workflow_templates is the repository of official ComfyUI workflow templates and reusable subgraph blueprints. It supplies standalone workflows and node components for ComfyUI, along with a browsable site for finding templates. The catalogue entries are skills and instructions for working with these workflows.
Borrowing it
Nothing to install: this file belongs to Comfy-Org/workflow_templates. 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/Comfy-Org/workflow_templates/main/AGENTS.mdgit clone --depth 1 https://github.com/Comfy-Org/workflow_templatesWrote 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/comfy-org/workflow_templates/agents-md)<a href="https://agentmods.dev/instructions/comfy-org/workflow_templates/agents-md"><img src="https://agentmods.dev/badge/instructions/comfy-org/workflow_templates/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/comfy-org/workflow_templates/agents-md"><img src="https://agentmods.dev/badge/instructions/comfy-org/workflow_templates/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 | $0.02446 | $0.02446 |
| Opus 5.5 | $0.00978 | $0.00978 |
| Sonnet 5.5 | $0.00489 | $0.00489 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
workflow_templates 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 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Build & Run Commands
npm run sync— Sync template bundles (run after editing templates/ or bundles.json)npm run sync:templates/npm run i18n— Hub i18n:index.json→index.{locale}.json(NOT MCP)npm run sync:bundles— Regenerate manifest and copy assets to packagesnpm run mcp— Syncindex.json→index.mcp.json(MCP tool index)npm run mcp:check— MCP sync dry-runnpm run mcp:ai— AI English descriptions for stale MCP templatesnpm run mcp:models— AI model profiles inmodels_registry.jsonnpm run validate:templates— Validate template JSON filesnpm run validate:manifests— Validate package manifestsnpm run validate:comfyui-nodes— Compare templates to ComfyUI node baseline (local: live/object_info)npm run validate:widget-types— Fail on widget values stored with the wrong JSON type, e.g."1536"for an INT (local: live/object_info)python scripts/sync/sync_bundles.py— Same asnpm run sync:bundlespython scripts/sync/sync_is_app.py— WriteisAppintoindex.jsonfrom each workflow'sextra.linearMode(--dry-runto report,--checkfor the CI gate)python scripts/validate/validate_templates.py— Same asnpm run validate:templatespython scripts/comfyui_node_compat/check.py --static-scan --clone-comfyui --no-fail— CI-style static compat scanpython scripts/sync/sync_frozen_inventory.py— Regenerate frozen bundle template inventory frombundles.jsonpython scripts/ci/check_frozen_policy.py --base-ref origin/main— Dry-run frozen-bundle PR reminder locally
MCP index pipeline: see skill .claude/skills/managing-mcp-index/SKILL.md and scripts/mcp/docs/MCP_AI_ENHANCEMENT.md. Do not confuse with hub i18n (i18n) or site AI (site/scripts/generate-ai.ts).
Frozen legacy media bundles: see scripts/docs/frozen_bundles.md (policy, inventory, CI reminders, publishing).
BFL product names: FLUX 3 uses a space (FLUX 3 Image, FLUX 3 Image Klein, FLUX 3 Video); FLUX.2 uses a dot (FLUX.2, FLUX.2 Max, FLUX.2 Klein). See .claude/skills/managing-templates/SKILL.md (Black Forest Labs product names).
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 Changed · +1 lines · +39 tokens per session 5eb7b2bcfa4a
- 9d ago Changed · +2 lines · +85 tokens per session 6c0dc64852c9
- 1mo ago First seen · 139 lines · 2,322 tokens per session scan A 938e02a31748
workflow_templates AGENTS.md is an instructions file published in the GitHub repository Comfy-Org/workflow_templates (1,360 stars, last pushed yesterday), licensed MIT. It adds 2,446 tokens to every session, about $0.0098 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.