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 amplitude/mcp-marketplace --skill analyze-account-healthgit clone --depth 1 https://github.com/amplitude/mcp-marketplaceWrote 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/amplitude/mcp-marketplace/analyze-account-health)<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/analyze-account-health"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/analyze-account-health/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/amplitude/mcp-marketplace/analyze-account-health"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/analyze-account-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01876 |
| Opus 5 | $0.00023 | $0.00938 |
| Sonnet 5 | $0.00009 | $0.00375 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade A, and why
analyze-account-health 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 7d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Account Health
Deep-dive into a B2B account's product usage to prepare for QBRs, assess renewal risk, identify expansion opportunities, or prioritize CS outreach.
Instructions
Step 0: Identify Account & Discover Context
Get the account identifier:
- Company name, org ID, account ID, or group property value
- Ask user if not provided
Search for existing work:
Use Amplitude:search_amp_entities to find existing dashboards, charts, or notebooks for this account. If found, ask user if they want fresh analysis or to review existing.
Resolve how accounts are modelled — do this before any query. Every step below breaks down "by account", and there are three different ways a project represents one. Check in this order and reuse the answer throughout:
- Use the connected catalog's group-type discovery capability. If the project
has a group type (commonly
org idorcompany), that is the account. Read its attributes from the active taxonomy reader's group-property surface, then reference them withscope: 'group'plusgroup_type. To count accounts rather than users, setcount_unique_byto the group type. - If there is no group type, the account is usually a user property
(
company,org_name) —scope: 'user'. - Failing both, an event property carrying the org (
org id,org url).
If a group property comes back as Invalid group property … for group type …,
the query engine's registry is missing it — that is a platform gap, not a
naming mistake. Do not retry spelling variants. Fall back to the user- or
event-level equivalent from (2)/(3), and tell the user which representation you
used, since the numbers are not interchangeable.
Step 1: Quick Health Triage
Use Amplitude:query_amplitude_data to run these queries in parallel:
Usage Trend:
- Event:
_active, Metric:uniques, Group by: the account property resolved in Step 0 (with its scope) - Time: Last 60 days, daily interval
- Shows: Activity increasing or decreasing?
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.
- 7d ago Changed c26ce9be3bc0
- 13d ago First seen · 235 lines · 46 tokens per session scan A 5eb3b32d18d6
analyze-account-health is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 1,876 once invoked, about $0.0002 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 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…