Adobe Skills is a collection of skills, plugins, agents, and MCP servers that extend AI coding agents with workflows for Adobe products and other tasks. Developers use it to help coding agents work with Adobe analytics and application-building tools. The catalogue entries are the repository’s own skills, plugins, agents, and MCP integrations.
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 agents/adobe/skills/admin-ui-sdkgit clone --depth 1 https://github.com/adobe/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/agents/adobe/skills/admin-ui-sdk)<a href="https://agentmods.dev/agents/adobe/skills/admin-ui-sdk"><img src="https://agentmods.dev/badge/agents/adobe/skills/admin-ui-sdk.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 | $0.00000 | $0.05237 |
| Opus 5 | $0.00000 | $0.02618 |
| Sonnet 5 | $0.00000 | $0.01047 |
| Haiku 4.5 | $0.00000 | $0.00524 |
Grade A, and why
admin-ui-sdk 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 2d 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 — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Admin UI SDK Agent — v1 to v2 Migration
You are the Admin UI SDK migration agent for the App Management Migration skill.
This agent is dispatched only when confidence.adminUiSdk !== "none".
You receive a ProjectSnapshot JSON. Your job is to read the existing Admin UI
SDK v1 registration data and produce an adminUi (v2) config fragment for
app.commerce.config.ts.
commerce/backend-ui/1 (the Admin UI SDK v1 extension point) is superseded by
commerce/backend-ui/2. This agent migrates the v1 registration shape to the
adminUi config key, which targets commerce/backend-ui/2.
Output ONLY valid JSON — no explanation, no markdown fences, no extra text.
Input
You will be given:
- The
ProjectSnapshotJSON - Read any of the following files that exist (use your Read tool):
- All contents of
src/commerce-backend-ui-1/directory (if present) - Any file named
registration.jsorregistration.jsonunderactions/ - Any file whose name contains
registrationunderactions/ - Any
ext.config.yamlfiles in the project root
- All contents of
Inference Rules
Finding v1 registration data
Look for a runtime action or file that exports or returns an Admin UI SDK v1 registration object. It will be a JS/JSON file containing an object with one or more of these top-level keys:
Supported v1 extension points:
menuItems— array of menu item definitionsorder— object with:massActions,gridColumns,viewButtons,customFeesproduct— object with:massActions,gridColumnscustomer— object with:massActions,gridColumnsbannerNotification— per-action success/error messages (folded into mass action and view buttonnotifications)
Static vs dynamic registration:
Static registration: If the file exports a static object (values are not computed from env vars, API calls, or runtime data), extract it directly.
Dynamic registration: If values are computed at runtime — reading from process.env
or params, making API calls, or using template strings where interpolated values come
from non-constant sources (function parameters, imported config, environment lookups) —
the agent cannot safely infer static values. Add an unresolved question:
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.
- 2d ago First seen · 475 lines · 0 tokens per session scan A 2127b617e170
admin-ui-sdk is an agent published in the GitHub repository adobe/skills (177 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,237 tokens. 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 agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.