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 Nevaberry/nevaberry-plugins --skill apache-spark-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWrote 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/nevaberry/nevaberry-plugins/apache-spark-knowledge-patch)<a href="https://agentmods.dev/skills/nevaberry/nevaberry-plugins/apache-spark-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/apache-spark-knowledge-patch/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/nevaberry/nevaberry-plugins/apache-spark-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/apache-spark-knowledge-patch.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 125 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 | $0.00010 | $0.02218 |
| Opus 5.5 | $0.00004 | $0.00887 |
| Sonnet 5.5 | $0.00002 | $0.00444 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
apache-spark-knowledge-patch 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apache Spark Knowledge Patch
Use this skill when upgrading, configuring, extending, or debugging modern Apache Spark applications. Check the application's Spark version before using version-specific advice, and prefer the application's manifests, code, and tests when they demonstrate different behavior.
Reference index
| Reference | Topics |
|---|---|
| references/migration-and-runtime.md | Core runtime defaults, compatibility switches, API corrections, and upgrade hazards |
| references/sql-and-dataframes.md | SQL semantics, parser and DDL changes, expressions, types, views, and DataFrame behavior |
| references/data-sources-and-formats.md | Data Source V2, JDBC, catalogs, file formats, schema evolution, and connector APIs |
| references/streaming-and-state.md | Structured Streaming triggers, checkpoints, state APIs, joins, and Python streaming sources |
| references/python-and-pandas.md | PySpark requirements, Arrow execution, pandas API on Spark, UDFs, exceptions, and inference |
| references/connect-ml-and-pipelines.md | Spark Connect, Spark ML, Declarative Pipelines, client modes, and remote lifecycle APIs |
| references/deployment-security-observability.md | Kubernetes, YARN, standalone deployment, security, metrics, logging, web UI, and History Server |
| references/dependencies-and-packaging.md | Bundled libraries, language runtimes, build flags, packaging, and dependency alignment |
Upgrade triage
Before changing code, identify whether the failure comes from a new default, a removed compatibility alias, a stricter correctness check, or a genuinely new API. Use the following order:
- Pin the exact Spark runtime used by driver and executors.
- Compare SQL, Python, streaming, storage, and deployment compatibility flags.
- Confirm bundled dependency overrides match Spark's own dependency line.
- Re-run query-result and checkpoint-restart tests, not only compilation.
- Use a legacy switch only as a temporary migration step and document it.
What ships with it
9 files 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.
- coverage.json 1.3 KB
- references/connect-ml-and-pipelines.md 3.4 KB
- references/data-sources-and-formats.md 8.4 KB
- references/dependencies-and-packaging.md 3.8 KB
- references/deployment-security-observability.md 5.7 KB
- references/migration-and-runtime.md 5.9 KB
- references/python-and-pandas.md 8.9 KB
- references/sql-and-dataframes.md 10 KB
- references/streaming-and-state.md 5.0 KB
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 · 194 lines · 10 tokens per session scan A a15e211c02b9
apache-spark-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (23 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 2,218 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor-sanitize-prompt
Google Model Armor: Sanitize a user prompt through a Model Armor template.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.