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 qte77/claude-code-plugins --skill verifying-design-canvasgit clone --depth 1 https://github.com/qte77/claude-code-pluginsWrote 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/qte77/claude-code-plugins/verifying-design-canvas)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/verifying-design-canvas"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/verifying-design-canvas/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/qte77/claude-code-plugins/verifying-design-canvas"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/verifying-design-canvas.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 | $0.00047 | $0.03441 |
| Opus 5.5 | $0.00019 | $0.01376 |
| Sonnet 5.5 | $0.00009 | $0.00688 |
| Haiku 4.5 | $0.00005 | $0.00344 |
Grade A, and why
verifying-design-canvas 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 3d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying a design canvas against a live app
Use this whenever someone asks whether a deployed app matches its Claude Design source, or
whether a repo's committed docs/design-refs/*.dc.html mirror has drifted from the live canvas.
Learned the hard way: a text-level or default-state-only diff misses real gaps — an interactive
canvas can mock an entire screen that only appears in a non-default state (a role selection, a
tab, a toggle), and a document diff alone won't render it.
Related skills: artifact-design, artifact-diagramming, and artifact-capabilities are
built into the Artifact/Claude Design runtime (not part of this plugin, and not guaranteed present
in every environment) and cover creating a canvas or Artifact — its layout, diagrams, and
capability wiring. This skill only verifies an existing canvas against what's actually deployed;
reach for those instead when the task is building or designing, not checking.
1. Pull the canvas straight from source (not a stale local copy)
The DesignSync tool reads claude.ai/design projects directly — the URL form is
claude.ai/design/p/<projectId>?file=<name>.
DesignSync(method: "get_project", projectId: "<uuid>") # confirms access + canEdit
DesignSync(method: "list_files", projectId: "<uuid>") # find the exact filename (often several:
# "X.dc.html" the editable source,
# "X -export-.dc.html" a frozen export,
# "X.html" a compiled/flattened view —
# read the .dc.html one, it's the source)
DesignSync(method: "get_file", projectId: "<uuid>", path: "<exact filename>")
get_file caps at 256 KiB — and truncates silently, not with an error. A .dc.html canvas
source (plain HTML/CSS/JS) is usually well under that; the compiled bundle variant (often
named without .dc, e.g. "X.html" — base64/gzip blobs inlined) is not, and gets cut off
mid-base64 with no warning (verified against a real project this size). Always fetch the .dc.html
source, never the compiled bundle, and treat an unexpectedly-small or oddly-truncated response as a
cap hit, not a small file.
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.
- 3d ago Changed · +12 lines 8bfdf89baace
- 17d ago Changed b39627c69262
- 22d ago Changed · +47 tokens per session d3fa4a1d355a
- 24d ago Changed · +6 lines · -84 tokens per session 9547126530b3
- 26d ago Changed · +20 lines 4ad4d14b988f
- 29d ago First seen · 169 lines · 84 tokens per session scan A beb1ba052d93
verifying-design-canvas is a skill published in the GitHub repository qte77/claude-code-plugins (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 3,441 once invoked, about $0.0002 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 2026-09-17.
Other skills, from other repositories
customer-journey-map
Create an end-to-end customer journey map with stages, touchpoints, emotions, pain points, and opportunities. Use when mapping the customer experience, identifying friction points, improving onboarding, or visualizing the user journey.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
design-sprint
Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product…
hooked-ux
Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "habit formation", "engagement loops", "habit zone", or "the manipulation matrix". Also trigger when designing notification or re-engagement strategies, building…
steve-jobs-design-review
Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence. Use when the user mentions "Steve Jobs review", "design review", "product review", "what would Steve do", "insanely great", "this feels too complicated", "too many features", "product taste"…