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 wardawgmalvicious/agent-config --skill fabric-mlvgit clone --depth 1 https://github.com/wardawgmalvicious/agent-configWrote 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/wardawgmalvicious/agent-config/fabric-mlv)<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/fabric-mlv"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-mlv/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/wardawgmalvicious/agent-config/fabric-mlv"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-mlv.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 | $0.00245 | $0.04620 |
| Opus 5 | $0.00122 | $0.02310 |
| Sonnet 5 | $0.00049 | $0.00924 |
| Haiku 4.5 | $0.00024 | $0.00462 |
Grade A, and why
fabric-mlv 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 today.
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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabric Materialized Lake Views (MLV)
Declarative SQL/PySpark transformations that persist as Delta tables in a schema-enabled lakehouse. Fabric handles refresh strategy, dependency order, and data quality enforcement so you don't write notebook orchestration.
When to use vs not
Use MLVs for medallion bronze→silver→gold pipelines, frequently-queried aggregates, declarative data quality, and reporting datasets that need automatic refresh. Skip them for one-off queries, sub-second streaming (use Real-Time Intelligence), or transformations that need ML inference / external API calls / non-SQL Python (use a regular Spark notebook).
Prerequisites
- Schema-enabled lakehouse — required.
enableSchemasis immutable per lakehouse; you can't retrofit it. - Fabric Runtime 1.3 — earlier runtimes can't author MLVs. Upstream still names 1.3 exactly (checked 2026-08-29), and has not extended the prerequisite to Runtime 2.0 (GA Aug 2026 — Spark 4.1, Delta Lake 4.2, Python 3.13), so treat 2.0 as unverified for MLV authoring rather than assumed. This has a deadline: 2.0 is planned to become the default for new workspaces and environment items in late September 2026, at which point a new workspace stops defaulting to a runtime MLVs are documented against. Re-check the prerequisite then.
- Region — not available in South Central US (as of 2026-04).
- CDF on source tables — required for incremental refresh:
ALTER TABLE bronze.x SET TBLPROPERTIES (delta.enableChangeDataFeed = true). Without it, optimal refresh degrades to skip-or-full only.
Spark SQL — CREATE
CREATE [OR REPLACE] MATERIALIZED LAKE VIEW [IF NOT EXISTS]
[workspace.lakehouse.schema].MLV_Identifier
[(
CONSTRAINT name1 CHECK (expr1) [ON MISMATCH DROP | FAIL],
CONSTRAINT name2 CHECK (expr2) [ON MISMATCH DROP | FAIL]
)]
[PARTITIONED BY (col1, col2, ...)]
[COMMENT "..."]
[TBLPROPERTIES ("k1"="v1", ...)]
AS select_statement
| Clause | Notes |
|---|---|
OR REPLACE |
Mutually exclusive with IF NOT EXISTS |
CONSTRAINT ... CHECK |
Multiple allowed. Only deterministic built-ins permitted |
ON MISMATCH DROP |
Silently drops violating rows. Each row dropped at most once even if it violates multiple constraints |
ON MISMATCH FAIL |
Default. Stops the refresh with an error |
PARTITIONED BY |
Improves filtered-read performance |
TBLPROPERTIES |
Set delta.enableChangeDataFeed=true here to enable CDF on the MLV itself for downstream MLVs |
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.
- today Changed ece577042946
- 6d ago Changed · +3 lines 9af0f9632e62
- 10d ago First seen · 265 lines · 245 tokens per session scan A e68b47f44d9c
fabric-mlv is a skill published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed today), licensed MIT. It adds 245 tokens to every session and 4,620 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and…
speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…