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 IvanYangYangXi/artclaw_bridge --skill comfyui-workflow-repairgit clone --depth 1 https://github.com/IvanYangYangXi/artclaw_bridgeWrote 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/ivanyangyangxi/artclaw_bridge/comfyui-workflow-repair)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/comfyui-workflow-repair"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/comfyui-workflow-repair/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/ivanyangyangxi/artclaw_bridge/comfyui-workflow-repair"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/comfyui-workflow-repair.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 | $0.00085 | $0.01048 |
| Opus 5 | $0.00043 | $0.00524 |
| Sonnet 5 | $0.00017 | $0.00210 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
comfyui-workflow-repair 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 13d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Workflow 修复器
自动诊断 workflow 问题并提供修复方案。
预注入变量
run_python 已注入:nodes, client
核心功能
1. 诊断 Workflow
from comfyui_workflow_repair import diagnose_workflow
wf = {...} # 你的 workflow
report = diagnose_workflow(wf)
print(report)
# {
# "status": "issues_found",
# "issues": [
# {
# "type": "missing_node",
# "severity": "error",
# "node_id": "15",
# "node_type": "OldNodeName",
# "message": "节点类型不存在",
# "fixable": True,
# "suggestion": "替换为 NewNodeName"
# },
# {
# "type": "invalid_connection",
# "severity": "warning",
# "message": "节点 3 的输入引用不存在的输出",
# "fixable": True
# }
# ],
# "can_auto_repair": True
# }
2. 自动修复
from comfyui_workflow_repair import repair_workflow
fixed_wf = repair_workflow(wf, auto_fix=True)
print("修复完成")
3. 迁移旧版本 Workflow
from comfyui_workflow_repair import migrate_workflow
# 从旧版本迁移
migrated = migrate_workflow(wf, from_version="0.1", to_version="0.2")
问题类型
| 类型 | 严重程度 | 自动修复 | 说明 |
|---|---|---|---|
| missing_node | error | ✅ | 节点类型不存在 |
| deprecated_node | warning | ✅ | 节点已弃用 |
| invalid_connection | error | ✅ | 无效连接 |
| missing_input | error | ❌ | 缺少必填参数 |
| type_mismatch | warning | ⚠️ | 类型不匹配 |
| orphaned_node | info | ✅ | 孤立节点 |
修复策略
节点重命名迁移
MIGRATION_MAP = {
"CheckpointLoader": "CheckpointLoaderSimple",
"CLIPTextEncodeSDXL": "CLIPTextEncode",
# ...
}
替代节点推荐
ALTERNATIVES = {
"OldSampler": {
"replacement": "KSampler",
"input_mapping": {
"old_param": "new_param"
}
}
}
完整示例
修复加载失败的 Workflow
# 1. 加载 workflow(可能来自旧版本)
wf = load_workflow_file("old_workflow.json")
# 2. 诊断
report = diagnose_workflow(wf)
if report["issues"]:
print(f"发现 {len(report['issues'])} 个问题:")
for issue in report["issues"]:
icon = "🔴" if issue["severity"] == "error" else "🟡"
print(f"{icon} [{issue['type']}] {issue['message']}")
# 3. 自动修复
if report["can_auto_repair"]:
print("\n正在自动修复...")
fixed = repair_workflow(wf)
# 4. 验证
verify = diagnose_workflow(fixed)
if verify["status"] == "ok":
print("✅ 修复成功")
save_workflow(fixed, "fixed_workflow.json")
else:
print("⚠️ 仍有未修复的问题")
else:
print("✅ Workflow 正常")
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.
- 13d ago First seen · 176 lines · 85 tokens per session scan A 876ce4fb5513
comfyui-workflow-repair is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 1,048 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
dcc-diagnostics
Infrastructure skill — DCC-agnostic observability primitives: capture screenshots, query audit logs, inspect tool performance metrics, and monitor process health. Works in any DCC environment (Maya, Blender, Houdini, Unreal, etc.) or standalone Python. Use for debugging any skill failure or verifying DCC state. Not…
qt-ui-inspector
Infrastructure skill — DCC-agnostic Qt UI introspection: list top-level windows, find widgets by name/class, describe widget properties, walk the widget tree, and poll for availability. Works in any DCC with a Qt binding (Maya, Blender, Houdini, Unreal, etc.). All tools are read-only and lazy-loaded.
dcc-mcp-core
Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…
dcc-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
clawhub-compat
Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.