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 agentmods add skills/artokun/comfyui-mcp/panel-node-pack-syncnpx skills add artokun/comfyui-mcp --skill panel-node-pack-syncgit 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/panel-node-pack-sync)<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/panel-node-pack-sync"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/panel-node-pack-sync.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00206 | $0.03041 |
| Opus 5 | $0.00103 | $0.01520 |
| Sonnet 5 | $0.00041 | $0.00608 |
| Haiku 4.5 | $0.00021 | $0.00304 |
Grade A, and why
panel-node-pack-sync 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keep the panel node-pack in sync with the orchestrator
The orchestrator (comfyui-mcp, from npm) and the sidebar panel
(comfyui-agent-panel on the Comfy Registry, repo comfyui-mcp-panel) ship
separately. Updating one does not update the other. A new orchestrator
driving an old panel fails in confusing ways, such as a bridge command the panel
doesn't implement or a feature that exists in the docs but not in the sidebar,
and those failures are hard for a user to diagnose. This skill closes that gap.
The two rules that outrank everything else here
-
Never report a sync that did not happen. This whole feature sits on top of the fabricate-success fixes (#639/#641): ComfyUI-Manager reports its queue "drained" even when it never enqueued anything, and a
.bak-style copy incustom_nodescan shadow the real panel in the browser. So the only version you may ever tell the user is the one read back from disk after the fact. If the tool throws, the sync FAILED. Say so plainly. Do not soften it, do not retry it into a success, do not report the version you intended to install. -
Never move a pinned user. A pin is a promise. If the user pinned the panel, you warn and stop. You do not unpin for them, you do not "just this once", you do not sync anyway because the new version is obviously better. Offer to clear the pin, and act only if they say yes.
Step 1 — Look before you touch anything
install_comfyui(action:'panel', panel_action:'status')
This never errors. Read these fields:
| Field | Meaning |
|---|---|
installedVersion |
The panel version on disk (from its pyproject.toml). |
sync.requiredPanelVersion |
The highest panel version this orchestrator build needs. |
sync.decision |
What to do — the whole decision is made for you (Step 2). |
sync.summary |
Plain-language explanation, safe to paraphrase to the user. |
pin |
The active pin: { pinned, version, source: "env"|"settings", reason }. |
shadows |
.bak-style copies that shadow the real panel in the browser. |
isDevSymlink |
A developer's symlinked checkout — never ours to modify. |
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.
- 5d ago First seen · 202 lines · 206 tokens per session scan A e075ee425003
panel-node-pack-sync is a skill published in the GitHub repository artokun/comfyui-mcp (716 stars, last pushed yesterday), licensed MIT. It adds 206 tokens to every session and 3,041 once invoked, about $0.0010 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
brand-setup
Create or update the brand profile every other skill reads — a quick 5-question or full 17-question interactive setup capturing identity, business model, industry and compliance markets, 4-dimension voice scales, channels, goals, and competitors, saved to /.claude-marketing/brands/{slug}/profile.json via…
spring-security-jwt
Use when an application issues and validates its own first-party JWT access and refresh tokens, including authentication filters, password encoding, RBAC, and method security. For JWTs issued by Keycloak, Auth0, Okta, Cognito, or another authorization server, use oauth2-resource-server.
spring-ai-integration
Use when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. Covers Spring AI ChatClient, prompt templates, embeddings, vector stores, and structured output. Use when user mentions Spring AI, LLM, ChatGPT, Claude, RAG, embeddings.
mcp-server
Use when exposing Spring Boot 3 application capabilities through Model Context Protocol tools, resources, or prompts. Covers Spring AI 1.x tool callback registration, transports, schemas, errors, security, and standalone MCP Java SDK compatibility.
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
people-report
Generate a report on people in your Immich photo library: unique faces detected, photos per person, unnamed faces, people appearing together, and face recognition quality. Use when the user says "people report", "faces report", "who's in my library", "unnamed faces", "face recognition", "how many people", "people…