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 forcedotcom/sf-skills --skill experience-ui-bundle-frontend-generategit clone --depth 1 https://github.com/forcedotcom/sf-skillsWrote 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/forcedotcom/sf-skills/experience-ui-bundle-frontend-generate)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-ui-bundle-frontend-generate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-ui-bundle-frontend-generate/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/forcedotcom/sf-skills/experience-ui-bundle-frontend-generate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-ui-bundle-frontend-generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00211 | $0.03275 |
| Opus 5 | $0.00105 | $0.01638 |
| Sonnet 5 | $0.00042 | $0.00655 |
| Haiku 4.5 | $0.00021 | $0.00328 |
Grade A, and why
experience-ui-bundle-frontend-generate 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Bundle UI
Resolve the Bundle Directory
MUST run scripts/resolve-ui-bundle.sh [project-root] before applying any rule below or writing any file — an ad-hoc find/ls is not a substitute; it does not enforce the exit-code gate below. It reads sfdx-project.json's packageDirectories[0].path (does not assume force-app — the source path is configurable) and looks under <sourceDir>/main/default/uiBundles/:
- Exit 0, bundle path printed to stdout: exactly one bundle directory found — that is the bundle directory. Use that exact directory name; never substitute a different name (e.g. a generic "AcmePortal" example from a prompt template) for the one actually printed.
- Exit 2, candidates printed to stderr: multiple
uiBundles/*subdirectories exist — do not guess, and do not write to any of them, or to a bundle name not in the printed list. Ask the user which app/bundle they mean before editing or running any command. - Exit 1:
sfdx-project.jsonmissing/invalid, or no bundle directory found at all.
Run all npm/lint/build/dev commands from inside the resolved bundle directory, never from the project root.
Preconditions
Before applying any rule below, confirm this is an existing, scaffolded UI bundle: MUST run scripts/check-preconditions.sh <bundle-dir> with the directory resolve-ui-bundle.sh printed.
- Single-bundle (exit 0) case: run it once, on that bundle.
- Multi-bundle (exit 2) case: do not run it yet — first ask the user which app/bundle they mean, per the Resolve step above. Once the user names the bundle, run
check-preconditions.shon that one bundle only. Never run it against multiple candidates speculatively before the user has chosen — that means touching/inspecting bundles the user didn't ask about. - Exit 0: the bundle has
src/appLayout.tsx,src/routes.tsx, andsrc/components/ui/— proceed. - Exit 1, missing pieces listed: this is a fresh SFDX project, a non-UI-bundle React project, or a partially-scaffolded bundle — stop. Do not fall back to generic React knowledge (e.g.
react-router-dom, a hardcoded basename, or raw HTML), and do not hand-writeappLayout.tsx/routes.tsx/a page/a component to "fill in" the missing scaffold, even for a casual, vague, or urgent-sounding request ("just change the header", "make the background blue"). Tell the user the bundle isn't scaffolded yet and direct them toexperience-ui-bundle-app-coordinate(orexperience-ui-bundle-metadata-generate) to scaffold it first. If, after the user names their intended bundle, that one turns out to be unscaffolded, stop and redirect for it — do not silently switch to scaffolding a different candidate instead.
What ships with it
6 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.
- 10d ago First seen · 198 lines · 211 tokens per session scan A e7cc9af68bc2
experience-ui-bundle-frontend-generate is a skill published in the GitHub repository forcedotcom/sf-skills (978 stars, last pushed 2d ago), licensed Apache-2.0. It adds 211 tokens to every session and 3,275 once invoked, about $0.0011 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…