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 skills add orchestra-hq/orchestra-skills --skill databricks-cost-driversgit clone --depth 1 https://github.com/orchestra-hq/orchestra-skillsWrote 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/skills/orchestra-hq/orchestra-skills/databricks-cost-drivers)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/databricks-cost-drivers"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/databricks-cost-drivers/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/skills/orchestra-hq/orchestra-skills/databricks-cost-drivers"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/databricks-cost-drivers.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 | $0.00057 | $0.00617 |
| Opus 5.5 | $0.00023 | $0.00247 |
| Sonnet 5.5 | $0.00011 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
databricks-cost-drivers 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 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.
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.
What it actually says
Identify Databricks cost drivers
You help data platform teams understand where Databricks spend is going and whether it's trending up. Use the Orchestra MCP tools (or Orchestra API) to gather run data — never estimate or guess durations or costs.
Steps
- Scope the review. If the user doesn't specify a window, default to
the last 30 days. Use
list_pipeline_runsto get all runs for pipelines that contain Databricks tasks (integration = Databricks / Databricks Jobs / Databricks Workflows / Delta Live Tables). - Collect task-level data. For each run, use the task/operation list to pull every Databricks task: duration, cluster type (job cluster vs all-purpose), DBU-relevant metadata if present (node type, autoscaling min/max, photon on/off, serverless flag), and status.
- Compute a cost-proxy score per job. Where exact DBU $ cost isn't
available from Orchestra metadata alone, use duration × cluster size as
a proxy, and flag it clearly as a proxy rather than a billed dollar
figure. If the agent has a Databricks SQL/system-tables integration
available (
system.billing.usage,system.billing.list_prices), prefer querying that directly for true DBU/$ cost joined on job/run id — this gives exact figures instead of a proxy. - Rank and trend. Sort jobs by total cost/proxy over the window. For each of the top 10, compute the trend vs the prior window of the same length (up/down/flat, with %).
- Flag anomalies separately from drivers. A job can be a top spender without being anomalous (e.g. a large but expected daily job). Call out separately any job whose cost/duration jumped materially more than its own historical volatility would suggest — that's a candidate for the cluster-review or job-optimisation skills, not just a top-N listing.
Output
A ranked table — job/pipeline, avg cost or cost-proxy, % of total spend, trend vs prior period — for the top 10, followed by 2-3 sentences flagging anything trending up sharply. State clearly whether figures are exact (from billing system tables) or a duration-based proxy. Do not recommend fixes here — that's the cluster-review and job-optimisation skills; just point to which one applies to each flagged job.
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 · 49 lines · 57 tokens per session scan A 9de1152b4bba
databricks-cost-drivers is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 617 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-09.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…