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-tmdl-apigit 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-tmdl-api)<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/fabric-tmdl-api"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-tmdl-api/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-tmdl-api"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-tmdl-api.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 | $0.00136 | $0.01056 |
| Opus 5 | $0.00068 | $0.00528 |
| Sonnet 5 | $0.00027 | $0.00211 |
| Haiku 4.5 | $0.00014 | $0.00106 |
Grade A, and why
fabric-tmdl-api 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Model Definition API rules
- Two audiences: Fabric API (
api.fabric.microsoft.com) for CRUD on definitions; Power BI API (analysis.windows.net/powerbi/api) for refresh, data sources, permissions updateDefinitionmust include ALL parts — modified AND unmodified. The API replaces the entire definition; omitting parts deletes them.- Never include
.platforminupdateDefinitionpayloads — it is Git integration metadata and causes errors - Base64-encode all TMDL content in definition payloads
getDefinitionis a POST (not GET) — requires--body '{}'- Poll LRO to completion —
createItemWithDefinition,getDefinition, andupdateDefinitionreturn 202
Required TMDL Parts
| Part Path | Content |
|---|---|
definition.pbism |
Semantic model connection settings (JSON) |
definition/database.tmdl |
database declaration + compatibilityLevel: 1702 |
definition/model.tmdl |
Model properties + ref declarations for tables/roles/etc. |
definition/tables/<TableName>.tmdl |
Per-table: measures, columns, partitions |
Critical: database.tmdl MUST start with database object declaration, not bare properties. Bare compatibilityLevel: causes InvalidLineType: Property! errors.
model.tmdl Required Properties
model Model
culture: en-US
defaultPowerBIDataSourceVersion: powerBI_V3
discourageImplicitMeasures
defaultPowerBIDataSourceVersion: powerBI_V3 is required for Import-mode models. Without it: Import from JSON supported for V3 models only.
Direct Lake Configuration
-
ALL partitions must use
EntityPartitionSource— no M/Power Query -
A named expression pointing to the Lakehouse/Warehouse must be defined before tables:
expression DL_Lakehouse = let Source = AzureStorage.DataLake("https://onelake.dfs.fabric.microsoft.com/<WorkspaceId>/<LakehouseId>", [HierarchicalNavigation=true]) in Source -
Each table partition references the expression:
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 4d5c85434e8e
- yesterday Changed e95b415969c0
- 6d ago Changed · +5 lines 28483f47d617
- 10d ago First seen · 77 lines · 136 tokens per session scan A b21f274b84c0
fabric-tmdl-api is a skill published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 1,056 once invoked, about $0.0007 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
gemini-api-agent-platform
Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.
sglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
mcp-server-dev
Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation involves stdio transport, server lifecycle…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…
ccc-saas
Skill "ccc-saas" from KevinZai/commander, covering $ccc-saas — saas domain hub, what's inside, routing matrix, campaign templates and greenfield saas (zero to mvp).