- Home
- Skills
- Agents & Orchestration
- Pepper Orchestrator for Codex
Works with the AI Agents you already use
Pepper Orchestrator for Codex
Coordinate Codex work across repositories and Git worktrees with plans, work packages, independent review and an owner queue.
Free
About this skill
One coordinator for a multi-repository program
Pepper Orchestrator 0.11.0 is a free, MIT-licensed preview for Codex. It turns a program spanning several repositories, or parallel areas of one repository, into explicit work packages, dependencies, locks, evidence and decisions.
The coordinator plans and records program state. Independent module sessions implement the work in their own repositories or worktrees. Review and verification compare the actual PR, commit and test evidence before a task is accepted. The owner queue keeps decisions and privileged actions visible.
Included
- Program initialization, planning, dispatch, review, verification and recovery instructions.
- Shared Python runtime, templates, state management, atomic IDs and file locks.
- Dedicated Codex CLI entrypoint, local session registry, queue/App Server transport and templates for native scoped roles.
- English and Russian methodology resources.
Install and start
Extract the ZIP into ~/.agents/skills/, preserving the complete top-level folder. Restart the agent and ask: “Use Pepper Orchestrator. Initialize a Codex program for these repositories, then prepare a plan.” This is a standalone Codex skill package; it includes its shared scripts and references.
The owner launches module sessions using the prepared commands. Read the bundled runtime contract before operating a program. Install one copy per host; avoid simultaneously installing this ZIP and the same skill from a marketplace.
Validation and scope
Package/frontmatter checks passed. The shared packaged runtime passed 11 local regression tests covering IDs, locks, recovery, project instructions and Codex worktrees. The dedicated entrypoint resolves its bundled workflow and runtime locally. These are package and runtime checks, not a recorded end-to-end multi-repository release.
This is a 0.11 preview. It does not provision accounts, authorize MCP services or grant production access. Irreversible actions require the owner’s explicit decisions and the workflow’s gates. Free download; model usage and optional third-party tools may have their own costs.
Preview release. Full interactive account/MCP/browser permissions and a real module PR lifecycle are not established by local package checks. Mixed clients and multiple hosts are outside v1 scope; owner-launched module sessions are required.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Permissions
Uses local Git/workspace files and Python. GitHub PR/CI operations require gh and authenticated GitHub access. Browser or MCP access is needed only when explicitly configured for a work package; credentials are not included.