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 EmbrasureAI/spark-observability-skills --skill optimize-spark-sql-plangit clone --depth 1 https://github.com/EmbrasureAI/spark-observability-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/embrasureai/spark-observability-skills/optimize-spark-sql-plan)<a href="https://agentmods.dev/skills/embrasureai/spark-observability-skills/optimize-spark-sql-plan"><img src="https://agentmods.dev/badge/skills/embrasureai/spark-observability-skills/optimize-spark-sql-plan/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/embrasureai/spark-observability-skills/optimize-spark-sql-plan"><img src="https://agentmods.dev/badge/skills/embrasureai/spark-observability-skills/optimize-spark-sql-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 92 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00066 | $0.01627 |
| Opus 5 | $0.00033 | $0.00813 |
| Sonnet 5 | $0.00013 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
optimize-spark-sql-plan 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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize a Spark SQL plan
Find the highest-impact improvement supported by the executed plan and its runtime metrics. Work from the final adaptive plan (isFinalPlan=true), not source code or the initial plan: AQE may already have broadcast, coalesced, or split what you were about to recommend.
Get the evidence
export SPARK_HISTORY_URL="https://history.example.com"
python3 scripts/spark_history_api.py sql-list --app-id <application-id>
python3 scripts/spark_history_api.py sql --app-id <application-id> --execution-id <execution-id> > /tmp/spark-sql.json
Run from this skill directory. If SPARK_HISTORY_URL is unset, find the server before asking the user: try http://localhost:18080, a running application's UI on http://localhost:4040, and the history-server or eventLog settings in the local Spark config; ask only when nothing responds. Authentication comes from SPARK_HISTORY_AUTHORIZATION, SPARK_HISTORY_COOKIE, or SPARK_HISTORY_HEADERS_JSON; never ask for credentials in chat and never disable TLS verification (--ca-file for a private CA).
The snapshot's layout: sqlExecution.planDescription is the executed plan text, sqlExecution.nodes[].metrics carry per-operator counters with edges giving parent-child links, jobs[].stageIds tie the execution to stages, longestStages[] holds each stage with its taskSummary quantiles (arrays align with quantiles; middle is median, last is max), and environment.sparkProperties is the effective configuration. For data beyond the profile, other subcommands (slow, failure, applications) and the raw $SPARK_HISTORY_URL/api/v1 endpoints (/stages/{stage}/{attempt}/taskSummary, /allexecutors, /environment) are available with the same auth. If the API omits the plan, recover it from the driver log or generate explain(mode="formatted") from the deployed code yourself. Get the deployed query code too: the plan tells you what ran, the code tells you what was intended.
Highest-impact opportunities, in order, and how to check each
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 93 lines · 66 tokens per session scan A 56677d8abf31
optimize-spark-sql-plan is a skill published in the GitHub repository EmbrasureAI/spark-observability-skills (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,627 once invoked, about $0.0003 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
setup
Configure MLflow tracing for Claude Code.
monte-carlo-instrument-agent
Instrument a new AI agent in a Python codebase for Monte Carlo Agent Observability. Detects AI libraries, installs the Monte Carlo OpenTelemetry SDK, and proposes tracing setup and decorator placements as diffs. Asks before editing any file.
safe-backfill-and-replay-orchestration
Forces replay-safe rollout plans, reconciliation gates, and rollback paths before executing any data backfill or historical reprocessing. Use when running /backfill, rerunning pipelines, repairing publish windows, or any work that risks double-counting or downstream corruption.
lakefs-and-data-versioning
Guides agents through data versioning workflows using lakeFS or similar systems. Use when branching data, validating changes before publish, or controlling risky lakehouse operations with versioned data states.
openmetadata-datahub-and-openlineage
Guides agents through metadata platform and lineage workflows using OpenMetadata, DataHub, or OpenLineage-compatible systems. Use when improving discovery, lineage quality, metadata governance, or producer-to-catalog integration.
apache-beam-unified-batch-and-stream
Guides agents through Apache Beam pipelines that unify batch and streaming logic. Use when designing Beam transforms, windowing, runners, replay behavior, or portability across execution backends.