Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add artokun/comfyui-mcp --skill comfyui-frontend-extensionsgit clone --depth 1 https://github.com/artokun/comfyui-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/artokun/comfyui-mcp/comfyui-frontend-extensions)<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/comfyui-frontend-extensions"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/comfyui-frontend-extensions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/comfyui-frontend-extensions"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/comfyui-frontend-extensions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.05364 |
| Opus 5 | $0.00038 | $0.02682 |
| Sonnet 5 | $0.00015 | $0.01073 |
| Haiku 4.5 | $0.00008 | $0.00536 |
Grade A, and why
comfyui-frontend-extensions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- comfyui-frontend-extensions — 89% identical, 77 lines differ
How it starts
The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI v2 Frontend Extension API
The v2 extension API is the published npm package @comfyorg/extension-api. It
replaces the legacy app.registerExtension() / nodeType.prototype monkey-patching
model with a typed, tree-shakeable, import-based API.
If you are converting an existing v1 extension, read
references/migrate-v1-to-v2.mdfor a pattern-by-pattern mapping.
Mental model
| v1 (legacy) | v2 (@comfyorg/extension-api) |
|---|---|
One giant app.registerExtension({...}) call |
One defineX per concern, each independently disposable |
window.app / app.* globals |
Direct import from the package; no window.app at module-eval time |
nodeType.prototype.onExecuted = ... patching |
node.on('executed', fn) on a NodeHandle |
Mutate widget.value, assign widget.callback |
widget.setValue(v) / widget.on('valueChange', fn) |
api.addEventListener('execution_start', fn) |
execution.on('start', fn) (typed namespaces) |
Manual removeEventListener bookkeeping |
Every subscription returns Unsubscribe; every defineX returns DisposableHandle |
Core principles baked into the API:
- Import, don't reach for globals.
import { defineNode } from '@comfyorg/extension-api'. Nowindow.appdependency at module evaluation time. - Read via getters, write via command-dispatch setters.
getValue()reads;setValue()dispatches an undo-able, serializable command. Read-only invariants (set at construction) arereadonlyaccessors (node.type,widget.name). - Observe via typed
on(...)subscriptions. Each returns anUnsubscribecleanup function. No Vue refs/signals are ever exposed; Vue reactivity is the internal engine only. - Everything is disposable. Every
defineXreturns aDisposableHandlewith an idempotent, synchronousdispose().
Registration entry points
All imported from @comfyorg/extension-api:
| Function | Purpose | Returns |
|---|---|---|
defineNode(opts) |
Primary entry — react to node lifecycle (replaces prototype patching) | NodeExtensionOptions |
defineExtension(opts) |
App-scoped lifecycle (init/setup) + shell UI host |
ExtensionOptions |
defineWidget(opts) |
Register a custom widget type (DOM via mount) |
WidgetExtensionOptions |
defineSidebarTab(opts) |
Add a left-sidebar tab (Vue or custom) | DisposableHandle |
defineBottomPanelTab(opts) |
Add a bottom-panel tab | DisposableHandle |
defineToolbarButton(opts) |
Add an action-bar button | DisposableHandle |
defineCommand(opts) |
Register an invokable command | DisposableHandle |
defineHotkey(opts) |
Bind a key combo to a command id | DisposableHandle |
defineSetting(opts) |
Add a settings-menu entry | DisposableHandle |
defineAboutBadge(opts) |
Add a badge to the About page | DisposableHandle |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 504 lines · 76 tokens per session scan A 547062066d04
comfyui-frontend-extensions is a skill published in the GitHub repository artokun/comfyui-mcp (740 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 5,364 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
image-seo-audit
Audit every image on a page for SEO, performance, and accessibility — alt text quality, tiered file-size thresholds, WebP/AVIF format adoption, srcset/sizes responsiveness, lazy loading, fetchpriority on the LCP image, and width/height for CLS — producing an optimization list sorted by file-size savings. Triggers on…
design-system
Builds and maintains the design system a product is assembled from — tokens for color, type, spacing and elevation, component contracts, and the rules that keep them coherent as the product grows. Use this when starting a new interface, when screens have drifted apart visually, when the same component exists three…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
json-render-catalog
Skill "json-render-catalog" from yonatangross/orchestkit, covering json-render component catalogs, storybook → catalog import (#1529, 2026-04), new in 2026-04 → 2026-08 (json-render 0.14 → 0.20), directives — @json-render/directives (0.19) and registration.
interface-redesign
Upgrades an existing interface to a higher standard without rebuilding it — auditing what is there, identifying what reads as generic or unfinished, and sequencing changes by impact. Use this when a product works but looks dated or default, when a redesign is being considered, when deciding whether to restyle or…
design-context-extract
Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…