Kody Agent Skills

Clean up leftover code, schema, shims, dual-writes, compatibility aliases, feature flags, and docs after a migration or similar change. Use when you introduce transitional leftovers, leave a deprecated path, need a soak or follow-up migration before dropping something, or are finishing a migration runbook. Remove the leftover in the same change when it is safe; otherwise open a GitHub issue so it is not forgotten.

Coordinate a fleet of cloud agents across separate environments for large multi-track programs (migrations, purges, upgrades). The conductor audits, partitions, spawns one agent per track, monitors, and QAs — but implements nothing. Use only when work needs multiple environments; otherwise load orchestrate or implement directly.

Drive and verify the Kody app with a Feature Map and one CLI. Use when changing UI, account routes, preview deploys, or proving a Cloud Agent change with a real origin, session, and /health SHA.

Orchestrate sub-agents for large tasks inside a single environment: plan, delegate coding to cheap/fast models, parallelize the critical path, keep reviews lean, and close every loop. Use when acting as an orchestrator or writing a kickoff for one. Prefer implement when fan-out does not clearly pay. For multi-environment fleets, use conduct instead.

Discover, wait for, sign in, create specific user data, and assert a PR preview deploy. Use on medium or high risk PRs, after pushing a ready-for-review PR, or when the user asks to test the preview URL.

Build and review Remix 3 applications using the `remix` npm package and subpath imports. Use when working on Remix app structure, routes, controllers, middleware, validation, data access, auth, sessions, file uploads, server setup, UI components, hydration, navigation, or tests.

Review data, issues, code, and git history; present options with effort; recommend one path and name the right fix (explain if they differ). Use before implementing when a decision needs evidence-backed options.

Babysit a PR: iterate with AI reviewers and CI until green, get it ready, optionally squash-merge as Kody and watch the deploy, then send a Discord summary. Medium risk waits for AI reviewer(s) and addresses valid feedback. Use when a pull request needs to be shepherded to done.

How to run and test kody's multi-worker local dev (origin kody worker + kody-platform + kody-runtime + kody-jobs secondary configs), including known wrangler multi-config pitfalls (secondary worker env-name suffix, remote AI binding, .env secrets not propagated) and how to verify runtime-worker forwarding.

Generate and maintain the system recap block in a PR description - a GitHub-rendered visual summary of which system primitives a change touches, how risky it is, and what changed. Prefer mermaid sequence diagrams for the change; pick another graph type when it explains the diff better. Use when planning a non-trivial change (plan mode), when creating or updating a pull request (recap mode), or when the user asks for a visual recap, visual plan, system review, or PR recap.