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 skills/rilldata/agent-skills/rill-explorenpx skills add rilldata/agent-skills --skill rill-exploregit clone --depth 1 https://github.com/rilldata/agent-skillsWhat 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 | $0.00017 | $0.02101 |
| Opus 5 | $0.00009 | $0.01051 |
| Sonnet 5 | $0.00003 | $0.00420 |
| Haiku 4.5 | $0.00002 | $0.00210 |
Grade A, and why
rill-explore 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 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.
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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for developing an explore dashboard in Rill
Introduction
Explore dashboards are resources that configure an interactive, drill-down dashboard for a metrics view. They are Rill's default dashboard type, designed for explorative slice-and-dice analysis of a single metrics view.
Explore dashboards are lightweight resources that sit downstream of a metrics view in the project DAG. Their reconcile logic is fast (validation only), so they can be created and modified freely without performance concerns.
When to use explores vs canvases
- Explore dashboards: Best for explorative analysis, drill-down investigations, and letting users freely slice data by any dimension.
- Canvas dashboards: Best for fixed reports, executive summaries, or combining multiple metrics views into a single view.
Development approach
Explore dashboards require minimal configuration. In most cases, you only need to:
- Reference the metrics view
- Select which dimensions and measures to expose (usually all, indicated by
'*') - Optionally configure defaults and time ranges
Best practice: Keep explore configurations simple. Only add advanced features (security policies, custom themes, restricted dimensions) when there is a clear requirement. The metrics view already defines the business logic; the explore just controls presentation and access.
Inline explores in metrics views
The preferred way to create an explore is inline in the metrics view file: set version: 1 and add an explore: block, which emits an explore resource with the same name as the metrics view (or name: if set):
# metrics/sales.yaml
version: 1
type: metrics_view
display_name: Sales Analytics
model: sales_model
timeseries: order_date
dimensions:
- column: region
- column: product_category
measures:
- name: total_revenue
expression: SUM(revenue)
# Inline explore configuration
explore:
display_name: Sales Dashboard
dimensions: '*' # Optional: dimensions to expose ('*', a list, or {exclude: [...]}); defaults to all
measures: '*' # Optional: measures to expose ('*', a list, or {exclude: [...]}); defaults to all
time_ranges:
- P7D
- P30D
- P90D
defaults:
time_range: P30D
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 · 270 lines · 17 tokens per session scan A 2826fc3f6d36
rill-explore is a skill published in the GitHub repository rilldata/agent-skills (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,101 once invoked, about $0.0001 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.