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 agentmods add commands/bvdr/claude-plugins/using-umamigit clone --depth 1 https://github.com/bvdr/claude-pluginsWhat 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 | $0.00035 | $0.00796 |
| Opus 5 | $0.00017 | $0.00398 |
| Sonnet 5 | $0.00007 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
using-umami 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 2d 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 -X POST "{host}/api/auth/verify" \ How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Umami Analytics Hub
Entry point for all Umami Analytics operations. Routes to the right sub-skill based on what the user needs.
Routing Flow
digraph umami_routing {
"User request" [shape=doublecircle];
".umami.json exists?" [shape=diamond];
"Invoke umami-setup" [shape=box];
"Validate token" [shape=box];
"Token valid?" [shape=diamond];
"Detect intent" [shape=box];
"Route to skill" [shape=doublecircle];
"User request" -> ".umami.json exists?";
".umami.json exists?" -> "Invoke umami-setup" [label="no"];
".umami.json exists?" -> "Validate token" [label="yes"];
"Validate token" -> "Token valid?";
"Token valid?" -> "Invoke umami-setup" [label="no (401)"];
"Token valid?" -> "Detect intent" [label="yes"];
"Detect intent" -> "Route to skill";
}
Step 1: Check Config
Read .umami.json from the project root. It must contain:
host— Umami instance URLwebsiteId— target website UUIDtoken— JWT auth token
If missing or malformed → invoke bvdr:umami-setup.
Step 2: Validate Token
Quick health check — verify the token is still valid:
curl -s -X POST "{host}/api/auth/verify" \
-H "Authorization: Bearer {token}"
- Success → proceed to routing
- 401 → token expired, invoke
bvdr:umami-setupwith "Refresh token" option - Connection error → warn user, suggest checking if instance is running
Step 3: Route by Intent
| User says something like... | Invoke skill |
|---|---|
| "set up umami", "connect", "install tracker", "configure" | bvdr:umami-setup |
| "track", "add event", "identify users", "implement tracking", "data attributes", "revenue tracking", "server-side event", "what should I track" | bvdr:umami-track |
| "funnel", "journey", "retention", "goal", "UTM", "attribution", "breakdown", "revenue report", "create report" | bvdr:umami-reports |
| "stats", "metrics", "how many visitors", "show pageviews", "sessions", "realtime", "query", "event data", "active users" | bvdr:umami-query |
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.
- 2d ago First seen · 82 lines · 35 tokens per session scan A 1ee131d9e0a5
using-umami is a command published in the GitHub repository bvdr/claude-plugins (3 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 796 once invoked, about $0.0002 per session on Opus 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-clean
Actively find and remove dead code, unused imports, duplicates, and zombie code.
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.
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.