codex-orchestratorMonitor, control, and orchestrate background Codex sessions. Use this skill to track progress, handle interruptions, and ensure task completion for long-running coding tasks.
Install via ClawdBot CLI:
clawdbot install Microcarft/codex-orchestratorThis skill provides a workflow for supervising the Codex coding agent running in background processes.
Always launch Codex in a background PTY session to maintain interactivity without blocking the main agent.
bash pty:true workdir:<target_dir> background:true command:"codex exec --full-auto '<PROMPT>'"
sessionId.sessionId is lost, find it via process action:list.Check progress regularly (e.g., via cron or manual check).
# Get last 2KB of logs to see current status
process action:log sessionId:<id> limit:2000
Signs of life:
Edit ...).Signs of blockage:
If Codex is stuck at a prompt:
# Send 'y' and Enter
process action:submit sessionId:<id> data:"y"
# Send just Enter (default choice)
process action:submit sessionId:<id> data:""
If Codex is looping or hallucinating:
# Kill the session
process action:kill sessionId:<id>
When a significant milestone is reached or the task is done:
process action:log sessionId: limit:500 .submit.submit data:"\n" to refresh prompt) or kill/resume.If a session died or was killed:
codex resume --last or codex resume in a new background process.codex exec "task..." > codex.log 2>&1 (Note: buffering may delay output).process action:log to snapshot the buffer periodically.Generated Mar 1, 2026
Automates code refactoring and test generation in CI/CD pipelines by orchestrating Codex sessions to handle pull request reviews, generate unit tests, and apply fixes. This reduces manual intervention, accelerates deployment cycles, and ensures code quality through automated background processing.
Supervises long-running Codex tasks to convert legacy codebases to modern frameworks, such as migrating from COBOL to Java or updating deprecated libraries. The skill monitors progress, handles prompts for ambiguous code sections, and restarts sessions if stalled, ensuring efficient and error-free migration.
Orchestrates Codex to generate and optimize ETL scripts, data transformation code, and API integrations for big data projects. It tracks session logs for errors or hangs, submits inputs for configuration choices, and notifies teams upon completion, streamlining data engineering workflows.
Uses Codex sessions to automatically evaluate student coding submissions, provide feedback, and generate reports. The skill monitors for prompts requiring human judgment, submits default responses when safe, and kills sessions if looping, enabling scalable assessment in online learning platforms.
Offers a subscription-based service integrating this skill into development environments to automate code reviews, bug fixes, and documentation. Revenue comes from tiered plans based on usage volume and features, targeting enterprises seeking to reduce manual coding overhead.
Provides custom integration of the skill into client workflows, such as setting up automated testing or migration projects. Revenue is generated through project-based fees and ongoing support contracts, catering to businesses needing tailored AI orchestration solutions.
Distributes this skill as part of a marketplace where users can purchase or subscribe to pre-configured AI agent packages. Revenue comes from transaction fees on sales and subscriptions, appealing to developers looking to enhance their AI toolkits with specialized orchestration capabilities.
💬 Integration Tip
Integrate with existing CI/CD tools like Jenkins or GitHub Actions by triggering Codex sessions via API calls and using the skill's monitoring to handle failures automatically.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.