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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-code-webflowgit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-webflow)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-webflow"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-webflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.04591 |
| Opus 5 | $0.00022 | $0.02295 |
| Sonnet 5 | $0.00009 | $0.00918 |
| Haiku 4.5 | $0.00004 | $0.00459 |
Grade A, and why
sk-code-webflow 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 4d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
webflow Surface — Frontend Evidence
Domain evidence and shared workflow doctrine for browser/Webflow frontend work. This surface owns the implement -> debug -> verify phases through the workflow references below, and acts on the evidence gathered here when the hub detects a Webflow surface. Detection markers: src/2_javascript, webflow, --vw- custom properties, CDN-delivered client scripts.
1. WHEN THE HUB BUNDLES THIS
- The task touches Webflow-published pages, CDN-delivered
webflow.js/client scripts, orsrc/2_javascriptsources. - The active workflow phase needs frontend standards (CSS/HTML/JS), an implementation pattern, a performance remediation, a deployment step, or a browser debugging/verification procedure.
- This surface owns edits, tests, and verification through the workflow references; hand off formal findings-first review to
code-reviewand author-side quality gates tocode-quality.
2. REFERENCE MAP
Language standards (load the detected language's trio; a frontend task legitimately spans all three):
- CSS —
references/css/style-guide.md,references/css/quality-standards/patterns-and-naming-enforcement.md,references/css/quality-standards/typography-autofill-and-color.md,references/css/quality-standards/focus-has-print-and-quick-reference.md,references/css/quick-reference.md,references/css/patterns/tokens-state-machine-and-triggers.md,references/css/patterns/data-attributes-and-forms.md,references/css/patterns/focus-accessibility-and-mobile.md,references/css/patterns/designer-component-and-performance.md,references/css/patterns/quick-reference-and-related.md - HTML —
references/html/style-guide.md,references/html/quality-standards.md - JavaScript —
references/javascript/style-guide/overview-naming-and-structure.md,references/javascript/style-guide/formatting.md,references/javascript/style-guide/commenting-and-related.md,references/javascript/quality-standards/init-dom-error-and-async.md,references/javascript/quality-standards/observer-validation-and-performance.md,references/javascript/quality-standards/state-and-cleanup.md,references/javascript/quality-standards/shared-listener-and-weakmap.md,references/javascript/quality-standards/enforcement-and-quick-reference.md,references/javascript/quick-reference.md
What ships with it
60 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.
- assets/animation/install-card.md 3.1 KB
- assets/animation/playbook-entries.md 6.6 KB
- assets/animation/snippets/animate-on-scroll.js 1.5 KB runs code
- assets/animation/snippets/cdn-bootstrap.js 1.8 KB runs code
- assets/animation/snippets/es-module-bootstrap.js 2.3 KB runs code
- assets/animation/snippets/hover-gesture.js 1.1 KB runs code
- assets/animation/snippets/in-view-reveal.js 893 B runs code
- assets/animation/snippets/layout-transition.js 1.3 KB runs code
- assets/animation/snippets/principled-reveal.js 2.3 KB runs code
- assets/animation/snippets/README.md 3.9 KB
- assets/animation/snippets/spring-animation.js 1.0 KB runs code
- assets/animation/snippets/stagger-animation.js 1.0 KB runs code
- assets/animation/snippets/timeline-sequence.js 1.2 KB runs code
- assets/integrations/hls-patterns.js 23 KB runs code
- assets/integrations/lenis-patterns.js 14 KB runs code
- assets/integrations/README.md 3.5 KB
- assets/patterns/interaction-gate-patterns.js 6.5 KB runs code
- assets/patterns/performance-patterns.js 17 KB runs code
- assets/patterns/README.md 3.6 KB
- assets/patterns/validation-patterns.js 50 KB runs code
- assets/patterns/wait-patterns.js 23 KB runs code
- assets/scripts/minify-webflow.mjs 8.7 KB runs code
- assets/scripts/README.md 3.5 KB
- assets/scripts/test-minified-runtime.mjs 12 KB runs code
- assets/scripts/verify-minification.mjs 12 KB runs code
