ult
v1.0.0Ultivis workflow baseline with natural-language routing, focused engineering skills, and scenario-driven UX review.
By UltivisLicense: MIT1 GitHub starsUpdated 2 days ago
Directory evidence
- Runtimes
- Codex
- Parsed components
- 15 skill or MCP entries
- Source updated
- Sep 22, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install ult for Codex
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add ult@agent-plugin-marketplacePaste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/ultivis-iot/claude-code-setupClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is codex/plugins/dev-workflow/.
Plugin files
├── .codex-plugin/plugin.json├── skills/codebase-design/SKILL.md├── skills/diagnosing-bugs/SKILL.md├── skills/domain-modeling/SKILL.md├── skills/grill-me/SKILL.md├── skills/grilling/SKILL.md├── skills/handoff/SKILL.md├── skills/improve-codebase-architecture/SKILL.md├── skills/research/SKILL.md├── skills/resolving-merge-conflicts/SKILL.md├── skills/tdd/SKILL.md├── skills/teach/SKILL.md├── skills/ultivis-flow/SKILL.md├── skills/ux-review/SKILL.md├── skills/wayfinder/SKILL.md└── skills/writing-great-skills/SKILL.md
Included Skills15
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Build a reproduction loop for uncertain, recurring or performance bugs. Use for investigation and hypothesis testing; a known local correction does not require the full loop.
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
A relentless interview to sharpen a plan or design.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Compact the current conversation into a handoff document for another agent to pick up.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Investigate a question against high-trust primary sources and capture cited findings. Use when the user wants a topic researched, documentation or API facts gathered, or claims verified.
Use when you need to resolve an in-progress git merge/rebase conflict.
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Build a multi-session learning course in a dedicated teaching workspace. Use for guided lessons and learning records, not a one-off explanation in a software repository.
Baseline workflow and query router for repositories using this setup. Use for planning, implementation, GitHub/Notion Story and Task work, validation, commits, PRs, reviews, or whenever a focused engineering overlay should be selected from the user's natural-language request.
Design role-based scenarios, preserve successful or failed Playwright WebM journey evidence, evaluate product-native usability and accessibility, and produce either reviewed or directly requested guide recordings. Use for evidence-backed UX audits and training guides, not generic code review or one-off screenshots.
Plan a huge, foggy, multi-session effort as a shared map of tickets, then resolve them one at a time until the route is clear — confirmed work hands off to implementation on the same ticket and its issue-keyed branch, never a new record.
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
Plugin manifests1
{
"name": "ult",
"version": "1.0.0",
"description": "Ultivis workflow baseline with natural-language routing, focused engineering skills, and scenario-driven UX review.",
"author": {
"name": "Ultivis",
"url": "https://github.com/ultivis-iot/claude-code-setup"
},
"homepage": "https://github.com/ultivis-iot/claude-code-setup",
"repository": "https://github.com/ultivis-iot/claude-code-setup",
"license": "MIT",
"keywords": [
"workflow",
"codex",
"validation",
"pr",
"notion",
"ultivis"
],
"skills": "./skills/",
"interface": {
"displayName": "Ult",
"shortDescription": "Ultivis workflow and engineering skill router",
"longDescription": "Keeps ultivis-flow as the lifecycle baseline and routes natural-language work to focused skills for TDD, diagnosis, research, design, architecture, wayfinding, UX review, conflict resolution, and productivity.",
"developerName": "Ultivis",
"category": "Coding",
"capabilities": [
"Interactive",
"Read",
"Write"
],
"websiteURL": "https://github.com/ultivis-iot/claude-code-setup",
"privacyPolicyURL": "https://github.com/ultivis-iot/claude-code-setup",
"termsOfServiceURL": "https://github.com/ultivis-iot/claude-code-setup",
"defaultPrompt": [
"Use the ultivis-flow skill to validate and commit this change.",
"Use ultivis-flow to choose the best overlay for this request.",
"Create a PR after validation passes.",
"Check my Ultivis tasks and start work."
],
"brandColor": "#1F6FEB"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[ult on Agent Plugins Marketplace](https://pluginsmp.com/plugins/ult)