code-judo
v0.1.0Strict quality review and architecture deepening: deep-review, deepen-architecture, codebase-design, and domain-modeling skills.
By PrasLicense: MIT0 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 4 skill or MCP entries
- Source updated
- Oct 4, 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 code-judo for Codex and Claude Code
codex plugin marketplace add pulseai-labs/claude-agent-scaffolding
codex plugin marketplace upgrade claude-agent-scaffolding-codex
codex plugin add code-judo@claude-agent-scaffolding-codexPaste and run these commands in a terminal with Codex. They add and refresh the claude-agent-scaffolding-codex catalog, then install this plugin.
Compatibility: the page URL and API slug “code-judo” remain stable.
- Codex:
code-judo@agent-plugin-marketplace→code-judo@claude-agent-scaffolding-codex
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/pulseai-labs/claude-agent-scaffoldingClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is code-judo/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/codebase-design/SKILL.md├── skills/deep-review/SKILL.md├── skills/deepen-architecture/SKILL.md└── skills/domain-modeling/SKILL.md
Included Skills4
Shared vocabulary and principles for designing deep modules. Use when designing or improving a module's interface, deciding where a seam goes, judging whether an abstraction earns its keep, making code more testable or easier for an agent to navigate, exploring two competing interfaces for the same problem, or when another skill needs the deep-module vocabulary. Triggers on "design this module", "where should the seam go", "is this abstraction earning its keep", "explain this codebase's seams", "design it twice", "deep module", "shallow module", "deletion test".
An unusually strict maintainability review of a branch or diff — abstraction quality, giant files, spaghetti growth, boundary leaks — pushed toward ambitious restructurings that delete complexity rather than rearrange it. Human-invoked only. Use for a deep code quality audit, a strict or harsh maintainability review, a code-judo pass over a branch, or "review this diff for structure, not bugs".
Scan a codebase for deepening opportunities — shallow modules that should become deep ones — present them as a visual HTML report opened in the browser, then grill through whichever candidate the user picks. Human-invoked only. Use for an architecture review of a codebase, "where is this codebase shallow", "find refactors worth doing", "improve the architecture here", or a proactive deepening scan.
Build and sharpen a project's domain model as you design. Use when discussing what a codebase's terms actually mean, when a term is fuzzy or overloaded, when writing or editing a CONTEXT.md glossary, or when an architecture decision is worth recording as an ADR — which this skill composes and hands to whoever owns the ADR directory rather than filing itself. Triggers on "what do we call this", "that term is overloaded", "add this to the glossary", "write a CONTEXT.md", "should this be an ADR", "record this decision", "domain model", "ubiquitous language".
Plugin manifests2
{
"name": "code-judo",
"version": "0.1.0",
"description": "Strict quality review and architecture deepening: deep-review, deepen-architecture, codebase-design, and domain-modeling skills.",
"author": {
"name": "Pras"
},
"repository": "https://github.com/pulseai-labs/claude-agent-scaffolding",
"license": "MIT",
"keywords": [
"code-review",
"architecture",
"refactoring",
"maintainability",
"skills"
],
"skills": "./skills/",
"interface": {
"displayName": "Code Judo",
"shortDescription": "Strict quality review and architecture deepening.",
"longDescription": "Code Judo reviews a diff for maintainability with an unusually strict bar, and scans a codebase for shallow modules worth deepening. It is ambitious about structure: it hunts for restructurings that delete complexity rather than rearrange it. Ships the deep-module design vocabulary and a domain-modeling discipline the other two skills speak.",
"developerName": "Pras",
"category": "Coding",
"capabilities": [
"Interactive",
"Read",
"Write"
],
"defaultPrompt": [
"Deep review this branch for structure, not bugs.",
"Where is this codebase shallow?",
"Is this abstraction earning its keep?"
],
"websiteURL": "https://github.com/pulseai-labs/claude-agent-scaffolding/tree/main/code-judo",
"brandColor": "#0F766E"
}
}{
"name": "code-judo",
"version": "0.1.0",
"description": "Strict quality review and architecture deepening. Four prose skills: deep-review (human-invoked maintainability audit of a diff — code-judo ambition, the 1000-line rule, spaghetti growth, boundary leaks — producing one report and one categorical disposition pass, never a loop), deepen-architecture (codebase scan for shallow modules, single HTML report with before/after diagrams and strength badges, then a grilling loop), codebase-design (the deep-module vocabulary), domain-modeling (CONTEXT.md glossary where nothing else owns it; composes ADRs, does not file them). Skill-first; no lib, no hooks, no state.",
"author": {
"name": "Pras"
}
}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.
[code-judo on Agent Plugins Marketplace](https://pluginsmp.com/plugins/code-judo)