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-deploygit 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-deploy)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-ui-bundle-deploy"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-ui-bundle-deploy.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 5.1 | $0.00234 | $0.04380 |
| Opus 5 | $0.00117 | $0.02190 |
| Sonnet 5 | $0.00047 | $0.00876 |
| Haiku 4.5 | $0.00023 | $0.00438 |
Grade A, and why
experience-ui-bundle-deploy 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 yesterday.
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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploying a UI Bundle App
Deploy order is load-bearing: a step's output is the next step's precondition
(deploy before schema fetch; permissions before schema fetch; role/self-reg
before the schema the guest user must see). This is the canonical setup sequence,
ported from the reference org-setup.mjs. The org-setup.mjs line
citations in references/ are port-provenance (why each rule exists) pointing at
that external reference script — not files shipped with this skill — so you don't
need to open them to run the steps.
Run each step in order. Every optional step is presence-driven: if its convention file is absent, no-op cleanly and move on — do not fabricate config. For the two destructive/expensive steps (self-registration, data import), ask the user before running.
Inputs to gather up front
Read these from the project; ask the user only for what's missing:
- Target org — alias/username for
--target-org. Ask if not obvious. - Source root — run
scripts/get-source-root.shto resolve the metadata source dir fromsfdx-project.json(packageDirectories[0].path+/main/default). It exits non-zero if the project file is missing or malformed. Never hardcodeforce-app/main/default. org-setup.config.json(optional) — drives permset assignment, role, self-registration, and social login. Absent keys mean "skip that step". Exception: if the file is missing butpermissionsets/has permsets to assign, don't silently skip — scaffold the config or gather equivalent inputs (see step 4).data-plan.json(optional, in the project'sdata/dir) — presence enables the data step.
Step 1 — Org authentication (always)
Unconditional precondition; cannot be skipped. If the org is already connected
(sf org display --target-org <org> --json succeeds), no-op. Otherwise:
sf org login web --alias <org>
A failed login aborts the whole setup before deploy.
Step 2 — Pre-deploy UI bundle build
What ships with it
22 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/Communities.settings-meta.xml 1001 B
- assets/data-delete.apex 1.6 KB
- assets/data-import.apex 3.0 KB
- assets/network-selfreg-xml-recipe.md 3.5 KB
- assets/network-selfreg.apex 2.1 KB
- assets/org-setup.config.template.json 662 B
- assets/prepare-import-unique-fields.js 1.7 KB runs code
- assets/social-login-auth-providers.apex 6.7 KB
- references/config-scaffold.md 5.6 KB
- references/data-import.md 5.1 KB
- references/dev-preview.md 3.2 KB
- references/graphql.md 1.1 KB
- references/license-checks.md 2.8 KB
- references/logout-url.md 4.8 KB
- references/role-assignment.md 1.4 KB
- references/self-registration.md 4.0 KB
- references/social-login.md 11 KB
- scripts/derive-site-name.sh 1.3 KB runs code
- scripts/find-data-plan.sh 1.3 KB runs code
- scripts/find-prep-script.sh 1.1 KB runs code
- scripts/get-source-root.sh 989 B runs code
- scripts/set-logout-url.mjs 11 KB runs code
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.
- yesterday Changed · +41 lines · -1 tokens per session 4b89307d5d08
- 7d ago First seen · 314 lines · 235 tokens per session scan A b6c287765bce
experience-ui-bundle-deploy is a skill published in the GitHub repository forcedotcom/sf-skills (966 stars, last pushed yesterday), licensed Apache-2.0. It adds 234 tokens to every session and 4,380 once invoked, about $0.0012 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
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.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…
vite
Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.