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 gainsight-exec-pattern-huntergit 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/gainsight-exec-pattern-hunter)<a href="https://agentmods.dev/skills/gs-bbluhm/gainsight-mcp-plugins/gainsight-exec-pattern-hunter"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/gainsight-exec-pattern-hunter/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/gainsight-exec-pattern-hunter"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/gainsight-exec-pattern-hunter.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 | $0.00059 | $0.02726 |
| Opus 5 | $0.00030 | $0.01363 |
| Sonnet 5 | $0.00012 | $0.00545 |
| Haiku 4.5 | $0.00006 | $0.00273 |
Grade A, and why
gainsight-exec-pattern-hunter 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staircase Pattern Hunter
Discovery
Auto-trigger phrases:
- "what are the patterns across our customers"
- "themes across the book"
- "what's happening across the portfolio"
- "cross-account trends"
- "voice of customer patterns"
- "common feature requests this quarter"
- "what friction is repeating"
Purpose: Portfolio-wide thematic view grounded in actual customer language. Staircase MCP cross-account queries support up to ~15 accounts in a single grouped-theme query with evidence IDs.
Optimized for: Cowork (theme card with expandable account lists) and Code (full markdown report). Cowork is the primary optimization target.
Foundation references
Read these BEFORE composing operations:
User profile (if exists):
~/.gainsight-mcp/user-profile.md— name, role, filter field, filter value. Apply role-appropriate defaults + filter automatically. If profile doesn't exist, prompt user to rungainsight-mcp-setup.
Foundation skills (for MCP mechanics):
../staircase-mcp-expert/references/query-patterns.md— validated phrasings + decompose-and-intersect../staircase-mcp-expert/references/anti-patterns.md— 15-cap clarification, OR not supported, determinism mitigations../staircase-mcp-expert/references/field-catalog.md— what's queryable
Output discipline (for any customer-facing write):
../../_shared/gainsight-output-best-practices.md(v1.1)
Rendering discipline (for Cowork app-feel):
../mcp-app-design/references/patterns.md— tab structure, action tee-up sequence, preference question cards, working mode picker, color/badge semantics
⚡ Pre-query quality gate (mandatory before any non-trivial Staircase query plan)
Canonical reference: plugins/gainsight-cs/skills/staircase-mcp-expert/references/query-patterns.md — top-of-doc Execution Checklist. 30-second scan before composing.
Composition rules — run mentally per query:
- One dimension per
askquery. AND/OR composition fails. Decompose first, intersect client-side. - Scope explicitly. "My accounts" doesn't auto-scope. Filter by the org's team-member field (
Csm/Owner/ org-bespoke — read from user profile or discover viagainsight-cs-mcp-expert/references/org-discovery.md). - No abstract score requests to the MCP. Pull raw fields; compute "urgency" / "composite priority" / "save-into-expansion score" client-side.
- 15-cap discipline. The 15 is for PARALLEL per-account analysis fan-out. Cross-account LIST queries return 25-100+ accounts routinely. Use long-list-then-prioritize-15 for portfolio-wide work.
- Action-verb phrasing for
analyze_account. "Summarize / Identify / Draft / List" outperforms "What are the current X." - Risk × Expansion are INDEPENDENT. Pull both. Merge client-side with recency weighting + stakeholder reconciliation + classification. NEVER expose Save-then-Expand / Skeptical Read / Expansion-as-Save labels in customer-facing fields.
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 · 254 lines · 59 tokens per session scan A a55caa42ab68
gainsight-exec-pattern-hunter is a skill published in the GitHub repository gs-bbluhm/gainsight-mcp-plugins (4 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 2,726 once invoked, about $0.0003 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 2026-08-31.
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…