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.
git clone --depth 1 https://github.com/bvdr/claude-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/commands/bvdr/claude-plugins/umami-query)<a href="https://agentmods.dev/commands/bvdr/claude-plugins/umami-query"><img src="https://agentmods.dev/badge/commands/bvdr/claude-plugins/umami-query/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/commands/bvdr/claude-plugins/umami-query"><img src="https://agentmods.dev/badge/commands/bvdr/claude-plugins/umami-query.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 | $0.00030 | $0.02464 |
| Opus 5.5 | $0.00012 | $0.00986 |
| Sonnet 5.5 | $0.00006 | $0.00493 |
| Haiku 4.5 | $0.00003 | $0.00246 |
Grade A, and why
umami-query scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "{host}/api/websites/{websiteId}/stats?startAt={startMs}&endAt={endMs}" \ How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Umami Query
Query the Umami API for analytics data. All operations are read-only and execute directly.
Prerequisites
Read .umami.json from project root for host, websiteId, token. If missing, invoke bvdr:umami-setup.
Smart Defaults
- No date range specified → default to last 7 days
- User says "today" → calculate
startAt/endAtfor current day - User says "this month" → first day of current month to now
- All
startAt/endAtvalues are in milliseconds since epoch - Calculate with:
date +%s000(bash) orDate.now()(JS) - Format results as readable tables
- After showing results, suggest relevant follow-up queries
Endpoints
Website Stats
Overview metrics for a date range.
curl -s "{host}/api/websites/{websiteId}/stats?startAt={startMs}&endAt={endMs}" \
-H "Authorization: Bearer {token}"
Response: { "pageviews": N, "visitors": N, "visits": N, "bounces": N, "totaltime": N, "comparison": {...} }
Active Visitors
Unique visitors in last 5 minutes.
curl -s "{host}/api/websites/{websiteId}/active" \
-H "Authorization: Bearer {token}"
Response: { "visitors": N }
Pageviews Over Time
Time series of pageviews and sessions.
curl -s "{host}/api/websites/{websiteId}/pageviews?startAt={startMs}&endAt={endMs}&unit=day&timezone=Europe/Bucharest" \
-H "Authorization: Bearer {token}"
unit values and limits:
minute— max range: 60 minuteshour— max range: 30 daysday— max range: 6 monthsmonth,year— no limit
Add &compare=prev for previous period comparison or &compare=yoy for year-over-year.
Response: { "pageviews": [{"x": "2026-03-01", "y": 150}], "sessions": [{"x": "2026-03-01", "y": 80}] }
Metrics Breakdown
Break down data by any dimension.
curl -s "{host}/api/websites/{websiteId}/metrics?startAt={startMs}&endAt={endMs}&type=path&limit=20" \
-H "Authorization: Bearer {token}"
type values: path, entry, exit, title, query, referrer, channel, domain, country, region, city, browser, os, device, language, screen, event, hostname, tag, distinctId
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.
- 1mo ago First seen · 265 lines · 30 tokens per session scan A 69124a355d1c
umami-query is a command published in the GitHub repository bvdr/claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 2,464 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
dead-code-scan
Scan for dead code, unused imports, duplicates, and zombie code across the project.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.
dotnet-harden
Scan and harden .NET backend code against high-impact anti-patterns such as sync-over-async, lifetime bugs, fat endpoints, and fragile SignalR state.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.
rust-harden
Harden Rust code — replace unwrap with proper error handling, add safety comments to unsafe blocks, enable overflow checks, validate inputs at boundaries. The defensive hardening pass.