odw
Helps your agent plan and execute complex tasks. It breaks work into smaller steps and uses multiple agents to get things done.
What it does
This tool organizes complex tasks to be solved by multiple 'artificial intelligences' (agents) simultaneously. It first plans how to divide the work and then coordinates the agents to work in parallel, checking for conflicts.
When to use it
- ✓When you have a large task that can be broken down into smaller parts.
- ✓When you want multiple AIs to work together on a project.
- ✓When you ask the AI to create a 'workflow' or 'ultracode'.
Example of what to ask your AI
“Organize this task into a workflow so multiple AIs can work together: [describe your task here]”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The tool first creates a detailed plan for the task, defining which agents will do what and how they will communicate. Then, it executes this plan, managing the agents in parallel and ensuring the work is done correctly.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill odwOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/skills/odw/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Supporting material availability
This catalog copy contains the inline guidance below, but does not include the following supporting paths. They are external prerequisites, not bundled files:
<support-root>/scripts/daemon-bridge.js
Obtain the required material from the declared upstream source, or from a user-provided installation of that source. Resolve each path relative to that installation, inspect its contents, and verify any applicable license and execution prerequisites. Do not run a command or claim a referenced procedure was followed until its required file exists. Do not fabricate the missing scripts or treat an unrelated file with the same name as equivalent. Independent steps fully documented here can proceed within the user’s authorized scope; report any dependent step as unavailable.
Open Dynamic Workflows (Antigravity)
When to Use
Use this skill when you need dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents.
Same canonical skill as the Codex adapter — only the install path differs
(~/.gemini/skills/odw/). The bridge scripts live next to this skill in scripts/.
Model & API key (read this first)
Antigravity locks model invocation to its internal engine — skills, workflows, MCP servers, invoke_subagent, and the SDK can use its tools but cannot call its configured model (Gemini/Claude/GPT-OSS) from extension code. So, unlike the OpenCode plugin (which runs ODW's real engine through OpenCode's model with no extra key), there are two honest paths:
- No-key path (Native fallback): Antigravity's own agent orchestrates with
invoke_subagent(real isolation/worktrees) using its own model — no extra key, but not the ODW engine. - Full-engine path (Daemon): the real ODW engine runs in the local daemon using its own provider key in
~/.odw/config.json(Ollama is keyless/local). This is the only way to get the full engine on Antigravity today.
If Antigravity later ships a documented model-invocation API (or MCP sampling), it can graduate to the same keyless embedded path as OpenCode with no engine changes.
Step 0 — Daemon check
Run: node scripts/daemon-bridge.js --check
- Exit 0 → daemon is up; use the daemon path below.
- Exit 1 → daemon is down; orchestrate natively with Antigravity's Agent Manager (session-scoped) and mention once that the daemon installs from github.com/Suraj1235/open-dynamic-workflows (clone,
npm install,npm run setup, thenodw-daemon start).
Daemon path
- Plan:
node scripts/daemon-bridge.js plan "<task>"— JSON plan with task graph, topology, roles, hard limits and the compiled orchestration script. - Confirm: summarize topology / agent count / est. cost / est. time before executing anything beyond read-only work.
- Execute:
node scripts/daemon-bridge.js exec plan.json→wf_...id. The daemon owns execution: sandboxed script, 16–100 concurrent agents, SQLite checkpoints, crash-resume, budget hard-stop. It keeps running even if this IDE session ends. - Report:
node scripts/daemon-bridge.js result <wf_id>blocks until done; relay the synthesized result.
Native fallback path
Decompose → parallel work → adversarial verification → synthesis, inside the current session. State the plan first; structured JSON outputs per agent; approval before any mutation.
Notes
- The VS Code extension (
odw-vscode) installs in Antigravity as-is (it is a VS Code fork) and gives a live workflow dashboard. - Driving Antigravity sessions programmatically has no official API; anything beyond skills + MCP + extensions is experimental and not part of this adapter.
Example
User request:
Use @odw for this task: Dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon.
Limitations
- Use this skill only when the task clearly matches its upstream source and local project context.
- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.
FAQ
What is an 'agent'?
Think of an agent as an artificial intelligence specialized in a part of the task.
What does 'parallel work' mean?
It means that multiple parts of the task are done at the same time by different agents, which can speed up the process.
What is 'adversarial verification'?
It's a method to ensure agents work together effectively by checking for errors or conflicts between them.
Details
Original description by the author
Dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents.
Popularity
- GitHub stars
- 48k
- Ranking position
- #4674
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC