Prepare feature work by reading a Linear ticket and its context, checking development tools, and looking for existing implementation or pull requests. Route requested PR changes to a separate review workflow before development proceeds.
Read the input and ticket, choose the mode, run preflight, and check for existing delivery.
Review the instructions the agent will receive before you install.
You are invoked with exactly one work source:
feature_url: a Linear feature ticket, e.g.
https://linear.app/omnigent/issue/OMNI-1234. Build this feature.review_pr: a canonical GitHub PR URL for a PR this agent opened, where a
trusted human requested changes. Load the shared otto-review-remediation
skill; it takes precedence over the build phases. Preserve the scanner's
review_fingerprint and review_requests ids in the final handoff.Optional fields:
skip_push (boolean): commit locally and stop before any push or PR. It takes
precedence over a CI publisher contract.public (boolean): share this session public-read as the first preflight
action.public: true, call sys_session_share with no session_id,
user_id: "__public__", level: "read". If it returns access_denied, note
that and continue.git remote get-url origin is
omnigent-ai/omnigent, the worktree is on a fresh branch off current
main (in review_pr mode, the PR's current head branch instead), and
git, gh (gh auth status), and the test runner work.${LINEAR_API_KEY:-$DATABRICKS_LINEAR_API_KEY} (local runs set the first,
--server runs the second): title, description, comments, labels, parent,
children, and attachments. Read the parent too when there is one; a child
ticket's scope is the child itself.gh pr list --search, the ticket key, and the ticket's GitHub attachments)
and main for the feature. If it is already delivered, stop with
nothing_to_build, naming the PR or commit. If an open PR is in progress,
stop with needs_more_info naming it rather than opening a competing PR.If you can't read the ticket or reach your tooling, stop with needs_more_info
and say what is missing. Don't narrate a clean preflight.
Then load feature-requirements.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Test Omnigent’s native Antigravity integration with a live local server and the real agy CLI. Verify messages traveling between the web interface and terminal, mirrored replies, permission requests, interruption, session resumption, and process cleanup.
Test Omnigent’s Antigravity SDK integration against a live local server. Build test agents and run real conversations to check Gemini authentication, model selection, tool connections, and failures across the full execution path.
Create reference documentation directly from source code for public functions, classes, command-line commands, and endpoints. Organize parameters, defaults, return values, errors, and runnable examples, then check that the documentation matches the implementation.
Create an Omnigent agent directory using validated templates for configuration and instructions. Choose how the agent runs, then add web search, shell access, external tool connections, or subagents only when the task requires them.
Turn a selected range of commits or merged pull requests into release notes grouped by change type. Describe user-visible effects, link to supporting changes, and highlight breaking changes so readers can assess an upgrade.
Test Omnigent’s setup, help, and terminal interactions by driving the real CLI in an isolated environment. Capture rendered screens and compare checks before and after a change to establish whether a reported interface problem was fixed.