// End-to-end autonomous task executor. Takes a task description and handles the full lifecycle: research, plan, implement, review with specialist skills, and merge via PR. Use when given a task to execute end-to-end.
Full environment variable reference for SAM. Use when adding, modifying, or documenting environment variables, configuring deployment, or working with Worker secrets. Trigger when asked about env vars, secrets, or configuration.
Full environment variable reference for SAM. Use when adding, modifying, or documenting environment variables, configuring deployment, or working with Worker secrets.
Content creation from strategy artifacts. Drafts social media posts, blog outlines, changelog announcements, product launch copy, and developer content. Trigger when asked to write social posts, blog content, announcements, launch copy, or atomize strategy docs into publishable content.
Engineering strategy and technical planning. Builds roadmaps (Now/Next/Later), technology radar, build-vs-buy analyses, and tech debt registers. Trigger when asked about roadmap planning, technology evaluation, build-vs-buy decisions, or tech debt prioritization.
Build a UI prototype for design exploration. Creates a self-contained, unauthed page in the real web app with mock data, exposes it for preview, and runs visual audits. Use when exploring layouts, information architecture, or interaction patterns before committing to production implementation.
Build a self-contained UI prototype for design exploration. Creates an unauthed page in the real web app with stress-test mock data, exposes the dev server for preview, and runs visual audits at mobile and desktop viewports. Use when exploring layouts, information architecture, or interaction patterns before production implementation.
| name | do |
| description | End-to-end autonomous task executor. Takes a task description and handles the full lifecycle: research, plan, implement, review with specialist skills, and merge via PR. Use when given a task to execute end-to-end. |
Read the full workflow from .codex/prompts/do.md and execute it.
tasks/backlog/, commit to main.claude/rules/17-ui-visual-testing.md)gh workflow run deploy-staging.yml --ref <branch>. Use $CF_TOKEN to query D1/KV/DNS directly (see .claude/rules/32-cf-api-debugging.md) to verify migrations, data state, and feature flags — this is faster and more precise than UI-based checks. Then verify changed behavior end-to-end via Playwright. For infrastructure changes (cloud-init, VM agent, DNS, TLS, scripts/deploy): MUST provision a real VM and verify heartbeat arrives. See Phase 6b in .codex/prompts/do.md.gh pr create, wait for CI, merge when green. If the user requested draft PR / do-not-merge, stop at the draft PR and do not merge.Long /do runs lose context to compaction. You MUST maintain .do-state.md (gitignored) as external memory. Re-read it before every phase. See .claude/rules/14-do-workflow-persistence.md.