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.
npx skills add peteromallet/VibeComfy --skill search-comfy-workflowsgit clone --depth 1 https://github.com/peteromallet/VibeComfyWrote 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/peteromallet/vibecomfy/search-comfy-workflows)<a href="https://agentmods.dev/skills/peteromallet/vibecomfy/search-comfy-workflows"><img src="https://agentmods.dev/badge/skills/peteromallet/vibecomfy/search-comfy-workflows/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/peteromallet/vibecomfy/search-comfy-workflows"><img src="https://agentmods.dev/badge/skills/peteromallet/vibecomfy/search-comfy-workflows.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 | $0.00085 | $0.00920 |
| Opus 5.5 | $0.00034 | $0.00368 |
| Sonnet 5.5 | $0.00017 | $0.00184 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
search-comfy-workflows 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Comfy Workflows
Use this to find evidence before editing or adding a graph. The result should tell the next agent what to open, why it matches, which node classes matter, and what is still uncertain. A found JSON workflow is a precedent to import and inspect; it is not itself an execution instruction.
Fast Path
Start local. Escalate to Hivemind when local search does not have the precedent, or when the user asks for community/Banodoco practice.
vibecomfy workflows list --ready
vibecomfy workflows list
vibecomfy search "wan i2v controlnet" --task i2v --limit 10 --json
vibecomfy inspect <workflow_id_or_path>
vibecomfy analyze info <workflow_id_or_path>
Run vibecomfy sources sync only when indexes are stale and generated index updates are acceptable.
Hivemind
Use Hivemind for current ComfyUI practice, Banodoco workflows, Kijai/Ablejones node usage, settings, model notes, and community workflow examples. Local search is for the selected imports and curated adapters already present in this checkout.
Use the deployed Hivemind pack through Astrid. This is the single supported route; it pins the installed pack and applies the runtime's retry/error handling:
python3 -m astrid hivemind search "wan animate workflow openpose" \
--kinds workflow --limit 10 --json
Fetch the exact accepted resource/revision through the Astrid Hivemind SDK
(hivemind.get_item) after search. Do not call Hivemind's PostgREST tables or
the retired unified_feed/contribute-resource paths directly from a
workflow task.
Favor topic-specific sources such as wan_comfyui, wan_resources,
ltx_chatter, ltx_resources, comfyui, resources, and daily_summaries.
One workflow lifecycle
Hivemind is the discovery and provenance layer. VibeComfy owns the local workflow artifacts:
- Search Hivemind and pin the accepted resource/revision.
- Pull that one workflow on demand with the normal importer, for example
vibecomfy import hivemind:external_resources:<id>orvibecomfy import hivemind://resource/<id>[/revisions/<revision>]. The importer writes the single local bundle underworkflows/<source-id>/and retains the Hivemind evidence ID, any provider revision, and hash in bundle metadata; when the provider exposes no revision, the hash is recorded as the local snapshot pin. - Edit, validate, and run that local bundle (or copy it to
recipes/). - Use
vibecomfy templates create ... --id ...only when deliberately promoting a validated workflow into a curatedready_templates/adapter. Any source snapshot shipped with that adapter is generated from the pinned Hivemind input; it is not a second source of truth.
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.
- 1mo ago Changed · +23 lines d8039047911b
- 1mo ago Changed 26890faed1f6
- 1mo ago First seen · 53 lines · 85 tokens per session scan A 2d93f741ec03
search-comfy-workflows is a skill published in the GitHub repository peteromallet/VibeComfy (152 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 920 once invoked, about $0.0003 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.