comfyops-mcp: Instructions file for Codex

AGENTS.md

comfyops-mcp AGENTS.md is an instructions file for Codex, OpenCode from sandraschi/comfyops-mcp. It costs 611 tokens per session, scanned A, original, MIT.

A project instruction file for comfyops-mcp, documenting its identity, important files, tools, and quick reference.

In plain words
What is it for?
Use it as a reference for the repository's agent rules, key files, available tools, and basic operation.
Why use it?
It gives coding agents the project-specific context they need when working in the comfyops-mcp repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is sandraschi/comfyops-mcp's own configuration. It tells Codex and OpenCode how to work on comfyops-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything comfyops-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sandraschi/comfyops-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sandraschi/comfyops-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/comfyops-mcp

Made for: Codex, OpenCode.

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.

agentmods badge for comfyops-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/comfyops-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/sandraschi/comfyops-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/comfyops-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/comfyops-mcp/agents-md/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.

agentmods 80×15 button for comfyops-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sandraschi/comfyops-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/comfyops-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 611 This file is loaded in full into every session.
When invoked 611 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00611 $0.00611
Opus 5.5 $0.00244 $0.00244
Sonnet 5.5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 2mo ago against content hash 96f553671692, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

comfyops-mcp AGENTS.md 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 2mo 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — comfyops-mcp

Identity

  • Name: comfyops-mcp
  • Purpose: Local generative AI engine — wraps ComfyUI for image/video/upscale/inpaint
  • Stack: FastMCP 3.4+, httpx, SQLite3, comfyui_manager
  • Ports: 11086 (ComfyUI), 11087 (backend), 11088 (frontend)
  • Transports: stdio and streamable HTTP
  • Onboarding: docs/ONBOARDING.md — ComfyUI + models; catalog via civitai-mcp
  • Fleet start: mcp-central-docs/starts/comfyops-mcp-start.bat

Key Files

File Purpose
src/comfyops_mcp/server.py FastMCP app + tool registration
src/comfyops_mcp/comfyui_manager.py ComfyUI sidecar lifecycle + API client
src/comfyops_mcp/config.py Env var config
src/comfyops_mcp/tools/generate.py comfy_generate portmanteau
src/comfyops_mcp/tools/workflows.py comfy_workflows portmanteau
src/comfyops_mcp/tools/models_tool.py comfy_models portmanteau
src/comfyops_mcp/tools/library.py comfy_library portmanteau
src/comfyops_mcp/tools/agentic.py comfy_agentic_assist
src/comfyops_mcp/tools/prefab/cards.py Prefab UI cards
workflows/ Curated ComfyUI workflow JSONs
web_sota/ Vite + React dashboard

Tools

Tool Ops Notes
comfy_generate image, video, upscale, inpaint, edit Submits workflow JSON, polls result
comfy_workflows list, get, validate, register Curated workflow depot
comfy_models list_installed, download, check_vram, health download = HF streaming, sha256 verify, Bearer auth (COMFYOPS_HF_TOKEN)
comfy_library recent, search, record SQLite generation history
comfy_agentic_assist — SEP-1577 sampling for multi-step gen

Quick Ref

uv run python -m comfyops_mcp.server           # stdio
.\start.ps1                                      # full stack

Danger Zones

  • comfy_generate can saturate the GPU for 30-300s — vram_guard prevents OOM
  • Workflows execute arbitrary ComfyUI node graphs — trust curated workflows only
  • ComfyUI must be installed at COMFYOPS_COMFYUI_DIR (or connected remotely)

Read the full file on GitHub · 48 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.

  1. 2mo ago Changed · +2 lines · +67 tokens per session 96f553671692
  2. 2mo ago First seen · 46 lines · 544 tokens per session scan A 9cf28b3f0579

Subscribe to this mod's changes

comfyops-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/comfyops-mcp (3 stars, last pushed 2d ago), licensed MIT. It adds 611 tokens to every session, about $0.0024 per session on Opus 5.5. 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.

Related

comfyops-mcp AGENTS.md compared with instructions from other repositories

comfyops-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
comfyops-mcp AGENTS.mdsandraschi/comfyops-mcpInstructions file32d agoMITA611Codex, OpenCode
runtm copilot-instructions.mdruntm-ai/runtmInstructions file303yesterdaynoneA297GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot