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/system-text-json-net11Wrote 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/system-text-json-net11)<a href="https://agentmods.dev/skills/managedcode/dotnet-skills/system-text-json-net11"><img src="https://agentmods.dev/badge/skills/managedcode/dotnet-skills/system-text-json-net11/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/system-text-json-net11"><img src="https://agentmods.dev/badge/skills/managedcode/dotnet-skills/system-text-json-net11.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 | $0.00180 | $0.03915 |
| Opus 5.5 | $0.00072 | $0.01566 |
| Sonnet 5.5 | $0.00036 | $0.00783 |
| Haiku 4.5 | $0.00018 | $0.00392 |
Grade A, and why
system-text-json-net11 scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://dot.net/v1/dotnet-install.sh -o "$install_script" How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System.Text.Json — .NET 11
Three APIs were added to System.Text.Json in .NET 11. This skill tells you exactly
when to reach for each one, what to write, what not to write, and how to prove the
result runs. Do not describe these APIs to the user — apply them, then run the code and
show the output.
| API | Replaces the pre-.NET-11 workaround of... |
|---|---|
JsonNamingPolicy.PascalCase (static property) |
writing a custom JsonNamingPolicy subclass or hand-annotating every member with [JsonPropertyName] |
JsonSerializerOptions.GetTypeInfo<T>() |
calling non-generic GetTypeInfo(typeof(T)) and casting to JsonTypeInfo<T> |
JsonSerializerOptions.TryGetTypeInfo<T>(out JsonTypeInfo<T>? info) |
wrapping GetTypeInfo in try/catch to probe availability |
Step 0 — Make the requested net11.0 validation possible
These APIs only exist in the .NET 11 base class library. Before writing code:
- Run
dotnet --list-sdksand confirm an SDK that can targetnet11.0is present — an11.xSDK, or a later SDK with thenet11.0targeting pack. - If the user explicitly asks you to run the sample and no suitable SDK is installed,
use the official
dotnet-installscript to install the current .NET 11 SDK into a temporary or project-local directory. Prefer the GA channel build. Use a preview only when GA is not yet available or the user explicitly requested a preview. Do not require administrator access, change the machine-widePATH, or replace an installed SDK. - Run the sample with that local
dotnetexecutable. If download or execution is blocked, still provide the completenet11.0program and report that it was not run. Never substitutenet10.0, a custom naming policy, or a different API and present that as validation of the .NET 11 feature.
Use the channel, not a guessed version. Try the GA channel first:
$installScript = Join-Path $env:TEMP "dotnet-install-$([guid]::NewGuid()).ps1"
try {
Invoke-WebRequest -Uri 'https://dot.net/v1/dotnet-install.ps1' -OutFile $installScript
& $installScript -Channel 11.0 -InstallDir .\.dotnet
& .\.dotnet\dotnet.exe run --project <PATH_TO_NET11_PROJECT>
}
finally {
Remove-Item -LiteralPath $installScript -Force -ErrorAction SilentlyContinue
}
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.
- 15d ago Changed · -1 lines · +2 tokens per session e067f1ad212f
- 1mo ago Changed · +55 lines · -24 tokens per session 12cb1cc7a44e
- 1mo ago First seen · 272 lines · 202 tokens per session scan A f0631fc89281
system-text-json-net11 is a skill published in the GitHub repository managedcode/dotnet-skills (490 stars, last pushed today), licensed MIT. It adds 180 tokens to every session and 3,915 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
a16z-crypto
Use when evaluating crypto networks and companies through an a16z crypto lens: web3 adoption, infrastructure vs apps, open networks, and long-duration crypto ecosystem investing.
finding-files
Use when searching for files by name, pattern, or type in large directories, or building file lists for pipelines with other tools.
querying-json
Use when querying JSON files, filtering or transforming JSON data, or extracting specific fields from large JSON files without loading entire file contents (saves 80-95% context).
expansion-retention
When the user wants to reduce churn, build expansion revenue, automate customer success, or optimize net revenue retention. Also use when the user mentions 'churn,' 'retention,' 'expansion revenue,' 'upsell,' 'NRR,' 'net revenue retention,' 'customer success,' 'land and expand,' 'closed-lost,' or 'renewal.' This skill…
nav-architecture-review
Generer Architecture Decision Records (ADR) med flerperspektiv-review tilpasset Nav.
positioning-icp
When the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit. Also use when the user mentions 'ICP,' 'ideal customer profile,' 'positioning,' 'PMF,' 'product-market fit,' 'messaging,' 'buyer persona,' 'enrichment signals,' 'market…