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 agentmods add skills/microsoft/datafactory.mcp/coder.datafactory-stylenpx skills add microsoft/DataFactory.MCP --skill coder.datafactory-stylegit clone --depth 1 https://github.com/microsoft/DataFactory.MCPWhat 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 | $0.00026 | $0.00524 |
| Opus 5 | $0.00013 | $0.00262 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
coder.datafactory-style 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Style — DataFactory.MCP
Project Settings
- Target: net10.0
- Nullable: enabled (project-wide)
- Implicit usings: enabled
- License: MIT
Conventions
Naming
| Element | Style | Example |
|---|---|---|
| Classes | PascalCase | FabricGatewayService |
| Interfaces | I prefix |
IFabricGatewayService |
| Methods | PascalCase | ListGatewaysAsync |
| Parameters | camelCase | gatewayClusterId |
| Private fields | _ prefix |
_httpClient |
| Constants | PascalCase | MaxRetryCount |
| Async methods | Async suffix |
GetGatewayAsync |
File Organization
- One primary class per file
- File name matches class name
- Tools in
Tools/, Services inServices/, Models inModels/ - Interfaces in
Abstractions/
Null Safety
- Nullable is ON — respect nullable annotations
- Use
?for nullable types,!only when provably non-null - Prefer pattern matching:
if (value is not null) - Never suppress
#pragma warning disablefor nullable without justification
Error Handling
- Catch specific exceptions, not
Exceptionbroadly - Translate API errors to meaningful MCP error responses
- Always check auth state before API calls
- Log errors with context (operation name, resource ID)
Async/Await
- All I/O operations must be async
- Use
ConfigureAwait(false)in library code (Core project) - Never use
.Resultor.Wait()— always await
Dependency Injection
- All services registered in DI container via extension methods in
Extensions/ - Constructor injection only
- Depend on interfaces (
Abstractions/), not concrete types
Key Patterns
Tool → Service → Model
Tool (MCP schema + validation) → Service (API call) → Model (data)
- Tools handle: parameter parsing, validation, MCP response formatting
- Services handle: HTTP calls, auth tokens, error translation
- Models handle: data shape (DTOs, no logic)
Configuration
- Feature flags control tool availability
- API versions managed in
Configuration/classes - Environment variables for auth settings
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.
- 2d ago First seen · 79 lines · 26 tokens per session scan A 797621498bee
coder.datafactory-style is a skill published in the GitHub repository microsoft/DataFactory.MCP (42 stars, last pushed 20d ago), licensed MIT. It adds 26 tokens to every session and 524 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…