Borrowing it
Nothing to install: this file belongs to rondoflow/rondoflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rondoflow/rondoflow/master/.claude/skills/rondoflow-canvas-node/SKILL.mdgit clone --depth 1 https://github.com/rondoflow/rondoflowWrote 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/rondoflow/rondoflow/rondoflow-canvas-node)<a href="https://agentmods.dev/skills/rondoflow/rondoflow/rondoflow-canvas-node"><img src="https://agentmods.dev/badge/skills/rondoflow/rondoflow/rondoflow-canvas-node/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/rondoflow/rondoflow/rondoflow-canvas-node"><img src="https://agentmods.dev/badge/skills/rondoflow/rondoflow/rondoflow-canvas-node.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 81 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 82 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.01231 |
| Opus 5 | $0.00043 | $0.00616 |
| Sonnet 5 | $0.00017 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
rondoflow-canvas-node 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 10d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RondoFlow Canvas Nodes
A workflow is a React Flow graph that gets compiled into an ordered/branched list of execution steps. The critical thing to know: there are two independent compilers, and a node that only one of them understands works in one run path and is silently dropped in the other.
The two run paths (keep them in sync!)
| Path | Compiler | Trigger |
|---|---|---|
| Interactive (user clicks Run in the canvas) | packages/ui/src/lib/chain-utils.ts |
browser → socket |
| Headless / scheduled (Scheduler, cron, API) | packages/server/src/engine/canvas-chain.ts |
server-side |
Both turn { nodes, edges } into steps for chain-executor.ts, but they are separate
codebases that must agree. They have already drifted:
chain-utils.ts(UI) treats'agent' | 'structurer' | 'db-save' | 'http-request' | 'duckduckgo-search'as executable steps (see itsStepNodeTypeunion, ~L10 and thenodeTypemapping ~L249-266).canvas-chain.ts(server) only recognizes'agent' | 'structurer' | 'db-save'(the executable filter ~L118).http-requestandduckduckgo-searchare NOT compiled server-side, so they run interactively but vanish from scheduled runs.
⚠️ Whenever you add or change an executable node type, edit BOTH
chain-utils.tsandcanvas-chain.ts. If you only touch one, the node will work in one run path and silently no-op in the other. This is the single most common bug class for nodes.
Where each piece lives
packages/shared/src/canvas.ts # node/edge/data TYPES (shared contract)
packages/ui/src/components/canvas/nodes/*.tsx # React Flow node components (visuals + editing)
packages/ui/src/components/canvas/canvas-palette.tsx # drag-to-canvas palette entry
packages/ui/src/lib/chain-utils.ts # UI compiler: graph → steps (interactive)
packages/server/src/engine/canvas-chain.ts # server compiler: graph → steps (headless)
packages/server/src/engine/chain-executor.ts # DAG runner (parallel branches), both paths
packages/server/src/engine/<kind>-runner.ts # per-kind execution (agent-runner, http-request-runner, duckduckgo-search-runner, ...)
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.
- 10d ago First seen · 92 lines · 85 tokens per session scan A 4a34be4a2c02
rondoflow-canvas-node is a skill published in the GitHub repository rondoflow/rondoflow (19 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 1,231 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
factory-render-verify
Render-and-measure receipts for any HTML page your factory builds — the render half of the design quality gate. Engineer runs it to screenshot every screen size and MEASURE what a source read or a single screenshot only guesses at: horizontal overflow, computed type sizes, tap-target sizes, safe-area presence, mono…
biome
Use when the user wants to format or lint JavaScript, TypeScript, JSX, TSX, JSON, JSONC, CSS, GraphQL, HTML, Vue, Svelte, or Astro - biome is the unified Rust-based replacement for prettier + eslint, doing both with one binary and one config file.
worker-visualizer
A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…
webgl-particle-galaxy
A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…
webgl-aurora-veil
A self-contained WebGL2 hero: layered aurora light curtains warped over a night sky scattered with stars; move the cursor to sway the veil.