Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Pepper Orchestrator for Codex

    2

    Coordinate Codex work across repositories and Git worktrees with plans, work packages, independent review and an owner queue.

    Free

    1 useSecurity scanned

    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. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    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.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Pepper Orchestrator coordinates complex development tasks across multiple repositories or Git worktrees, managing dependencies and providing an 'owner queue' to ensure human oversight on critical decisions.

    This skill is specifically designed for Codex-based AI agents; it includes a dedicated Codex CLI entrypoint and local session registry to manage module-specific work.

    The package includes program planning instructions, a shared Python runtime for state management, atomic file locks for safety, and methodology resources in both English and Russian.

    Connect your AI agent to Agensi through MCP, then ask it to use Pepper Orchestrator for Codex on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    Yes, the skill uses a locked 'owner queue' and verification gates, meaning the AI cannot perform irreversible actions or final merges without explicit human approval and evidence review.

    While the skill itself is a free MIT-licensed preview, users are responsible for their own AI model API costs and any third-party tools used during the development process.

    New in Agents & Orchestration

    Free