I’ve been working on a small skill called Manual Orchestrator to make longer projects with AI agents easier to manage.

The problem started with a familiar situation: one chat would accumulate plans, implementation details, corrections, and test results. By the time I was ready for the next phase, I wanted a fresh conversation without losing the decisions we’d already made.

Manual Orchestrator gives that process some structure. One chat acts as the orchestrator: it breaks the work into stages and writes a prompt for the next one. I run that prompt in a new session, then bring the result back. The orchestrator reviews it against the stage’s criteria before preparing the next prompt. If something needs fixing, I go back to the same worker session.

The skill also keeps a record in the project with the current stage, decisions, evidence, and next steps. That makes it easier to pause, resume, or hand the work to another session.

The handoff is manual. I choose when to open a session and carry the result back. The orchestrator and worker sessions can also use different agent CLIs, with the prompt adapted to the capabilities available.

It’s open source and still a work in progress. I’m using it to learn what helps in practice and where the workflow needs to improve. Installation has been checked for Codex, Claude Code, and Gemini CLI, but the full workflow hasn’t been tested across every CLI or version.

If you try it, I’d be interested in hearing what works and where it gets in your way.

I like that the handoff is manual. A written record with decisions and next steps is what I miss most when a long AI chat gets messy. How do you decide when a stage is finished: with tests, or with your own review?

Would you run a command without knowing what it could do?

A copied installation script. An automated workflow. A shell command suggested by AI.

Convenient? Yes. Worth checking before execution? Absolutely.

That’s why I built SafeShell, an open-source tool for inspecting commands, applying security policies, and running permitted commands with sandboxing on Linux.

The goal: help developers and engineering teams work faster with more control over what they execute.

Explore the code, try it, and share your feedback: https://github.com/HamzaGhebriche/SafeShell

Building automation or CI/CD workflows that need stronger security controls? I’m available for freelance projects in DevSecOps, secure automation, and cloud security. Let’s talk through Contra.

Useful idea, especially for commands suggested by AI. In my deploy script every step is logged, but nothing checks a command before it runs. Can SafeShell also run inside CI, for example as a step in GitHub Actions?