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 scheduled-report-refreshgit 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/scheduled-report-refresh)<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/scheduled-report-refresh"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/scheduled-report-refresh/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/scheduled-report-refresh"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/scheduled-report-refresh.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 | $0.00071 | $0.00503 |
| Opus 5 | $0.00036 | $0.00251 |
| Sonnet 5 | $0.00014 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
scheduled-report-refresh 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 12d 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.
What it actually says
Scheduled Report Refresh
The dominant automated job on this MCP server: custom agents and scheduled runs re-pulling a known set of charts and summarizing changes.
The arc
- Anchor on saved content.
use_amp_dashboardsaction: 'get'(batch ≤3) for the report's chart list, orget_from_urlif the run input is a link. Saved charts are the contract — do not rebuild definitions from scratch. - Re-pull data.
get_amplitude_chartsinclude: 'data', ≤3 chart IDs per call, at the report's granularity (daily for daily/weekly briefs). For each chart compare the current period against the trailing baseline the report uses. - Fill gaps ad hoc.
query_amplitude_data(typedchart) only for numbers no saved chart covers (a new funnel step, a one-off slice). - Context for movement.
use_amp_flagsaction: 'list_deployments'once — recent deploys are the first hypothesis for any metric movement. - Report. Delta table first (metric, current, baseline, % change), then notable movers with hypotheses. State explicitly when the current period is partial ("today is tracking at X vs Y full-day yesterday").
Expectations to set
get_amplitude_chartsinclude: 'data'on a saved chart returns exactly what the UI shows — trust it; don't re-validate every number withquery_amplitude_data.- Keep definition reads (
include: 'definition'/'typed') minimal on refresh runs — the dashboard chart list plus data is enough unless a chart looks misconfigured. - If a chart errors or returns empty, report it as a broken report item rather than silently dropping it — a missing tile in a recurring report is itself a finding.
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.
- 12d ago First seen · 40 lines · 71 tokens per session scan A 207d02e551d3
scheduled-report-refresh is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed 4d ago), licensed MIT. It adds 71 tokens to every session and 503 once invoked, about $0.0004 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…