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 Galius5136/databricks-spark-3.5-cert-prep --skill spark-cert-3.5git clone --depth 1 https://github.com/Galius5136/databricks-spark-3.5-cert-prepWrote 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/galius5136/databricks-spark-3.5-cert-prep/spark-cert-3.5)<a href="https://agentmods.dev/skills/galius5136/databricks-spark-3.5-cert-prep/spark-cert-3.5"><img src="https://agentmods.dev/badge/skills/galius5136/databricks-spark-3.5-cert-prep/spark-cert-3.5/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/galius5136/databricks-spark-3.5-cert-prep/spark-cert-3.5"><img src="https://agentmods.dev/badge/skills/galius5136/databricks-spark-3.5-cert-prep/spark-cert-3.5.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 | $0.00101 | $0.01129 |
| Opus 5 | $0.00051 | $0.00564 |
| Sonnet 5 | $0.00020 | $0.00226 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
spark-cert-3.5 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 11d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spark-cert-3.5 — Study Orchestrator
Purpose
Coordinate the underlying Spark sub-skills for effective, exam-targeted study of the Databricks Certified Associate Developer for Apache Spark 3.5. Track study progress. Generate practice material.
Sub-skills consulted
apache-spark: Damji book "Learning Spark, 2nd Edition" (Spark 3.0 baseline) → ch01–ch12spark-connect: exam Section 6pandas-on-spark: exam Section 7 (Pandas API on Spark)spark-3.5-updates: built-ins added in 3.1–3.5, AQE evolution post-3.0, Pandas UDF / Arrow APIs
Exam topic map
| Sec | Topic | Primary source | Secondary |
|---|---|---|---|
| 1 | Architecture & Components | apache-spark/ch01, ch02 | — |
| 2 | DataFrame API basics | apache-spark/ch03, ch04 | — |
| 3 | DataFrame transformations + built-ins | apache-spark/ch05 | spark-3.5-updates (new built-ins) |
| 4 | Performance & tuning | apache-spark/ch07, ch12 | spark-3.5-updates (AQE post-3.0) |
| 5 | Structured Streaming | apache-spark/ch08 | — |
| 6 | Spark Connect | spark-connect (only) | — |
| 7 | Pandas API on Spark + Pandas UDF | pandas-on-spark + spark-3.5-updates | apache-spark/ch05 (baseline) |
State file
Persistent state in ~/spark-cert/progress.md. Update at every session.
Workflows
study
- Identify section/topic from the exam topic map.
- Consult the primary source plus any secondary source.
- Produce output:
- Concept (concise)
- Code example (runnable)
- 2 exam-style multiple-choice questions (4 options each)
- 1 trap question (tests a common misconception)
- Wait for the user's answers.
- Explain mistakes, update
progress.md(coverage % and weak spots when answers are wrong).
quiz | quiz random
- 5–10 exam-style questions on the given topic, or random from the full syllabus.
- Format: stem + 4 options + correct answer + explanation.
- Track score in
progress.mdsession log.
mock-exam
- 45 questions distributed by syllabus weight.
- Indicative time limit: 90 minutes.
- Explicit caveat: this does NOT replace external mocks (Udemy / ExamTopics).
- Score + per-section breakdown.
- Identify weak sections and suggest follow-up study sessions.
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.
- 11d ago First seen · 94 lines · 101 tokens per session scan A 6cc6c00066d2
spark-cert-3.5 is a skill published in the GitHub repository Galius5136/databricks-spark-3.5-cert-prep (12 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 1,129 once invoked, about $0.0005 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
alt-import
Parse an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam-probability signal into the PAIDEIA course index — write course-index/radar.md, annotate course-index/coverage.md with a lecture-emphasis column and divergence flags, and seed a gold-zone weakmap. Invoked by /paideia:alt. The export…
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
setup
Configure MLflow tracing for Claude Code.
learning-notes-automation
A workflow for turning videos, podcasts, and articles into structured learning notes. It extracts key ideas and creates flashcards that can be imported into Anki, a spaced-repetition study app.
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.