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/ytvee-dev/webdev-agent-kit/design-screenshot-specnpx skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-specgit clone --depth 1 https://github.com/ytvee-dev/webdev-agent-kitWhat 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 | $0.00038 | $0.01513 |
| Opus 5 | $0.00019 | $0.00757 |
| Sonnet 5 | $0.00008 | $0.00303 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
design-screenshot-spec 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Screenshot Spec
Purpose
Convert user-supplied Figma screenshots, copied visual inspect panels, exported
assets, and design notes into a strict Design Implementation Spec for a
frontend implementer.
When To Use
- The user sends screenshots of Figma frames, components, screens, or inspect panels.
- The user asks to analyze a visual design before implementation.
- The next step is frontend layout work and the implementer needs a structured spec.
When Not To Use
- The user asks for live Figma inspection, canvas editing, file creation, Figma whiteboard workflows, design-system generation, or Code Connect.
- The user supplies only a Figma URL, file key, or node id without screenshots or copied design material.
- The user already provides a complete
Design Implementation Specand asks to implement it. Usefrontend-layout-implementer.
Required Context
- Read
AGENTS.md. - Confirm the classified task is
design-specor design intake for later frontend implementation. - Read
common/approved-patterns.md. - Read
common/anti-patterns.md. - Read
project/design-reference-profile.mdwhen present. - Read
references/spec-extraction-checklist.md.
Tool Contract
- Do not use Figma MCP.
- Use Visual Reference MCP when available for user-supplied image references.
- Use Design Spec MCP when available to store or read structured specs.
- If those MCP servers are unavailable, work from attached images, local image files, copied inspect text, and user-provided notes.
- Do not open live Figma links.
Workflow
- Inventory all supplied artifacts: screenshots, inspect panels, exported assets, dimensions, fonts, colors, states, notes, and target screens.
- If only a Figma URL, file key, node id, Figma whiteboard reference is present, stop and ask for screenshots, exported assets, copied inspect values, or a written brief.
- Group screenshots by screen, component, state, and viewport. For each screenshot, record the visible frame or viewport width, height, state, screen or component ownership, and confidence.
- Treat each screenshot or design-frame size as a reference coordinate system, not as a production container cap. Record whether containment is explicitly visible and capture desktop edge anchors plus expected behavior beyond the reference viewport.
- Extract visible layout, hierarchy, typography, color, spacing, sizing, radius, shadow, assets, states, and responsive behavior.
- For typography, prefer copied inspect values or selected-text properties for
font-family,font-size,font-weight,line-height, color, alignment, max width, and wrapping. When properties are unavailable, estimate from the screenshot and mark each estimate asscreenshot-inferred. - For spacing, separate outside margins, section rhythm, inter-component gaps, container padding, and internal control padding instead of merging them into one generic gap value.
- Mark each value as
source-provided,screenshot-inferred, orunknown. - Resolve conflicts by preferring copied inspect values and exported values over screenshot estimates.
- Ask the user about disputed or low-confidence values when the answer changes layout, responsive behavior, visual hierarchy, typography, or implementation acceptance.
- Produce the
Design Implementation Specand stop unless the user also asks for implementation. - Route to
frontend-design-directorbefore implementation when the supplied material needs redesign, polish, distinctive visual direction, anti-template critique, interface-copy stance, motion stance, or visual acceptance criteria.
What ships with it
2 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.
- 3d ago First seen · 169 lines · 38 tokens per session scan A 5be2d0a5e09a
design-screenshot-spec is a skill published in the GitHub repository ytvee-dev/webdev-agent-kit (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,513 once invoked, about $0.0002 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
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
shipping-reproducible-results
Package completed data analysis and ML work so an independent recipient can reproduce the claimed results, verify artifact lineage, and operate the handoff within its stated scope. Use when finalizing a project, study, model package, or review bundle; not for deploying to a live system.
actions-reusable-workflows
Wire a repository to the bitwise-media-group/github-workflows reusable workflows — thin, SHA-pinned caller workflows for CI, security (CodeQL) scanning, release (release-please/GoReleaser/Zensical docs), the signature-preserving fast-forward /merge + merge-review-ack + merge-notice flows, and add-to-project — plus the…
go-style
Modern Go code style for stdlib-first programs — error wrapping with %w, sentinel errors, structured logging with log/slog, context threading, consumer-defined interfaces, nil-safe constructors, net/http servers with method-pattern routing, flag/env configuration for services, and cobra commands with viper…
diagnosing-ml-failures
Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance…