Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/managedcode/dotnet-skillsnpx agentmods add skills/managedcode/dotnet-skills/template-instantiationWrote 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/managedcode/dotnet-skills/template-instantiation)<a href="https://agentmods.dev/skills/managedcode/dotnet-skills/template-instantiation"><img src="https://agentmods.dev/badge/skills/managedcode/dotnet-skills/template-instantiation/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/managedcode/dotnet-skills/template-instantiation"><img src="https://agentmods.dev/badge/skills/managedcode/dotnet-skills/template-instantiation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00168 | $0.02538 |
| Opus 5.5 | $0.00067 | $0.01015 |
| Sonnet 5.5 | $0.00034 | $0.00508 |
| Haiku 4.5 | $0.00017 | $0.00254 |
Grade A, and why
template-instantiation 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 1mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template Instantiation
This skill creates .NET projects from templates using dotnet new CLI commands, with guidance for parameter validation, Central Package Management adaptation, and multi-project composition.
Match the workspace, then stop. The highest-value move is aligning the new project with the repo it lands in: detect CPM (
Directory.Packages.props) and the target framework used by neighbouring.csprojfiles, and mirror both. Treat the discovered target framework as an explicit choice — pass it as--frameworksotemplate-smart-defaultswon't override it; deviate only when it's incompatible with a requested feature (then flag the conflict). Do this in as few steps as possible — a--dry-run, the create, and onedotnet buildto confirm is usually enough. Extra exploratory turns add cost without improving the result.
Perform the requested creation. Do not return only a plan or statement of intent. Run state-dependent commands sequentially: inspect, dry-run, create, then build. Never launch create and build in parallel; a build-before-create race produces a false failure.
| Situation | Required action |
|---|---|
| Simple standalone project | inspect only the requested template, create at the exact path, then build |
| Existing neighboring projects | read their TFMs first and pass the matching supported --framework explicitly |
Directory.Packages.props found |
create with --no-restore when supported, normalize generated package references, then restore/build once |
| Multi-project solution | create each project at its final path, add references, add all projects to the solution, then build the solution once |
User explicitly requests .sln |
inspect dotnet new sln --help; pass --format sln when supported, otherwise use the older SDK's default .sln output |
Do not predict the generated target framework. If the user and workspace do not supply one,
inspect dotnet new <template> --help, choose a supported value (normally its documented
default), pass it explicitly, then confirm the generated .csproj. Never announce an
intermediate framework guess that was not grounded in the template's current choices.
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.
- 1mo ago Changed · +29 lines 106718dba766
- 1mo ago First seen · 152 lines · 168 tokens per session scan A f1af5fc868ac
template-instantiation is a skill published in the GitHub repository managedcode/dotnet-skills (490 stars, last pushed today), licensed MIT. It adds 168 tokens to every session and 2,538 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
clean-architecture-dotnet
Use when domain logic leaks into API/Infrastructure, project references violate layer boundaries, or you need to decide between CQS (always), CQRS bus (complex domains), and DDD patterns (invariants and events).
creating-dotnet-mcp-servers
Use when building Model Context Protocol (MCP) servers in .NET, configuring tools, transports (SSE/stdio), JSON serialization for AOT, or testing MCP endpoints.
opengis-skills
Use when AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise. Index of 96 skills across 8 categories: gis (32), cad (21), csharp (9), ai (14), iot (2), 3d (6), demos (4), others (8). Tag-based search and on-demand loading for GDAL, GeoServer, MapServer, Leaflet, PROJ, PostGIS, JTS, CesiumJS, FreeCAD…
dotnet-inspect
Query .NET APIs across NuGet packages, platform libraries, and local files. Search for types, list API surfaces, compare and diff versions, find extension methods and implementors. Use whenever you need to answer questions about .NET library contents. Commands pin v0.9.1; pair with cs0618-hunter (compiler-based) for…
maf-migration-retrospective
Post-migration learning skill. After a migration completes, reads the migration plan notes, build history, and surprises to improve the registry, guide, and constraint rules. Invoked as the final step of any migration. This is how the toolkit gets smarter with each use.
maf-migration-plan-creator
Generates a complete, ready-to-execute MAF migration plan (migration-plan.md) for any .NET codebase. Used by @maf-auditor (which calls this skill after scanning to produce the plan). Use this skill directly when no migration plan exists yet, or when the existing plan needs to be regenerated after a codebase audit.…