open-dynamic-workflows
Plan, orchestrate, and adversarially verify parallel AI coding agents with a dynamic multi-agent workflow engine.
- License 许可
- MIT
- 最近更新
- 2026-08-07
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- open-dynamic-workflows
- risk
- critical
- tags
- [ "multi-agent", "orchestration", "workflow", "adversarial-verification", "coding-agents" ]
- tools
- [ "claude", "cursor", "codex", "gemini", "antigravity" ]
- author
- Suraj1235
- source
- community
- license
- MIT
- category
- ai-agents
- date_added
- 2026-06-06
- description
- Plan, orchestrate, and adversarially verify parallel AI coding agents with a dynamic multi-agent workflow engine.
- source_repo
- Suraj1235/open-dynamic-workflows
- source_type
- community
- license_source
- https://github.com/Suraj1235/open-dynamic-workflows/blob/main/LICENSE
03 SKILL.md 正文
Open Dynamic Workflows
Overview
Open Dynamic Workflows (ODW) is an open-source dynamic multi-agent workflow engine for AI coding agents such as OpenCode, Codex, Antigravity, and VS Code. It lets you plan a task, orchestrate multiple agents working in parallel, and adversarially verify their output before it lands. ODW ships a Codex/Antigravity skill folder (SKILL.md plus a daemon bridge) and an OpenCode plugin, and it is bring-your-own-model (Anthropic, OpenAI-compatible, or Ollama). This skill is adapted from the community project at Suraj1235/open-dynamic-workflows.
When to Use This Skill
- Use when you need to decompose a coding task into independent subtasks and run multiple agents in parallel.
- Use when working across more than one AI coding tool (OpenCode, Codex, Antigravity, VS Code) and want a single orchestration layer.
- Use when the user asks for adversarial review or verification of agent-generated changes before merging.
How It Works
Step 1: Plan
ODW takes a high-level goal and produces a dynamic workflow graph of subtasks, identifying which can run in parallel and which have dependencies.
Step 2: Orchestrate
The engine dispatches subtasks to parallel agents through the OpenCode plugin or the Codex/Antigravity daemon bridge, using your configured model provider (Anthropic, OpenAI-compatible, or Ollama).
Step 3: Adversarially Verify
Completed work is routed through an adversarial verification pass that challenges the output before results are synthesized and returned.
Examples
Example 1: Run a parallel workflow
ODW is installed from source (clone the repo, then npm install). The CLI is
odw-daemon — run it as npm run odw -- <args> from inside the repo, or as
npx odw-daemon <args> / a global odw-daemon if you link the bin.
# Configure your model provider (bring-your-own-model)
export ANTHROPIC_API_KEY=... # or an OpenAI-compatible / Ollama endpoint
# One-time setup: generate ~/.odw/config.json
npm run setup
# Start the local workflow daemon (once)
npm run odw -- start
# Plan, orchestrate, and verify a task across parallel agents
npm run odw -- run --prompt "refactor the auth module and add tests"
Example 2: Use the Codex/Antigravity skill bridge
# ODW ships a SKILL.md + daemon bridge consumed by Codex / Antigravity.
# Start the daemon, then run a saved orchestration script through it:
npm run odw -- start
npm run odw -- run --script examples/workflows/studio-prime.workflow.js --cwd .
Best Practices
- ✅ Scope each subtask so agents can run without shared state.
- ✅ Keep the adversarial verification pass enabled before merging agent output.
- ❌ Don't run interdependent subtasks in parallel without declaring their dependencies.
- ❌ Don't commit provider API keys; use environment variables or a secrets manager.
Limitations
- This skill does not replace environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, or safety boundaries are missing.
Security & Safety Notes
- ODW executes agent-generated code and shell commands; run it only in an authorized, local, or sandboxed environment.
- Model provider credentials (Anthropic / OpenAI-compatible / Ollama) must be supplied via environment variables, never committed to source.
- Review adversarial-verification output before applying changes to a production branch.
Common Pitfalls
- Problem: Parallel agents collide on the same files. Solution: Give each subtask exclusive file/module ownership and run conflicting tasks sequentially.
Related Skills
@multi-agent-orchestration- When coordinating multiple agents on one goal.@code-review- How adversarial verification complements human review.
04 同仓库更多 Skills
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
stop-slop
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like writing.
ogilvy-copywriting
Apply David Ogilvy's advertising principles when writing or reviewing copy, headlines, product descriptions, landing pages, ads, emails, or any persuasive text. Use when the goal is copy that sells, not copy that wins awards. Covers positioning, headlines, promises, brand voice, long-form copy, and visual logic. Source: How to Create Advertising That Sells (1972) + Ogilvy on Advertising.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.