What is comfypilot-core?

A set of instructions for controlling ComfyUI, a visual tool for building AI image, video, audio, and 3D-generation workflows. It guides an assistant using ComfyPilot's MCP tools, which connect to a running ComfyUI setup.

Checking GPU and memory status, finding or building generation workflows, inserting workflow blueprints, and working with image, video, audio, and 3D tasks supported by ComfyUI.

It provides a defined process for checking the system, choosing or building workflows, and validating them against the installed ComfyUI setup. This helps avoid sending workflows that do not match the available models or controls.

comfypilot-core — Skill for Claude Code and Codex by dreamrec: A set of instructions for controlling ComfyUI, a visual…

Install

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.

agentmods

npx agentmods add skills/dreamrec/comfypilot/comfypilot-core

Any agent

npx skills add dreamrec/ComfyPilot --skill comfypilot-core

Clone the repo

git clone --depth 1 https://github.com/dreamrec/ComfyPilot

Made for: Claude Code, Codex.

Or install comfypilot, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dreamrec/comfypilot/comfypilot-core.svg)](https://agentmods.dev/skills/dreamrec/comfypilot/comfypilot-core)

Your own site

<a href="https://agentmods.dev/skills/dreamrec/comfypilot/comfypilot-core"><img src="https://agentmods.dev/badge/skills/dreamrec/comfypilot/comfypilot-core.svg" alt="Measured on agentmods" height="20"></a>

Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,248 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00150	$0.02248
Opus 5	$0.00075	$0.01124
Sonnet 5	$0.00030	$0.00450
Haiku 4.5	$0.00015	$0.00225

Measured 3d ago against content hash f6ef68650223, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comfypilot-core 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 3d 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.

skills/comfypilot-core/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ComfyPilot Core Skill

Use this when working with ComfyUI through ComfyPilot's 96 MCP tools (tested with ComfyUI v0.20.0-v0.31.1). v1.9.0 adds modern jobs, strict live-schema validation, Desktop-aware control, generic artifacts, worker observability, native global subgraphs, and expanded V3 widget/schema support.

Default Workflow

Check system - comfy_get_system_stats (typed SystemStats) to verify GPU, VRAM, ComfyUI version.
Check VRAM - comfy_check_vram (typed VRAMStatus) for headroom before loading large models.
Discover or build
- Search the library first: comfy_search_techniques for saved patterns, or comfy_list_blueprints for blueprints (13 bundled; pass source="native" to read canonical ComfyUI global subgraphs).
- Build: comfy_build_workflow(template=<intent>) auto-detects the installed checkpoint family and emits the right graph (SD 1.5 / SDXL / SD 3.5 / Flux 2 / Qwen / Wan 2.2 / LTX-2 / HunyuanVideo / Hunyuan3D / ACE-Step / Ernie Image). Family-agnostic intents (super_resolution, interpolate_frames, segment, train_lora, txt2audio) skip checkpoint detection and dispatch by intent name.
- Or insert a blueprint: comfy_insert_blueprint(name="flux2-txt2img") and override inputs. Bundled: flux2-txt2img, sd35-txt2img, sdxl-hires-fix, qwen-txt2img, wan22-txt2video, ltx2-txt2video, hunyuan-video-txt2video, hunyuan3d-image2_3d, acestep-txt2music, ernie-txt2img, supir-upscale, rife-interpolate, sam31-segment.
Validate - comfy_validate_workflow (typed ValidationReport) runs 6 passes: schema / catalog / graph / anti_cycle / environment / execution_risk. Anti-cycle mirrors ComfyUI v0.20's execution-side cycle detection. Environment pass also runs a deprecated-model lint that warns on retired partner models.
Snapshot before changes - comfy_snapshot_workflow saves state. Set COMFY_SNAPSHOT_DIR to persist across restarts.
Queue - comfy_queue_prompt (typed QueueAck) submits for execution. Preserves error/node_errors from ComfyUI.
Monitor - comfy_watch_progress (typed WatchProgressFrame) polls. comfy_describe_dynamics (typed DynamicsReport) for full queue + events + active jobs view.
Retrieve - comfy_get_output_image returns image content blocks directly in chat.
Route - comfy_send_to_disk / comfy_send_to_td / comfy_send_to_blender - atomic writes with <filename>.json manifest sidecars (prompt_id, seeds, model refs, dimensions).

Read the full file on GitHub · 106 lines

Changes

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.

3d ago First seen · 106 lines · 150 tokens per session scan A f6ef68650223

Subscribe to this mod's changes

comfypilot-core is a skill published in the GitHub repository dreamrec/ComfyPilot (1 stars, last pushed 22d ago), licensed MIT. It adds 150 tokens to every session and 2,248 once invoked, about $0.0007 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 2026-08-31.

Creative and media Data and AI

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

comfypilot-core

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ComfyPilot Core Skill

Default Workflow

What this file has done since we first saw it

Other skills, from other repositories

general-video

media-ingest

diagnostic-stem-delivery

chengfeng-cut

chengfeng-check-updates

infographic-template-updater