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 instructions/constantineb6/comfy-pilot/claude-mdgit clone --depth 1 https://github.com/ConstantineB6/comfy-pilotWrote 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/instructions/constantineb6/comfy-pilot/claude-md)<a href="https://agentmods.dev/instructions/constantineb6/comfy-pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/constantineb6/comfy-pilot/claude-md.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 | $0.01889 | $0.01889 |
| Opus 5 | $0.00945 | $0.00945 |
| Sonnet 5 | $0.00378 | $0.00378 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade C, and why
comfy-pilot CLAUDE.md scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
> "I'd prefer to use `uv` for package management as it's faster and more reliable. Can I install it? (`curl -LsSf https://astral.sh/uv/install.sh | sh`). If you'd rather use pip or another tool, let me know." Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> "I'd prefer to use `uv` for package management as it's faster and more reliable. Can I install it? (`curl -LsSf https://astral.sh/uv/install.sh | sh`). If you'd rather use pip or another tool, let me know." How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Claude Code Plugin - Guidelines
Working with ComfyUI Workflows
When creating or modifying ComfyUI workflows, follow these best practices:
Node Titles
Always assign descriptive custom titles to nodes when creating them. This makes workflows much easier to understand when reading them back later.
Instead of generic type names like:
CLIPTextEncode→ Use"Positive Prompt"or"Style Description"KSampler→ Use"Initial Generation"or"Refine Pass"LoadImage→ Use"Reference Photo"or"Input Image"VAEDecode→ Use"Final Decode"or"Preview Decode"ImageScale→ Use"Upscale 2x"or"Resize for ControlNet"
Example:
comfyui_create_node(node_type="CLIPTextEncode", title="Positive Prompt", pos_x=200, pos_y=100)
comfyui_create_node(node_type="CLIPTextEncode", title="Negative Prompt", pos_x=200, pos_y=300)
Node Layout
Position nodes logically from left to right following the data flow:
- Loaders on the left (pos_x ~100-300)
- Processing in the middle (pos_x ~400-700)
- Output/preview on the right (pos_x ~800+)
- Keep related nodes vertically aligned
- Minimum padding: Always leave at least 20px of padding between nodes (2 grid units, default grid = 10px)
Node sizing: When placing a node directly below another node, match the width of the node above it for visual consistency. Use edit_graph with resize action after creation if needed.
Special case: Load 3D & Animation nodes These nodes expand after creation to show a 3D preview. The preview adds ~180px in height. When placing nodes below a Load 3D & Animation node, add at least 200px of extra vertical spacing to avoid overlap.
Placing New Node Groups in View
When creating nodes that are not connected to existing workflow (new starting points, separate node groups, or standalone utilities), use place_in_view: true:
edit_graph(operations=[
{action: "create", node_type: "CheckpointLoaderSimple", title: "Load Model", place_in_view: true, ref: "loader"},
{action: "create", node_type: "KSampler", title: "Sampler", place_in_view: true, ref: "sampler"},
{action: "connect", from_node: "loader", from_slot: 0, to_node: "sampler", to_slot: 0}
])
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.
- 4d ago First seen · 173 lines · 1,889 tokens per session scan C 6e183fda423a
comfy-pilot CLAUDE.md is an instructions file published in the GitHub repository ConstantineB6/comfy-pilot (231 stars, last pushed 6mo ago), licensed MIT. It adds 1,889 tokens to every session, about $0.0094 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
civitai-mcp AGENTS.md
Instructions for sandraschi/civitai-mcp, covering civitai-mcp — agent guide, standards, key files and quick ref.
Orkas-VideoStudio AGENTS.md
Instructions for Orkas-AI/Orkas-VideoStudio, covering working with orkasvideostudio (for coding agents), skills and capabilities.
velorn AGENTS.md
AGENTS.md instructions for VelornLabs/velorn, a project described as: AI-native video editing built around real creative timelines, generative workflows, and local agent control.
minimax-h3-skill CLAUDE.md
Instructions for teskor-hub/minimax-h3-skill, covering minimax h3 skill — working notes, what this is, after every edit: hand over the push commands, where things live and three deliverables, kept in sync.
comfyui_mcp AGENTS.md
Instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.
comfy-prompt-studio CLAUDE.md
Instructions for yxhpy/comfy-prompt-studio, covering claude.md, 架构设计, 快速启动, 1. 复制环境变量模板 and 2. 编辑 .env 文件,填入你的 api 密钥等敏感信息.