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.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Comfy-Org/workflow_templatesnpx agentmods add skills/comfy-org/workflow_templates/managing-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/skills/comfy-org/workflow_templates/managing-templates)<a href="https://agentmods.dev/skills/comfy-org/workflow_templates/managing-templates"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/managing-templates/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/skills/comfy-org/workflow_templates/managing-templates"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/managing-templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.03560 |
| Opus 5.5 | $0.00045 | $0.01424 |
| Sonnet 5.5 | $0.00023 | $0.00712 |
| Haiku 4.5 | $0.00011 | $0.00356 |
Grade A, and why
managing-templates 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 9d 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Templates
Covers adding new templates and renaming existing ones in this repository.
Related skills (do not replace this one):
/managing-bundles— move between bundles / categories / order/managing-thumbnails— thumbnail-only work/managing-translations— broader i18n work/managing-mcp-index— MCP index only
Shared Rules
- Never modify scripts, build tooling, or CI configuration.
- Template names must be
snake_case— no spaces, dots, or special characters. namemust match the workflow JSON filename (without.json).- Always run
python3 scripts/sync/sync_bundles.pyafter editingbundles.jsonor renaming template assets. - Always validate after structural changes (see Validation below).
- For new templates, assign media to
media-assets-02— seescripts/docs/frozen_bundles.md. - Bump root
pyproject.tomlonly for intentional PyPI releases (releaselabel). - Use double-quotes
"in all JSON files. - Model download URLs must produce filenames that exactly match
widgets_valuesin the workflow JSON. - Package copies under
packages/*/src/**/templates/are gitignored; regenerate viasync_bundles.py, do not hand-edit.
Black Forest Labs product names
Official spelling is the BFL All Models list. Use these tokens in titles and descriptions:
- FLUX 3 (space):
FLUX 3 Image,FLUX 3 Image Klein,FLUX 3 Video,FLUX 3 Action - FLUX.2 (dot):
FLUX.2,FLUX.2 Max,FLUX.2 Klein
Do not invent FLUX 2 (space), FLUX.3 / Flux.3 (dot), or mixed casing (Flux 3, Flux.2).
- Brand tokens stay untranslated and byte-identical in every locale. Translate only the rest of the title or description.
- Template Library search names in external docs must match these English titles exactly.
- Do not rename template ids, filenames, API paths, download URLs, or model tag enums to chase branding.
Decide the operation
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.
- 9d ago Changed · +14 lines 3f3a02503c20
- 12d ago Changed · +19 lines b36f3ba20937
- 1mo ago Changed 05ac19a41250
- 1mo ago First seen · 295 lines · 113 tokens per session scan A f3d76f59acbd
managing-templates is a skill published in the GitHub repository Comfy-Org/workflow_templates (1,360 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 3,560 once invoked, about $0.0005 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.