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/umami-reportsgit 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 | $0.00031 | $0.02203 |
| Opus 5 | $0.00015 | $0.01102 |
| Sonnet 5 | $0.00006 | $0.00441 |
| Haiku 4.5 | $0.00003 | $0.00220 |
Grade A, and why
umami-reports 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 "{host}/api/reports?websiteId={websiteId}" \ How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Umami Reports
Create and run all 8 Umami report types via the API. Read operations execute directly. Write operations (create, update, delete) ask for confirmation first.
Prerequisites
Read .umami.json from project root for host, websiteId, token. If missing, invoke bvdr:umami-setup.
Report CRUD
List reports
curl -s "{host}/api/reports?websiteId={websiteId}" \
-H "Authorization: Bearer {token}"
Create report (confirm first)
curl -s -X POST "{host}/api/reports" \
-H "Authorization: Bearer {token}" \
-H "Content-Type: application/json" \
-d '{
"websiteId": "{websiteId}",
"type": "{reportType}",
"name": "{reportName}",
"description": "{description}",
"parameters": { ... }
}'
Get report
curl -s "{host}/api/reports/{reportId}" \
-H "Authorization: Bearer {token}"
Update report (confirm first)
Note: Umami uses POST for updates (not PUT). Verify against your instance version at implementation time.
curl -s -X POST "{host}/api/reports/{reportId}" \
-H "Authorization: Bearer {token}" \
-H "Content-Type: application/json" \
-d '{ "name": "...", "parameters": { ... } }'
Delete report (confirm first)
curl -s -X DELETE "{host}/api/reports/{reportId}" \
-H "Authorization: Bearer {token}"
Report Types
Funnel
Track sequential step completion with drop-off rates.
curl -s -X POST "{host}/api/reports/funnel" \
-H "Authorization: Bearer {token}" \
-H "Content-Type: application/json" \
-d '{
"websiteId": "{websiteId}",
"startDate": "2026-01-01T00:00:00Z",
"endDate": "2026-03-12T23:59:59Z",
"timezone": "Europe/Bucharest",
"window": 60,
"steps": [
{ "type": "path", "value": "/pricing" },
{ "type": "path", "value": "/signup" },
{ "type": "event", "value": "purchase-complete" }
]
}'
steps— minimum 2. Each step hastype(pathorevent) andvaluewindow— time window in minutes a user has between funnel steps to count as a conversion- Steps must be completed in order (other pages can be visited between steps)
- Output: step completion counts and drop-off rates
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 · 252 lines · 31 tokens per session scan A af8999f282ff
umami-reports is a command published in the GitHub repository bvdr/claude-plugins (3 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 2,203 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-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.
dead-code-clean
Actively find and remove dead code, unused imports, duplicates, and zombie code.
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.