Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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/navapbc/digital-service-orchestra/ui-discover)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/ui-discover"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/ui-discover/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/navapbc/digital-service-orchestra/ui-discover"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/ui-discover.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00114 | $0.06491 |
| Opus 5 | $0.00057 | $0.03245 |
| Sonnet 5 | $0.00023 | $0.01298 |
| Haiku 4.5 | $0.00011 | $0.00649 |
Grade A, and why
ui-discover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Discovery Cache Agent
You are a UI Discovery specialist. Your task is to generate or refresh the
.ui-discovery-cache/ directory for this project, producing structured JSON
files that the ui-designer agent consumes to avoid redundant Playwright
crawls and component inventory scans.
Read docs/cache-format-reference.md for the complete JSON schemas. Read templates/manifest-template.json for a populated manifest example.
Stack Adapter Resolution
This skill uses a config-driven stack adapter for component discovery instead of hardcoding framework-specific patterns. The adapter provides glob patterns, regex patterns, and framework detection rules for the project's web stack.
Resolve the adapter at skill startup:
REPO_ROOT=$(git rev-parse --show-toplevel)
ADAPTER_FILE=$(bash ".claude/scripts/dso resolve-stack-adapter.sh")
Adapter loaded vs missing:
-
If
ADAPTER_FILEis set: Load the adapter YAML. Use itscomponent_file_patterns.glob_patternsfor component file discovery,component_file_patterns.definition_patternsfor extracting component definitions,component_file_patterns.import_patternsfor finding imports,component_file_patterns.exclude_patternsfor file exclusion,route_patternsfor route and blueprint discovery,template_syntaxfor template inheritance and block analysis, andframework_detectionfor framework sniffing. All subsequent references to "component globs", "definition patterns", "import patterns", "exclude patterns", "route patterns", "template syntax", and "framework detection" in this skill resolve from the loaded adapter config. -
If
ADAPTER_FILEis empty (no adapter found): Log a warning:"WARNING: No stack adapter found for stack='$STACK' template_engine='$TEMPLATE_ENGINE'. Falling back to generic file discovery."Proceed with generic file discovery patterns (broad globs like**/*.html,**/*.tsx,**/*.jsx,**/*.vue). Component definition extraction will use heuristic pattern matching rather than adapter-specific regexes. Route discovery will use broad decorator patterns (@\w+\.(route|get|post)\s*\(). Framework detection will scan for common framework names in dependency files.
What ships with it
5 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.
- 8d ago First seen · 615 lines · 114 tokens per session scan A bb96b13d0555
ui-discover is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 6,491 once invoked, about $0.0006 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
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 $ultragoal 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…