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/evolplus/talos/figma-canvas-layoutnpx skills add evolplus/talos --skill figma-canvas-layoutgit clone --depth 1 https://github.com/evolplus/talosWrote 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/evolplus/talos/figma-canvas-layout)<a href="https://agentmods.dev/skills/evolplus/talos/figma-canvas-layout"><img src="https://agentmods.dev/badge/skills/evolplus/talos/figma-canvas-layout.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 | $0.00064 | $0.03554 |
| Opus 5 | $0.00032 | $0.01777 |
| Sonnet 5 | $0.00013 | $0.00711 |
| Haiku 4.5 | $0.00006 | $0.00355 |
Grade A, and why
figma-canvas-layout 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 5d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Canvas Layout
When to use
You are the UI/UX Designer authoring or revising Figma content via MCP. The kit requires a reviewable canvas arrangement before handoff because two consumers see your canvas directly:
- The Designated Design Approver opens the Figma file at confirmation time (design lifecycle Step 4,
.claude/rules/parallel-execution.md§4). Visual chaos on the canvas — long-scroll screens bleeding over neighbors, frames jumbled without grouping — produces falseunqualifiedBA Phase 3 verdicts and slower approval cycles. - QA-Author generates
docs/uiux/visual-specs/<task-id>.mdand may export page-level Figma snapshots. Overlapping frames muddy page exports; frame-level exports stay clean, but the operator reviewing the visual spec sees both.
FE Dev consumes frame data via MCP node-by-node and is less sensitive to canvas layout, but the design lifecycle still treats canvas readability as a handoff quality gate. A clean frame export is not enough; the scoped Figma page must also be usable for human review.
Inputs and outputs
- Inputs: SRS UI surfaces (SRS §3.4.1 Design References), the Figma file you're writing to via MCP, the current
## Design Referencesstate. - Outputs: A Figma file whose frames satisfy the layout rules below and pass the pre-handoff overlap lint; frame names that map 1:1 to handoff-doc anchors; an updated handoff doc with the lint result recorded.
Layout rules
The kit prescribes deterministic placement + lint. Choose the reading direction that fits the flow, but always compute explicit coordinates before writing or moving frames. Do not rely on Figma's default origin placement; stacked frames at (0, 0) or visually overlapping long-scroll screens fail handoff.
Placement contract
Use the resolved Figma-Design-Page-Node-ID from ui-ux-page-scoping as the only screen canvas for the dispatch.
- Group screens by US-ID or bounded feature flow.
- Create one Figma Section per group when the page has more than five frames.
- Place each section in a predictable grid:
- Start at
CANVAS_ORIGIN_X = 0,CANVAS_ORIGIN_Y = 0unless existing scoped frames already occupy that region. - Use
SECTION_GAP_X = 1200pxandSECTION_GAP_Y = 1200pxbetween sections. - Within a section, use
FRAME_GAP_X = max(240px, 0.15 * widest-frame-width-in-row). - Within a section, use
FRAME_GAP_Y = max(320px, 0.25 * tallest-frame-height-in-row). - Long-scroll frames define the row height; never let a short neighbor's height determine the vertical step.
- Start at
- Set
xandyexplicitly for every newly created or revised top-level screen frame. - After writing frames, re-enumerate bounding boxes and run the overlap lint. If any frame moved because of a collision, record it in the handoff
## Canvas Layout Lintnotes.
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.
- 5d ago First seen · 224 lines · 64 tokens per session scan A 8afd96ec13b8
figma-canvas-layout is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 3,554 once invoked, about $0.0003 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
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…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…