condux
v2.32.0Codex skills for lean agentic workflow: tier routing, discovery, design mockups and diagrams, plan drafting, tests-first, subagent coordination, finalize, live verification, code review, preflight, root-cause debugging, interactive plan review, and feature spec management.
By jabworksLicense: MIT1 GitHub starsUpdated 3 days ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 15 skill or MCP entries
- Source updated
- Sep 20, 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 condux for Codex and Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install condux-2@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
Compatibility: the page URL and API slug “condux-2” remain stable.
- Codex: Legacy selector
condux-2@agent-plugin-marketplaceremains documented for migration; install from source for this runtime.
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.
Codex has another source with the same manifest name. This directory does not invent numbered install aliases; use the publisher's catalog or inspect the source manually for that runtime.
Get the source manually
git clone https://github.com/jabworks/agentic-toolkitClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is dist/plugins/condux/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/blueprint/SKILL.md├── skills/code-review/SKILL.md├── skills/condux-doctor/SKILL.md├── skills/discovery/SKILL.md├── skills/draft-plan/SKILL.md├── skills/finalize/SKILL.md├── skills/live-verification/SKILL.md├── skills/plan-review/SKILL.md├── skills/preflight/SKILL.md├── skills/root-cause-analysis/SKILL.md├── skills/subagent-deployment/SKILL.md├── skills/subagent-execution/SKILL.md├── skills/technical-spec/SKILL.md├── skills/test-first-development/SKILL.md└── skills/workflow/SKILL.md
Included Skills15
Produce dependency-free visual clarity artifacts at design time — HTML wireframes and full renders for UI screens and flows in the house design language (surface-kit tokens), and inline-SVG system diagrams (data models, flows, architecture, state machines) for backend work.
One-shot code review. Produces a diagnostic report categorized by severity (Critical / Important / Minor). Never fixes issues automatically.
Health check for the condux plugin on the host it is installed on. Runs the SessionStart routing hook on both hosts and checks each wire format, confirms Codex's hooks flag is on and plan-review's Stop hook resolves, checks the OpenCode registration and its bundled agents and skills, verifies the four specialist agents shipped, compares the installed version against the marketplace clone, and flags conflicting skill libraries installed. Offline; read-only unless --fix.
Refine a rough idea into a signed-off design, presented in sections for sign-off before any planning or code begins. Opens with the requirements — the feature PRD — and feeds the tech spec, written via technical-spec at sign-off.
Turns a signed-off design into an executable plan of lean task cards (what, why, gotchas, dependencies). Writes Markdown; review in the browser via plan-review.
End-of-task quality gate — typecheck → lint → format → tests. Runs in order, once. Stops on first failure and fixes before continuing.
Verify a change by actually running it — drive the real UI or endpoint, check each claim against observed behaviour, and capture evidence before pushing.
Render a plan in a local browser for inline annotation, then return an approve / request-revisions / deny decision to the agent. Auto-captured via a Claude Code ExitPlanMode or Codex Stop hook, or run manually on a markdown file or spec directory.
Lightweight "am I actually done?" checklist before calling /finalize. Prevents premature completion — catches skipped steps, missing behavior, and silent regressions.
Enforces root-cause-first bug investigation — read the error, reproduce it, trace the data flow backward. Never propose a solution before the investigation phase completes.
Fan out 2+ independent tasks across named agents (explorer/researcher/planner/coder) in a single message when they share no files and no dependencies. For ad-hoc independent work discovered outside a formal plan.
Execute a plan using named specialist agents. Default is to implement yourself — only spawn when there is a concrete justification.
Persists feature requirements, decisions, API contracts, implementation details, and quirks into a structured, queryable spec tree — one folder per feature, one file per concern.
Tests-first development — write tests before implementation. Opt-in only: one upfront consent (write tests first + auto-run), then run the cycle without re-asking.
Routes any dev task into the right execution tier (Small/Medium/Large) and carries condux's operating rules — proportional effort, lazy skill loading, soft gates, implement-yourself-by-default.
Plugin manifests2
{
"name": "condux",
"version": "2.32.0",
"description": "Codex skills for lean agentic workflow: tier routing, discovery, design mockups and diagrams, plan drafting, tests-first, subagent coordination, finalize, live verification, code review, preflight, root-cause debugging, interactive plan review, and feature spec management.",
"author": {
"name": "jabworks"
},
"repository": "https://github.com/jabworks/agentic-toolkit",
"license": "MIT",
"keywords": [
"workflow",
"condux",
"tier",
"finalize",
"live-verification",
"discovery",
"blueprint",
"mockup",
"wireframe",
"diagram",
"test-first-development",
"code-review",
"preflight",
"subagent",
"planning",
"draft-plan",
"debugging",
"root-cause-analysis",
"spec",
"technical-spec",
"plan-review",
"doctor",
"health-check"
],
"skills": "./skills",
"hooks": "./hooks/codex-hooks.json",
"interface": {
"displayName": "Condux",
"shortDescription": "Lean agentic workflow skills.",
"longDescription": "Condux gives Codex a tiered workflow system — Small, Medium, or Large — with lean task cards, opt-in tests-first, on-request code review, and a single end-of-task quality gate. No runaway reviews, no mid-task tests, no monstrous plans.",
"developerName": "jabworks",
"category": "Productivity",
"defaultPrompt": [
"Route this task with /workflow.",
"Finalize this implementation.",
"Code review before merging.",
"Is condux working on this machine?"
]
}
}{
"name": "condux",
"version": "2.32.0",
"description": "Claude Code skills for lean agentic workflow: tier routing, discovery, design mockups and diagrams, plan drafting, tests-first, subagent coordination, finalize, live verification, code review, preflight, root-cause debugging, interactive plan review, and feature spec management.",
"author": {
"name": "jabworks"
},
"repository": "https://github.com/jabworks/agentic-toolkit",
"license": "MIT",
"keywords": [
"workflow",
"condux",
"tier",
"finalize",
"live-verification",
"discovery",
"blueprint",
"mockup",
"wireframe",
"diagram",
"test-first-development",
"code-review",
"preflight",
"subagent",
"planning",
"draft-plan",
"debugging",
"root-cause-analysis",
"spec",
"technical-spec",
"plan-review",
"doctor",
"health-check"
],
"skills": "./skills"
}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.
[condux on Agent Plugins Marketplace](https://pluginsmp.com/plugins/condux-2)