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 agentmods add skills/peteromallet/vibecomfy/edit-comfy-workflownpx skills add peteromallet/VibeComfy --skill edit-comfy-workflowgit 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/edit-comfy-workflow)<a href="https://agentmods.dev/skills/peteromallet/vibecomfy/edit-comfy-workflow"><img src="https://agentmods.dev/badge/skills/peteromallet/vibecomfy/edit-comfy-workflow.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.00804 |
| Opus 5 | $0.00036 | $0.00402 |
| Sonnet 5 | $0.00014 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
edit-comfy-workflow 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit Comfy Workflow
Use this when the graph needs to change. Follow the same shape as the agentic tests: identify the target, inspect it, materialize an editable Python surface if needed, make the smallest graph change, then validate.
Shared Edit Spine
Use the same spine as the Comfy app agent edit path and the structural/live agentic tests:
target graph -> inspect/research -> Python editable surface -> VibeWorkflow edit -> finalize_metadata -> validate/doctor -> candidate or run
For package-side edits, the editable surface is a recipe, scratchpad, or ready template. For the Comfy app, the same idea returns a candidate UI graph plus apply eligibility. Do not treat an edit candidate as an executed result; execution belongs to run-comfy-workflow.
Fast Path
vibecomfy inspect <target>
vibecomfy analyze info <target>
If the target is raw JSON:
vibecomfy port check <workflow.json> --json
vibecomfy port convert <workflow.json> --out out/scratchpads/<name>.py --json
If the target is a ready template and the edit is user-specific:
vibecomfy copy-to-recipe <ready_id> --out recipes/<name>.py
Then edit the Python recipe, scratchpad, or template.
Edit Shape
Use the lightest public API that fits:
from vibecomfy import load_workflow_any
def build():
wf = load_workflow_any("image/z_image")
wf.set_prompt("a glass teapot on basalt")
wf.set_seed(42)
wf.set_steps(20)
return wf.finalize_metadata()
Reach for patches when decorating an existing graph. Reach for blocks or direct VibeWorkflow methods only when the edit changes handles, splices nodes, or rewires topology.
Never invent node fields, sockets, or class names. Use vibecomfy nodes spec <ClassType>, visible graph data, local precedents, or search-comfy-workflows.
Validate
vibecomfy validate <edited.py>
vibecomfy doctor <edited.py> --json
For converted source workflows:
vibecomfy port doctor-all <source_or_edited_workflow> --json
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.
- 6d ago First seen · 97 lines · 72 tokens per session scan A f3885679f94c
edit-comfy-workflow is a skill published in the GitHub repository peteromallet/VibeComfy (149 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 804 once invoked, about $0.0004 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…