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-graphgit 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-graph)<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/fabric-graph"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-graph/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-graph"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-graph.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 | $0.00257 | $0.02753 |
| Opus 5 | $0.00129 | $0.01376 |
| Sonnet 5 | $0.00051 | $0.00551 |
| Haiku 4.5 | $0.00026 | $0.00275 |
Grade A, and why
fabric-graph 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 5d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Fabric Graph (GraphModel item)
Graph in Fabric models a labeled property graph directly over OneLake Delta tables — no ETL, no data duplication. You define node/edge types and map them to columns; on save, Fabric ingests the tables and builds a read-optimized queryable graph. Query it with GQL (the ISO/IEC 39075 standard) via UI, REST, or NL2GQL.
Item type name: GraphModel — the metadata.type a Git-synced export writes into .platform, so the folder serializes as <name>.GraphModel; also the REST collection /GraphModels and the Catalog Search filter Type eq 'GraphModel'. fabric-cli knows the name only for fab find: its ItemType enum has no GraphModel entry, so fab cannot create or address one. New item → Analyze and train data → Graph model.
Three things that catch people out
- It is NOT the KQL graph operators. Fabric Graph (GraphModel) is a separate workload from the
make-graph/graph-match/#crp query_language=gqlstory in Eventhouse/KQL (see fabric-eventhouse). Same word "graph", different engine, different API, different syntax surface. Don't cross-apply. - GQL is read-only here. You cannot
INSERT/SET/DELETEgraph data through GQL. Data is loaded and refreshed via data management (save the model = reingest from OneLake).CREATE GRAPHis only partially supported andDROP GRAPHis not in GQL — drop via the Fabric UI or REST API instead. - No schema evolution. Once nodes/edges/properties are modeled and data is ingested, the structure is fixed. Adding a property, changing a label, or changing a relationship type means reingesting source data into a new model. Plan the schema up front.
GQL query language (ISO/IEC 39075)
GQL expresses relationships as visual patterns instead of joins. Roots are SQL + openCypher, but it is its own dialect — do not assume Cypher syntax (e.g. no CREATE (n:Label) data writes here).
MATCH (c:Customer)-[:purchases]->(o:`Order`)
RETURN c.fullName AS customer_name, count(o) AS num_orders
GROUP BY customer_name
ORDER BY num_orders DESC
LIMIT 5
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.
- 5d ago Changed · +3 lines 2202b9e45ad7
- 9d ago First seen · 129 lines · 257 tokens per session scan A 216cefd43dc1
fabric-graph is a skill published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed yesterday), licensed MIT. It adds 257 tokens to every session and 2,753 once invoked, about $0.0013 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
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
dbt-expert
Expert-level dbt (data build tool), models, tests, documentation, incremental models, macros, and Jinja templating. Use when the user mentions analytics engineering, SQL, data transformation, Jinja, or testing, or when the task involves Project Structure and Configuration, Sources and Staging Models, Intermediate and…
ccc-pro-migration
Zero-downtime schema versioning, backfills, and safe deploy patterns · Pro tier only.