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 chart-link-analysisgit 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/chart-link-analysis)<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/chart-link-analysis"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/chart-link-analysis/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/chart-link-analysis"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/chart-link-analysis.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 | $0.00065 | $0.00661 |
| Opus 5 | $0.00032 | $0.00331 |
| Sonnet 5 | $0.00013 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
chart-link-analysis 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 10d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chart Link Analysis
Second most common job: the user pastes a link and wants the analysis understood, refreshed, or adapted.
The arc
- Resolve the URL.
get_from_urlreturns the entity type, IDs, and (for charts) the current definition. One call handles chart, dashboard, experiment, notebook, and cohort links — use it instead of asking the user for IDs. - Read the definition. For a chart:
get_amplitude_chartswithinclude: 'typed'— the typed params mirror the chart-builder UI and are the fastest way to see how the project spells events/properties. Iftypedfails to lower the chart ("advanced features are not modeled"), fall back toinclude: 'definition'for the raw form. For a dashboard:use_amp_dashboardsaction: 'get'(batch ≤3) to get its chart list, then read the charts that matter. - Pull the data.
get_amplitude_chartsinclude: 'data'with the chart IDs, ≤3 IDs per call. For a report refresh, request the granularity the report needs (daily for week-over-week, weekly for monthlies). - Adapt or fork. Edit the typed params, then call
query_amplitude_datawith the editedchartandchartIdset to the saved chart's id — the parent's params fill gaps the typed model omits, and the edit stays linked to its parent. Render the result withrender_amplitude_chart; the user saves it from the widget's Save chart button (there is no model-facing save tool). To replicate a whole dashboard in a new context: read the reference dashboard, then rebuild each chart — do not try to "copy" in one call.
Expectations to set
get_from_urldoes not run the chart — it returns metadata/definition. Data always comes fromget_amplitude_chartsinclude: 'data'(saved charts) orquery_amplitude_data(ad hoc).include: 'data'returns the same numbers the UI shows, including Amplitude's timezone bucketing — when comparing against external sources (e.g. BigQuery), call out timezone and partial-day differences explicitly.- Definition reads are cheap; data reads are the expensive calls. Read all definitions first, then decide which 1–3 charts actually need data.
- Just need the link for the user?
include: 'link'(the default) validates the ids and returns URLs without running anything.
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.
- 10d ago First seen · 48 lines · 65 tokens per session scan A 32bffa74932d
chart-link-analysis is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 661 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 2026-08-30.
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…
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…
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…