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-setupgit 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-setup)<a href="https://agentmods.dev/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-setup"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-setup/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-setup"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-setup.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 | $0.00108 | $0.01625 |
| Opus 5.5 | $0.00043 | $0.00650 |
| Sonnet 5.5 | $0.00022 | $0.00325 |
| Haiku 4.5 | $0.00011 | $0.00162 |
Grade A, and why
staircase-setup 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staircase Setup
What this skill is for
Every Staircase skill already resolves scope on its first call (the first-call contract in ../staircase-mcp-expert/SKILL.md, step 0). This skill runs that same contract as a friendly first-run experience: it shows the user how they appear in Staircase, confirms anything ambiguous, and lets them feel the payoff with one or two real results. Nothing here is required; a user can skip straight to any workflow skill.
Rhythm: one question per step, clear options, no walls of text.
The flow
Step 1: Connect
Call staircase_report_metadata.
- It works: note
current_user_id, the role fields (everycustomer.*field whosereferencedEntityisuser), and thelifecycle_event.typeoptions. Move on. - No Staircase tools, or an auth error: stop and explain how to connect. In Claude (web, desktop, Cowork), add Staircase AI as a connector in claude.ai connector settings. In Claude Code, run
claude mcp add --transport http staircase-ai https://mcp.staircase.ai/mcp, then authenticate. Offer to continue once it's connected.
Step 2: Show them how they appear in Staircase
Run the scope.membership recipe (../staircase-mcp-expert/references/report-recipes.md) for current_user_id. Show a small table: name, title, manager, and the account count under each role field that isn't zero.
Then decide scope:
| What membership shows | What to do |
|---|---|
| One role field with accounts | That's their book. Say so in one line: "You're the on N active accounts; I'll use those as your accounts." |
| Two or more role fields with accounts | Ask one question: "You show up as on N accounts and on M. Which should 'my accounts' mean?" Offer both plus "both." |
| No role fields, and people who report to them hold books | Team scope. "You don't carry a book, but N people on your team do. I'll default to your team's accounts." |
| No role fields, and no reports who hold books | Portfolio scope. "You don't carry a book, so I'll default to the whole portfolio." |
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 · 96 lines · 108 tokens per session scan A 00d456031216
staircase-setup is a skill published in the GitHub repository gs-bbluhm/gainsight-mcp-plugins (4 stars, last pushed 20d ago), licensed MIT. It adds 108 tokens to every session and 1,625 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…