Skip to content

Suraj1235/open-dynamic-workflows / packages/zed-adapter/skills/odw

Dynamic multi-agent workflows for Zed Agent. Use when the user says "ultracode", "workflow:", "/deep-research", or wants broad multi-file work with planning, parallel execution, verification, or crash-resume.

Open Dynamic Workflows for Zed Agent

Use this skill when the user invokes /odw, says ultracode, says workflow:, or asks for large coding work that benefits from explicit planning, parallel agents, verification, budgets, or crash-resumable execution.

The ODW context server should already be available from .zed/settings.json. The bridge scripts referenced below live next to this skill in scripts/.

Step 0: Check the daemon

Run:

node scripts/daemon-bridge.js --check
  • Exit 0: use the daemon path.
  • Exit 1 with auth guidance: tell the user to copy ~/.odw/daemon.token into ODW_DAEMON_TOKEN or the host setting.
  • Exit 1 because the daemon is offline: tell the user to run odw-daemon start or odw-daemon doctor zed.

Daemon path

  1. Prefer MCP/context-server tools when available: call odw_health, then odw_run for direct execution or odw_plan first when the user wants to review the plan, the task is expensive, or mutation risk is high.
  2. If tools are unavailable but the daemon is reachable, use the local bridge:
    • node scripts/daemon-bridge.js plan "<task>"
    • node scripts/daemon-bridge.js exec plan.json
    • node scripts/daemon-bridge.js status <workflowId>
    • node scripts/daemon-bridge.js result <workflowId>
  3. Report the workflow id, topology, agent count, cost/time estimate, and final synthesized result. Do not redo the same work manually while ODW is running it.

Zed-native fallback

If the daemon is unavailable, state that full ODW requires the daemon, then use Zed Agent's native planning and editing flow:

  1. Decompose into discovery -> parallel work -> adversarial verification -> synthesis.
  2. Keep independent work items narrow and structured.
  3. Verify the result before summarizing.
  4. Ask before executing risky mutations.

Safety

  • Never include secrets in prompts, plans, logs, or workflow artifacts.
  • Respect user approval and project safety rules before mutation.
  • If ODW is unavailable, name the missing piece exactly instead of pretending the full engine ran.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall