Borrowing it
Nothing to install: this file belongs to Zambav/ComfyUI-Agent-Toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Zambav/ComfyUI-Agent-Toolkit/main/AGENTS.mdgit clone --depth 1 https://github.com/Zambav/ComfyUI-Agent-ToolkitWrote 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/zambav/comfyui-agent-toolkit/agents-md)<a href="https://agentmods.dev/instructions/zambav/comfyui-agent-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/zambav/comfyui-agent-toolkit/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.
<a href="https://agentmods.dev/instructions/zambav/comfyui-agent-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/zambav/comfyui-agent-toolkit/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01797 | $0.01797 |
| Opus 5.5 | $0.00719 | $0.00719 |
| Sonnet 5.5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
ComfyUI-Agent-Toolkit 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI Agent Instructions
How an AI coding/operations agent (Hermes, Claude Code, Codex, etc.) should work with this skill in any environment.
This file exists so that an agent dropped into the project cold -- with no prior context -- can use the skill correctly on first contact. Read this before reading any other file in this skill.
What this skill is
comfyui-skill-public is a portable, installation-agnostic operating
model for ComfyUI. It contains:
- Prompting guides per model family (FLUX 2, LTX 2.3, WAN 2.2, general)
- Reference implementations of node maps and batch helpers
- A sanitized
scripts/api_lib.pyfor talking to a ComfyUI instance - A convention for JoyCaption-driven image description
- SOPs for batch operations, monitoring, and cron-based recovery
It is not tied to any specific:
- Machine path or username
- Discord channel, model filename, or checkpoint
- ComfyUI version (only the version range documented in
dependencies.md) - Custom node set (some demo workflows need custom nodes; check before running)
File placement rules
| File type | Correct location | Never at... |
|---|---|---|
Skill metadata (SKILL.md, README.md) |
repo root | subdirectories |
| Prompting guides | prompting-guides/ |
root or docs/ |
| Reference implementations | reference-implementations.md (root) |
docs/ |
| Setup, dependencies, models | setup.md, dependencies.md, models.md (root) |
anywhere else |
| Job/cron SOPs | batch-operations.md, cron-jobs.md (root) |
docs/ |
| Demo workflow JSONs | demo-workflows/ (READ ONLY examples) |
workflows/, project root |
| Shared helper code | scripts/ (e.g. api_lib.py) |
project root |
| Cross-cutting conventions | docs/ (e.g. joycaption-convention.md) |
repo root |
Why this matters: agents scanning a skill expect a stable layout. If
SKILL.md is at root and setup.md is at root but reference-implementations.md
is in docs/, the agent wastes context hunting for things that should be
predictable.
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.
- 2mo ago First seen · 180 lines · 1,797 tokens per session scan A 8eb5e4e17351
ComfyUI-Agent-Toolkit AGENTS.md is an instructions file published in the GitHub repository Zambav/ComfyUI-Agent-Toolkit (20 stars, last pushed 5mo ago), licensed MIT. It adds 1,797 tokens to every session, about $0.0072 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 2026-09-04.
ComfyUI-Agent-Toolkit AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ComfyUI-Agent-Toolkit AGENTS.mdZambav/ComfyUI-Agent-Toolkit | Instructions file | 20 | 5mo ago | MIT | A | 1,797 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |