Suraj1235/open-dynamic-workflows / packages/codex-adapter/skills/ultracode
ultracode
VerifiedUltracode-style dynamic workflows for Codex. Use when the user says "ultracode", "workflow:", "/deep-research", or asks for broad multi-file work with planning, parallel agents, verification, or crash-resume.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.6 KB |
SKILL.md
View on GitHub---
name: ultracode
description: Ultracode-style dynamic workflows for Codex. Use when the user says "ultracode", "workflow:", "/deep-research", or asks for broad multi-file work with planning, parallel agents, verification, or crash-resume.
---
# Ultracode Through Open Dynamic Workflows
This is the Codex-facing ultracode alias for Open Dynamic Workflows. It uses the same local ODW daemon, MCP tools, and native fallback as the `odw` skill, but gives users the expected ultracode entrypoint.
## Step 0: Check the daemon
Run:
```bash
node scripts/daemon-bridge.js --check
```
- Exit 0: use the daemon path.
- Exit 1: say exactly what is missing (`odw-daemon start` or `odw-daemon doctor codex`) and use Codex-native planning only if useful.
## Daemon Path
1. Plan with `node scripts/daemon-bridge.js plan "<task>"`.
2. If the task is expensive or mutation-risky, show the topology, agent count, estimated cost/time, and ask before execution.
3. Execute with `node scripts/daemon-bridge.js exec plan.json`.
4. Monitor with `node scripts/daemon-bridge.js status <workflowId>` and finish with `node scripts/daemon-bridge.js result <workflowId>`.
5. If MCP tools are available, prefer `odw_health`, `odw_plan`, `odw_run`, `odw_status`, `odw_result`, and `odw_list` over shell bridge calls.
## Native Fallback
If ODW is unavailable, be explicit that full ultracode power requires the daemon, then decompose into discovery -> parallel work -> adversarial verification -> synthesis using Codex-native capabilities.
Never include secrets in prompts, plans, logs, or workflow artifacts.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |