Geo Pipeline

If you're running GEO workflows on OpenAI Codex CLI, this orchestrates the seven-stage recomby-geo pipeline that would normally be slash commands in Claude Code. It routes intake, visibility audit, content gap analysis, brief creation, draft production, distribution, and monthly re-audits through their spec files while enforcing stage dependencies and validation. The key design choice is deliberate: it will not auto-fill expert content slots in briefs. That human checkpoint at stage 04 is load-bearing, and production won't run until an expert marks the brief ready. Useful if you need the GEO workflow on Codex but want to keep stage logic DRY across both CLI environments.

GitHub stars: 415
last updated: Jun 9, 2026

View on GitHub

Install

$ npx -y skills add recomby-ai/recomby-geo --skill geo-pipeline --agent claude-code

Installs into .claude/skills of the current project.

Files

geo-pipeline — Codex orchestrator for recomby-geo

On Claude Code each stage is a bare slash command (/01-intake … /07-reaudit). Codex CLI has no bare custom commands, so this skill is the Codex entry point: it carries the orchestration rules and routes to the per-stage specification files, which are the single source of truth shared with the Claude Code side. Do not duplicate stage logic here — read the stage file and follow it.

Per-stage specs (read the one you're running): commands/01-intake.md, commands/02-audit.md, commands/03-gap.md, commands/04-content-brief.md, commands/05-production.md, commands/06-distribution.md, commands/07-reaudit.md (relative to this plugin's root). Full directory convention + dependency graph: orchestrator/run.md.

How to run a stage on Codex

Identify the client folder clients/<slug>/ and the stage the user wants.
Read the matching commands/0X-*.md and execute its Procedure verbatim.
Validate every JSON artifact the stage writes against its schema before moving on (Codex has no built-in schema validation — run it explicitly):

SKILL.md on GitHub