process group, waits for a grace period, then sends SIGKILL to anything still running. There is no dashboard, account, or server: it is a local process wrapper.
Usage dashboards such as claude-spend and claude-usage help you review spending after the fact. SDK middleware such as llm-spend-guard and budget-guard applies when your own code calls a provider API. I wanted a guard for the claude CLI process itself, including unattended terminal runs.
That scope is why the confirmed dollar-cap enforcement claim is for Claude Code. Other CLIs do not expose the same confirmed cost signal in their output, so their support uses weaker fallback modes instead of pretending the same guarantee applies.
A tool meant to stop runaway spend has to be clear when it cannot do that job. It has three visible states:
The failure mode I wanted to avoid was a tool that stops enforcing the cap but still claims it is protecting the run.
The package has no runtime dependencies. Its test suite stubs Node networking primitives and checks that the wrapper does not make network calls; a dependency blocklist also guards against adding common telemetry packages later.
Those limitations are documented in the README.
npx claude-spend-guard --cap 5 -- claude -p "your prompt" Enter fullscreen mode Exit fullscreen mode The tool is MIT licensed and runs locally. If you run Claude Code unattended, I’d like to hear which edge cases you would test first.
npm: https://www.npmjs.com/package/claude-spend-guard GitHub: https://github.com/toxot-net/claude-spend-guard