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-2gp-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-2gp-deploy)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-ui-bundle-2gp-deploy"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-ui-bundle-2gp-deploy.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 317 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 330 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 359 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Tool Misuse · line 317 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 330 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 359 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00193 | $0.05523 |
| Opus 5 | $0.00097 | $0.02762 |
| Sonnet 5 | $0.00039 | $0.01105 |
| Haiku 4.5 | $0.00019 | $0.00552 |
Grade A, and why
experience-ui-bundle-2gp-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 9d 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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package an existing UI Bundle (2GP)
How to take a UI Bundle that already exists in the current project
(under <packageDir>/uiBundles/<name>/, where <packageDir> is the package
directory from sfdx-project.json — commonly force-app/main/default) and ship
it as a second-generation package (2GP), then install / upgrade / uninstall
it in another org.
This is reference knowledge, not a runbook to execute top-to-bottom. The user already has a project and a built (or buildable) bundle. Read their intent and apply only the matching part:
Answer only what was asked. Give the commands for the one part the user
needs plus the org each targets and any genuine caveat — nothing else. Do not
restate the other parts, re-explain the flavor table, or replay the full
build→create→install→promote sequence when the user asked about a single step. A
debug question wants the fix, not a packaging tutorial; an install question wants
the sf package install line and the subscriber-vs-Dev-Hub distinction, not
Part 1 and Part 2. Brevity is correctness here.
| The user wants to… | Go to |
|---|---|
| Decide managed vs. unlocked | Choose a flavor |
| Make the bundle packageable / wire a CustomApplication | Part 1 |
| Create the package or a new version | Part 2 |
| Install / upgrade / uninstall / promote | Part 3 |
| Debug a failure | Part 4 + Troubleshooting |
This skill is for packaging and cross-org distribution (sf package …). For
plain source deploy of a bundle into one org (sf project deploy …), use
experience-ui-bundle-deploy instead. Never sf project generate or
sf template generate ui-bundle here — the project and bundle exist.
MyReactApp / force-app / force-app/main/default are placeholders; substitute
the user's real bundle name and their <packageDir> everywhere they appear
below. Resolve <packageDir> deterministically — never guess [0] in a
multi-package project — with:
packageDir="$(scripts/find-bundle-package-dir.sh <bundleName>)" # walks packageDirectories; picks the entry whose tree contains uiBundles/<bundleName>/
What ships with it
3 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.
- 9d ago First seen · 456 lines · 193 tokens per session scan A 78f7a8f0659b
experience-ui-bundle-2gp-deploy is a skill published in the GitHub repository forcedotcom/sf-skills (974 stars, last pushed today), licensed Apache-2.0. It adds 193 tokens to every session and 5,523 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…