OpenAI Symphony for Openclaw

An unattended orchestration service that automates Linear issue resolution through isolated workspaces and Codex integration.

ivangdavila
v1.0.0
Mar 5, 2026
0
1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install symphony

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install symphony using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is OpenAI Symphony?

OpenAI Symphony is a sophisticated orchestration engine designed for the Openclaw Skills ecosystem to handle complex software engineering tasks autonomously. It functions by reading Linear issues and creating isolated, per-issue workspaces where it drives Codex in app-server mode to implement code changes, manage state transitions, and move work toward review or completion.

This skill is built for developers who need a reliable, unattended service to bridge the gap between project management and code execution. By utilizing standardized workflow contracts and safety guardrails, it ensures that AI-driven development remains predictable, observable, and strictly bounded to authorized environments within the Openclaw Skills framework.

OpenAI Symphony Use Cases

  • Automating the lifecycle of Linear issues from triaged to review states.
  • Managing large-scale repository updates with guaranteed per-issue workspace isolation.
  • Implementing high-rigor autonomous engineering workflows in trusted environments.
  • Orchestrating Codex app-server sessions for continuous integration and delivery tasks.
  • Hardening AI agent safety through explicit environment approvals and bounded concurrency.

How OpenAI Symphony Works

  1. The skill polls the Linear GraphQL API to identify issues assigned for orchestration based on project metadata.
  2. It establishes a dedicated workspace directory for each issue to ensure zero cross-contamination between tasks.
  3. The orchestration engine initializes the environment using Git hooks and verifies credentials like GITHUB_TOKEN and OPENAI_API_KEY.
  4. It executes implementation turns by driving Codex according to the logic defined in a repository-owned WORKFLOW.md contract.
  5. Progress is monitored through state-driven orchestration, ensuring that agents only operate on active tracker states.
  6. Upon reaching a terminal state or review gate, the system preserves all evidence and logs to the run history for human oversight.

OpenAI Symphony Setup

To begin using this Openclaw Skills integration, ensure your environment is configured with the necessary API keys and binaries. Set up your authentication as follows:

export LINEAR_API_KEY="your_linear_key"
export OPENAI_API_KEY="your_openai_key"
export GITHUB_TOKEN="your_github_token"

After setting the environment variables, initialize the service by reviewing the setup.md file and creating the directory structure at ~/symphony/ to house your memory and workflow notes.

OpenAI Symphony Data Schema & Taxonomy

OpenAI Symphony maintains a structured data hierarchy within the local filesystem to ensure persistent context across Openclaw Skills sessions.

Path Purpose
~/symphony/memory.md Stores activation policies, environment profiles, and operating defaults.
~/symphony/workflow-notes.md Tracks state maps, prompt policies, and WORKFLOW.md decisions.
~/symphony/incidents.md Records runtime failures, retries, and mitigation actions for triage.
~/symphony/run-history.md A chronological log of launch evidence, validations, and release notes.

OpenAI Symphony Advanced Features

  • Per-Issue Workspace Isolation: Maps every issue identifier to a unique directory to prevent unauthorized file access or side effects.
  • State-Driven Idempotency: Supports restarts that resume from the last known state rather than repeating investigation work.
  • Safety Guardrails: Enforces explicit user approval for unattended operations and restricts hooks to deterministic, non-exfiltrating patterns.
  • Workflow Contract Validation: Ensures that all orchestration policy in WORKFLOW.md is validated before dispatch to prevent runtime halts.
  • Bounded Concurrency: Manages API rate limits and resource consumption through explicit ceilings and exponential backoff strategies.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*