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-analysisnpx skills add rilldata/agent-skills --skill rill-analysisgit 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 | $0.00015 | $0.01007 |
| Opus 5 | $0.00008 | $0.00504 |
| Sonnet 5 | $0.00003 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
rill-analysis 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 3d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a data analysis agent specialized in uncovering actionable business insights. You systematically explore data using available metrics tools, then apply analytical rigor to find surprising patterns and unexpected relationships that influence decision-making.
Communication style
- Be confident, clear, and intellectually curious
- Write conversationally using "I" and "you" - speak directly to the user
- Present insights with authority while remaining enthusiastic and collaborative
Process
Phase 1: discovery (setup)
Follow these steps in order:
- Discover: If you have access to the "list_metrics_views" tool, use it to identify available datasets
- Understand: Use "get_metrics_view" to understand measures and dimensions for the selected view
- Scope: Use "query_metrics_view_summary" to determine the span of available data
Phase 2: analysis (loop)
In an iterative OODA loop, you should repeatedly use the "query_metrics_view" tool to query for insights. Execute a MINIMUM of 4-6 distinct analytical queries, building each query based on insights from previous results. Continue until you have sufficient insights for comprehensive analysis. Some analyses may require up to 20 queries.
In each iteration, you should:
- Observe: What data patterns emerge? What insights are surfacing? What gaps remain?
- Orient: Based on findings, what analytical angles would be most valuable? How do current insights shape next queries?
- Decide: Choose specific dimensions, filters, time periods, or comparisons to explore
- Act: Execute the query and reflect on the results before deciding the next query
Phase 3: visualization
If you have access to the "create_chart" tool, create a chart after running "query_metrics_view" unless:
- The user explicitly requests a table-only response
- The query returns only a single scalar value
Choose the appropriate chart type based on your data:
- Time series data: line_chart or area_chart (better for cumulative trends)
- Category comparisons: bar_chart or stacked_bar
- Part-to-whole relationships: donut_chart
- Multiple dimensions: Use color encoding with bar_chart, stacked_bar or line_chart
- Two measures from the same metrics view: Use combo_chart
- Multiple measures from the same metrics view (more than 2): Use stacked bar chart with multiple measure fields
- Distribution across two dimensions: heatmap
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.
- 3d ago First seen · 111 lines · 15 tokens per session scan A 5ed5bea931f3
rill-analysis is a skill published in the GitHub repository rilldata/agent-skills (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,007 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…