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 gs-bbluhm/gainsight-mcp-plugins --skill staircase-app-designgit clone --depth 1 https://github.com/gs-bbluhm/gainsight-mcp-pluginsWrote 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/gs-bbluhm/gainsight-mcp-plugins/staircase-app-design)<a href="https://agentmods.dev/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-app-design"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-app-design/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/gs-bbluhm/gainsight-mcp-plugins/staircase-app-design"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-app-design.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 | $0.00101 | $0.02207 |
| Opus 5.5 | $0.00040 | $0.00883 |
| Sonnet 5.5 | $0.00020 | $0.00441 |
| Haiku 4.5 | $0.00010 | $0.00221 |
Grade A, and why
staircase-app-design 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 25d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staircase App Design
What this skill is for
The Staircase plugin's output is the product. A CSM or CS leader reading a risk scan, a portfolio pulse, or a voice-of-customer roll-up needs an app: a colored header, metric cards, tabbed navigation, a sortable account table with signal pills, drill-down detail, and where the data earns it, an interactive experience they can explore. Not a 1,000-word markdown wall, which is the single biggest failure mode.
This skill defines two things:
- The deterministic chrome (which components, in what order, per skill). The chrome is fixed for reliability; the content inside is adaptive per run.
- The interactive-experiences pattern (new): how to ship a rich, self-contained interactive HTML app inside a skill. The
staircase-risk-radarpolar radar is the first.
Hardcode chrome plus components for reliability. Adapt content for intelligence. Reach for an interactive experience when the data has structure a table hides.
This plugin is read-only
Staircase reads and synthesizes communication signals. It never writes to a system of record. There are no CTAs, no timeline writes, no cockpit actions, no approval gates for writes, because there are no writes. Every component here surfaces or explains; none of them commit anything. When a component recommends a next move, it renders that move as read-only, copy-ready text the user acts on in their own tools. Content discipline lives in ../../_shared/staircase-output-best-practices.md.
Brand
Staircase dashboards use a vivid indigo brand mark, deliberately deeper and more violet than a generic sky blue so the plugin reads as its own product.
- Staircase primary:
#4B53D4(indigo). Header strip, brand mark, focused/active states, primary accents. - Logo motif: three white ascending stair-bars in a solid indigo circle. It doubles as a metaphor for climbing out of risk. Use it as the app-header icon (an inline SVG of three rising bars); a simple ascending-bars glyph or a neutral chart glyph is an acceptable fallback where an image cannot render.
- Signal colors stay semantic and independent of the brand:
- green = healthy / rising
- yellow = neutral / average (Staircase convention, never "concern")
- red = at-risk / declining
- blue = informational Keep signal-blue lighter than the brand indigo so pills do not blend into the header.
What ships with it
4 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.
- 25d ago First seen · 110 lines · 101 tokens per session scan A 335b1f6fb0a1
staircase-app-design is a skill published in the GitHub repository gs-bbluhm/gainsight-mcp-plugins (4 stars, last pushed 20d ago), licensed MIT. It adds 101 tokens to every session and 2,207 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.