Skill Claude CodeCodex
Multi-language codebase health scanner. Use when the user explicitly asks to run desloppify, scan for technical debt, get a health score, or create a cleanup plan. Do NOT trigger for general code review, renaming, or fixing individual bugs.
Skill Claude CodeCodex
Multi-language codebase health scanner. Use when the user explicitly asks to run desloppify, scan for technical debt, get a health score, or create a cleanup plan. Do NOT trigger for general code review, renaming, or fixing individual bugs.
Skill Claude CodeCodex
Drive the VibeComfy package to discover ComfyUI workflows, load ready Python templates, edit and compose them in a VibeWorkflow IR, validate, and execute either embedded locally, against an existing ComfyUI server, or on RunPod. Use whenever the user wants to generate images/video/audio/edits from ComfyUI workflows…
Skill Claude CodeCodex needs its repo
Add a durable VibeComfy ready workflow/template from a ComfyUI source workflow. Use when the user asks to add a new ready template, promote a workflow into readytemplates, add a model family/capability, update coverage manifests, or make a workflow reusable by id.
Skill Claude CodeCodex
Diagnose a VibeComfy or ComfyUI workflow that fails validation, conversion, node/model resolution, runtime execution, or output production. Use when the user asks why a workflow does not run, has missing nodes/models, validation errors, bad wiring, failed RunPod/local runs, or confusing agent-edit failures.
Skill Claude CodeCodex
Edit an existing VibeComfy or ComfyUI workflow, ready template, recipe, scratchpad, or target graph. Use when the user asks to tweak prompts/seeds/steps/resolution, alter nodes, splice a pattern into a workflow, convert JSON to editable Python, or make a graph change without necessarily running it.
Skill Claude CodeCodex
Explain an existing VibeComfy or ComfyUI workflow, ready template, recipe, scratchpad, target graph, node chain, model path, prompt path, or runtime result. Use when the user asks what a workflow does, how it works, what a node or setting means, why a graph is wired a certain way, what will happen if it runs, or wants…
Skill Claude CodeCodex
Reorganise an existing ComfyUI workflow layout without changing runtime behavior. Use when the user asks to clean up a messy graph, make it readable, regroup or align nodes, or run the explicit /reorganisecomfyworkflow agent route.
Skill Claude CodeCodex needs its repo
Execute an existing VibeComfy/ComfyUI workflow, ready template, recipe, or scratchpad and collect outputs. Use when the user asks to run, queue, execute, generate, render, smoke test, use a local/remote ComfyUI runtime, or run on RunPod.
Skill Claude CodeCodex
Search for ComfyUI workflow precedents, VibeComfy ready templates, node wiring examples, Banodoco/Hivemind community workflow knowledge, and concrete graph patterns before editing or adding a workflow. Use when the user asks to find workflows, examples, precedents, ComfyUI node combinations, Hivemind/Banodoco…
Skill Claude CodeCodex
Set up VibeComfy for local or remote ComfyUI use. Use when the user asks to install, configure, initialize, connect VibeComfy to ComfyUI, choose between pip-installed ComfyUI and their own ComfyUI checkout, configure customnodes/models paths, reuse existing nodes/models, create isolated libraries, or make vibecomfy…
Agent Claude Code
Arnold resident operator (agentbox-operator-v1): concise, state-first, one clarifying question.
Skill Claude CodeCodex
Scaffold a new Arnold native-first pipeline package from the template skeleton.
Skill Claude CodeCodex
Steps to create a new Arnold native-first pipeline package from the template.
Skill Claude CodeCodex
Reference contract for the canonical Arnold native-first pipeline template scaffold.
Skill Claude CodeCodex
Model-less verification of persisted evidence-pack JSON artifacts.
Skill Claude CodeCodex
Run the canonical Megaplan planning pipeline from its Arnold plugin home.
Skill Claude CodeCodex
AI agent harness for coordinating Claude and GPT to make and execute extremely robust plans.
Skill Claude CodeCodex
AI agent harness for coordinating Claude and GPT to make and execute extremely robust plans.
Cursor rule Cursor
Use megaplan for high-rigor planning on complex, high-risk, or multi-stage tasks.
Skill Claude CodeCodex
Run megaplan plans and chains on the Hetzner agentbox via the ssh provider, with a persistent workspace volume. Use when the run needs to outlast a local terminal session, span multiple repos, or share a long-lived dev box across concurrent chains. Covers cloud.yaml fields, extrarepos[] + chainsession multi-tenancy…
Skill Claude CodeCodex
Evidence-first recovery protocol for a stuck Megaplan epic or any autonomous pipeline. Pipeline: bounded DeepSeek V4 Flash evidence swarm to understand all context → Codex/Sol decision-maker produces an ordered implementation plan (durable root fix + get-it-moving) → DeepSeek implementer executes it in the approved…
Skill Claude CodeCodex
Driver: compatibility mirror for the native canonical package Arnold API version: 1.0 Supported modes: native.
Skill Claude CodeCodex
Driver: subprocessisolated Arnold API version: 1.0 Supported modes: (none — invoked directly, not via megaplan run).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: