openwork

Add a new feature, put work behind a feature flag, roll something out (per organization, for everyone, cloud or self-hosted), revert or kill a feature, or make a big change to existing behavior such as a new engine. Use BEFORE writing the feature code, and when finishing or removing a rollout.

Local OpenWork Electron browser automation with CDP. Use when driving a local Electron dev app, browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests.

Flag customer, prospect, partner, or outside-person identities in the diff. Reported in the Warden security summary.

Connect the OpenWork MCP Gateway (https://api.openworklabs.com/mcp/agent) to Claude Code, Codex, Gemini CLI, Cursor, VS Code, Claude Desktop, or ChatGPT so the agent can use the user's OpenWork organization skills, plugins, and connections.

Screen a pull request from an outside contributor for hidden, obfuscated, or supply-chain-risky changes before any of its code runs.

Create an OpenCode plugin for OpenWork. Scaffolds the plugin file with the correct API shape, tool definitions, and hook registration. Use when the user asks to 'create a plugin', 'write a plugin', or 'make a plugin that does X'.

Daytona CLI setup, sandbox debugging, keep a sandbox alive, secrets volume, snapshot refresh. Use when Daytona itself is the problem, not for running tests (see run-tests).

Daytona seeded cloud demo, demo credentials, Acme Robotics seed. Use when the user asks to spin up, keep running, seed, or prepare an OpenWork Cloud/Den Daytona demo instance.

test on Windows, enterprise CA, corporate certificate, GPO cert, TLS fetch failed, Windows sandbox, daytona windows, self-hosted cert. Use when validating OpenWork Windows enterprise TLS/OS-trust fixes in a Daytona Windows sandbox.

Warn when user-facing UI changes drift from DESIGN.md. Advisory only; findings never gate Warden clearance.

Flag desktop<->den contract drift introduced by this diff. High findings gate Warden clearance; medium findings are advisory only.

Test is red, typecheck failed, CI job failed, flaky, timed out, was this already broken. Use to classify any failing check before changing code or calling it pre-existing.

Flag only new security issues introduced by this diff. Reported in the Warden security summary.

Drive the running OpenWork app over CDP from the shell, headless by default (nothing opens on screen). Evaluate JS, take screenshots, open a new session, send a prompt with a chosen model, wait for the run to finish. Use when checking a UI change by hand in a world or pnpm dev, or when reproducing a chat state.

Make the desktop's model provider fail on demand (connection refused, DNS not found, socket reset, 429, 5xx, 401, 402, stalled or cut stream) with a local fault server and test providers. Use when reproducing or designing model error and retry states without a real outage.

Design notes on a PR, "Design review (advisory)" in the evidence check, "worth fixing", layout.split-row, OW-LIST, a reviewer says the UI looks off. Use to read what the design review found on a PR's screenshots, fix it in code, and prove the note is gone.

get an env var, fetch a secret, missing env var, missing token/API key, load secrets from Infisical, infisical. Fetch secrets from the team's Infisical workspace into the shell environment so subsequent commands can use them.

A user saw internal_error, "Unexpected server error", a 500, or an opaque failure in a shipped OpenWork build. Find the cause from local logs and Sentry, name the regressing PR, file the issue, and reply where it was reported.

Install the free OpenWork desktop app on macOS, Windows, or Linux and get the user to a first task. Use when someone wants OpenWork, an open-source Claude Cowork alternative, on their own computer.

Measure whether the chat jumps while a turn runs by sampling the Working line's position over CDP and counting upward moves. Use when changing step rows, live status lines, folding, or anything that can shrink content during a run.