Updated
On this page
Complete CLI reference for claudestream — all available commands, subcommands, flags, arguments, and usage examples with detailed descriptions.
#claudestream CLI Reference
Stream Claude Code's JSON protocol
Version: 0.14.2
#Commands
- send -- Send a prompt to Claude and display the complete response with events
- stream -- Stream a prompt with real-time incremental token-by-token output to stdout
- events -- Debug mode: display all raw JSON protocol events from the subprocess
- repl -- Start an interactive multi-turn read-eval-print loop session with Claude
- ask -- Send a prompt to Claude and print only the final response text
- doctor -- Check claudestream environment health: binary, version, and profile
- config -- Show resolved configuration including binary path and version
#Command Groups
- agent -- Manage and run agents defined in .agent.json files. Agent definitions declare a model, prompt template, allowed tools with input schemas, sandbox permissions, and budget limits (cost, turns, tokens). Use subcommands to validate configurations, run agents against prompts, and inspect metadata.
#Framework flags
These flags are owned by the strictcli framework, not by the app. No command may declare a flag with one of these names, and each is recognized anywhere on the command line.
| Flag | Effect |
|---|---|
--dry-run | Preview mode: no mutation runs. The framework prints a log of every effect the command would have performed. |
--approve-consequential | Skips the confirmation prompt a consequential command shows before it runs. |
--quiet | Hides informational output. Warnings, errors, structured data and the dry-run log are never suppressed. |
--verbose | Shows debug output. --quiet wins when both are passed. |