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/yogasw/wick/workflow-node-modulenpx skills add yogasw/wick --skill workflow-node-modulegit clone --depth 1 https://github.com/yogasw/wickWhat 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 | $0.00132 | $0.08418 |
| Opus 5 | $0.00066 | $0.04209 |
| Sonnet 5 | $0.00026 | $0.01684 |
| Haiku 4.5 | $0.00013 | $0.00842 |
Grade A, and why
workflow-node-module 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 yesterday.
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 — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Node Module — wick core
Activate this skill whenever the user touches a workflow node type — creating, improving, fixing, or adding fields. When editing an existing node, audit it against the rules below and bring it up to spec as part of the change.
Mental model
A node has two halves that share one schema:
| Half | Lives in | Touches |
|---|---|---|
| Engine (executor) | internal/agents/workflow/nodes/<type>.go |
runtime — receives workflow.Node, returns NodeOutput |
| UI plugin module (palette + inspector) | internal/tools/agents/workflow/nodes/<type>/ |
canvas — palette entry, drawflow codec, inspector partial, JS module |
The shared schema struct (exported type, e.g. HTTPSchema) lives in the engine package and is reflected by both:
- engine
Descriptor().Schema→integration.StructSchema(HTTPSchema{})→ MCPworkflow_node_types - UI inspector partial →
entity.StructToConfigs(HTTPSchema{})→wfview.ArgForm(rows)→ editor HTML
Adding a new node type touches:
internal/agents/workflow/types.go—NodeTypeconstant + flatNodestruct fieldsinternal/agents/workflow/nodes/<type>.go— executor + exported schema struct +Descriptor()internal/agents/workflow/setup/manager.go— oneeng.Registerlineinternal/tools/agents/workflow/nodes/<type>/meta.go— palette + codec moduleinternal/tools/agents/workflow/nodes/<type>/inspector.templ— inspector partial (one-liner that calls ArgForm)internal/tools/agents/workflow/nodes/<type>/inspector.js— hydrate/save glueinternal/tools/agents/workflow/nodes/all/all.go— blank import the new subpackageinternal/tools/agents/workflow/nodes/static.go— extend//go:embed all:<type>for the JS file
The catalog flow:
eng.Register(workflow.NodeFoo, nodes.NewFooExecutor())
→ engine.Register checks if executor implements engine.Describer
→ calls Descriptor() → stores engine.NodeDescriptor in Engine.Descriptors[t]
→ mcp.NodeTypesCatalog(eng) builds workflow_node_types response from Descriptors map
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.
- yesterday First seen · 619 lines · 132 tokens per session scan A c4a967c12fde
workflow-node-module is a skill published in the GitHub repository yogasw/wick (5 stars, last pushed 4d ago), licensed MIT. It adds 132 tokens to every session and 8,418 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.