---
title: "workflow"
description: "How to work: weigh problems in proportion, think before building, fix corrections as classes, failure classes to check, project tooling, changelogs and when to ask"
canonical: https://agentpluginsdirectory.com/plugins/workflow--georgelubaretsi
last-updated: 2026-10-10
---

# workflow
How to work: weigh problems in proportion, think before building, fix corrections as classes, failure classes to check, project tooling, changelogs and when to ask
- Slug: workflow--georgelubaretsi
- Publisher: George Lubaretsi
- Repository: https://github.com/georgelubaretsi/omp-drawer
- Manifest: plugins/workflow/plugin.json
- Version: 0.1.0
- License: MIT
- Category (editorial): other
- Skills: 1 (failure-classes)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-10-08
- Repository last pushed: 2026-10-09
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/workflow--georgelubaretsi
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What workflow does, in the publisher's words

Rules and a skill on how to work, for any project.

The skill failure-classes lists ten general failure classes, each with its members and how to test them.

Codex code review doesn't load plugins. To give it the same bar for findings as the reviewer agent, paste the text of rules/proportion-review.md (below its frontmatter) into ChatGPT Settings > Code Review, and paste it again when this plugin's changelog says that rule changed. OpenAI documents the setting for reviews started in the ChatGPT app; check that your GitHub reviews follow it too.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/georgelubaretsi/omp-drawer/HEAD/plugins/workflow/README.md