- assets/templates/component-template.css 6.9 KB
- assets/templates/component-template.js 8.7 KB runs code
- assets/templates/embed-template.html 3.8 KB
- assets/templates/form-scaffold-template.html 8.7 KB
- assets/templates/head-footer-code-template.html 9.2 KB
- assets/templates/README.md 3.7 KB
- assets/webflow-debugging-checklist.md 6.3 KB
- assets/webflow-verification-checklist.md 7.0 KB
- benchmark/reports/2026-07-10--live-mode-b--live/failed-runs.md 1.0 KB
- benchmark/reports/2026-07-10--live-mode-b--live/findings-and-recommendations.md 457 B
- benchmark/reports/2026-07-10--live-mode-b--live/README.md 1.4 KB
- benchmark/reports/2026-07-10--live-mode-b--live/results.csv 890 B
- benchmark/reports/2026-07-10--live-mode-b--live/skill-benchmark-report.json 35 KB
- benchmark/reports/2026-07-10--live-mode-b--live/skill-benchmark-report.md 2.4 KB
- benchmark/reports/2026-07-10--live-mode-b--live/source.md 909 B
- benchmark/reports/2026-07-10--router-mode-a--router/failed-runs.md 191 B
- benchmark/reports/2026-07-10--router-mode-a--router/findings-and-recommendations.md 238 B
- benchmark/reports/2026-07-10--router-mode-a--router/README.md 1.4 KB
- benchmark/reports/2026-07-10--router-mode-a--router/results.csv 957 B
- benchmark/reports/2026-07-10--router-mode-a--router/skill-benchmark-report.json 30 KB
- benchmark/reports/2026-07-10--router-mode-a--router/skill-benchmark-report.md 3.0 KB
- benchmark/reports/2026-07-10--router-mode-a--router/source.md 920 B
- benchmark/reports/README.md 1.5 KB
- changelog/v1.0.0.0.md 1.4 KB
- changelog/v1.1.0.0.md 1.5 KB
- manual-testing-playbook/deployment-forms-video/deployment-routing.md 5.8 KB
- manual-testing-playbook/deployment-forms-video/forms-routing.md 5.8 KB
- manual-testing-playbook/deployment-forms-video/video-routing.md 5.5 KB
- manual-testing-playbook/implementation-quality/code-quality-routing.md 5.2 KB
- manual-testing-playbook/implementation-quality/debugging-routing.md 6.3 KB
- manual-testing-playbook/implementation-quality/implementation-routing.md 8.5 KB
- manual-testing-playbook/implementation-quality/testing-routing.md 5.1 KB
- manual-testing-playbook/implementation-quality/verification-routing.md 5.8 KB
- manual-testing-playbook/language-standards/language-standards-routing.md 7.9 KB
- manual-testing-playbook/manual-testing-playbook.md 4.0 KB
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.
- 4d ago First seen · 241 lines · 44 tokens per session scan A 5466e2781566
sk-code-webflow is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 4,591 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 2026-09-03.
Other skills, from other repositories
figma-to-webui
Recreate Figma design frames as production-ready Chromium WebUI code following Chrome's Lit-element architecture and styling guidelines. Use when asked to create WebUI code from a Figma frame URL.
generate-token-map
Maps all Figma design tokens from figma-variables.md to their equivalent C++ (Views) identifiers, CSS (WebUI) variables, and Clank (Android) resource attributes/macros/methods in Chromium, and saves the formatted mapping table to the assets directory of the Chrome Design System project. Use this skill when asked to…
agent-canvas
Interactive element picker for web pages. Opens a browser with click-to-select UI overlay. Use when you need to let users visually select DOM elements, identify element selectors, or get detailed element information interactively. Triggers on "select an element", "pick element", "let me choose", "which element", or…
clone-website
Reverse-engineer and clone a website in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a…
responsiveness-check
Test website responsiveness across viewport widths using browser automation. Resizes a single session through breakpoints, screenshots each width, and detects layout transitions (column changes, nav switches, overflow). Produces comparison reports showing exactly where layouts break. Trigger with 'responsiveness…
html-craft
Create and verify single-file interactive HTML pages in the sandbox: build or edit the file, then prove the result with headless-Chromium screenshots, in-page DOM/geometry assertions, and JS-error capture (Playwright). No GPU, no service, no network. Use when the user wants an HTML page, animation, demo, dashboard, or…