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 xonovex/platform --skill node-graph-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/node-graph-guide)<a href="https://agentmods.dev/skills/xonovex/platform/node-graph-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/node-graph-guide/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/xonovex/platform/node-graph-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/node-graph-guide.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 | $0.00135 | $0.01526 |
| Opus 5.5 | $0.00054 | $0.00610 |
| Sonnet 5.5 | $0.00027 | $0.00305 |
| Haiku 4.5 | $0.00014 | $0.00153 |
Grade A, and why
node-graph-guide 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Node graph Guidelines (Visual Data-Flow Authoring)
Engine-agnostic architecture for a visual node-based graph that authors and non-programmers use to assemble behavior by wiring typed nodes together, then compile or evaluate into executable work. The graph itself is plain typed data (see data-model-guide); its node arrays are laid out for traversal (see data-oriented-design-guide); when it emits render/compute work, the scheduling of that work belongs to gpu-rendering-guide.
Requirements
- A reflectable typed object/data store the graph serializes into (nodes, connections, per-node settings, interface), so the editor, evaluator, and tools all read the same definition, see data-model-guide.
- A node-type registry that plugins can extend with new node kinds and new wire data types without modifying the core.
Essentials
- Graph is data, not code - Nodes, typed pins, wires, and constant inputs are serialized objects, not topology hidden in imperative code, see references/node-model.md
- Typed pins gate every wire - A wire is legal only when the producer's output type satisfies the consumer's input type, see references/typing-and-connections.md
- Compile, then run - Lower the authored graph into a flattened, ordered executable form and evaluate that, instead of walking the editor graph every frame, see references/evaluation-and-compilation.md
- Cache by validity hash - Fold every consumed input into an output's hash; a consumer skips recompute when the hash is unchanged, see references/evaluation-and-compilation.md
- Subgraphs are reusable nodes - Encapsulate a selection behind a typed input/output interface and instance it from an asset, see references/subgraphs-and-functions.md
Node model
- Nodes and pins - A node is a typed object with named, typed input and output pins, see references/node-model.md
- Data-driven node types - Register node kinds (pins, defaults, evaluate callback) as data so plugins extend the toolbox, see references/authoring-and-introspection.md
- Constant/default inputs - An unwired input falls back to a stored constant edited inline; no node is needed for a literal, see references/authoring-and-introspection.md
- Output nodes emit work - Terminal nodes hand their result (image, draw call, buffer) to the owning system that schedules it, see references/node-model.md
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 61 lines · 135 tokens per session scan A a78346eb358a
node-graph-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 4d ago), licensed MIT. It adds 135 tokens to every session and 1,526 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 2026-09-08.
Other skills, from other repositories
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
cli-anything-photoshop
A command-line tool that controls Adobe Photoshop through Windows automation. It can work with Photoshop documents, layers, selections, text, image adjustments, and exports.
ui-align
Visual-alignment workflow for a new UI need or a UI改进. Index-first (consult the ui-kit registry to avoid re-building an existing primitive), then implement, then run the screenshot harness to capture the component in light/dark against the live /ui-kit, then produce a ReportCard (screenshot assets side by side + a…
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
temps-design-system
Classify a console screen (list/record/form), build it on @temps-sdk/ds templates and the shared shadcn primitives in @temps-sdk/ui, and follow the console's status vocabulary and status colour rules. Use for any new or changed console UI in web/src, and when building or extending web/packages/ds itself.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.