Filters and compresses shell command output such as git, test runs and builds before a coding agent reads it, via hooks for Claude Code, Cursor, Codex and Gemini CLI.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Git Output Compaction
Use RTK to rewrite git status, diff and log output: ‹what you need›
- API Traffic Proxy
Use RTK to run the optional rtk-proxy daemon: ‹what you need›
- Agent Hook Setup
Use RTK to install a hook: ‹what you need›
Install the CLI
brew install rtk-ai/tap/rtk
Setup guide: rtk-ai.app/docs/getting-started/quick-start
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLI
- Auth
- None
- Skills
- 5
Skills
Git Output Compaction
Rewrites git status, diff and log output into compact summaries grouped by state, keeping hash, author and subject only.
Test Failure Filtering
Filters cargo test, npm test, pytest and go test output down to failures, collapsing passing tests into a single count.
Agent Hook Setup
Installs a hook with rtk init that rewrites an agent's shell commands to rtk equivalents in Claude Code, Cursor, Codex and more.
Output Analytics
Reports how much command output was filtered with rtk gain, as summaries, daily breakdowns, ASCII graphs or JSON exports.
API Traffic Proxy
Runs the optional rtk-proxy daemon, which compresses an agent's provider-API payloads before forwarding them to the model provider.