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 StefanTheCode/dotnet-ai-toolkit --skill stj-serialization-optimizergit clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkitWrote 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/stefanthecode/dotnet-ai-toolkit/stj-serialization-optimizer)<a href="https://agentmods.dev/skills/stefanthecode/dotnet-ai-toolkit/stj-serialization-optimizer"><img src="https://agentmods.dev/badge/skills/stefanthecode/dotnet-ai-toolkit/stj-serialization-optimizer/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/stefanthecode/dotnet-ai-toolkit/stj-serialization-optimizer"><img src="https://agentmods.dev/badge/skills/stefanthecode/dotnet-ai-toolkit/stj-serialization-optimizer.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 | $0.00095 | $0.00571 |
| Opus 5.5 | $0.00038 | $0.00228 |
| Sonnet 5.5 | $0.00019 | $0.00114 |
| Haiku 4.5 | $0.00010 | $0.00057 |
Grade A, and why
stj-serialization-optimizer 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 2mo 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.
What it actually says
System.Text.Json Optimizer
Make JSON serialization faster and leaner with System.Text.Json — source generation, reused options, streaming, and the small mistakes that cost a lot.
Input — point it at your code
Works on a target: a file, folder, project, or GitHub URL. Find usage: grep -rn "JsonSerializer\.\|JsonSerializerOptions\|System.Text.Json" --include=*.cs <target>.
Top fixes
- Reuse
JsonSerializerOptions— building a new options object per call is expensive (it caches metadata). Create one static instance and reuse it. This alone is a common big win. - Source generation — avoid reflection at runtime with a
JsonSerializerContext:
[JsonSerializable(typeof(Order))]
[JsonSerializable(typeof(List<Order>))]
public partial class AppJsonContext : JsonSerializerContext { }
var json = JsonSerializer.Serialize(order, AppJsonContext.Default.Order);
Faster startup, lower allocations, AOT-friendly.
3. Stream, don't buffer — JsonSerializer.SerializeAsync(stream, ...) / DeserializeAsync for large payloads and HTTP bodies instead of Serialize to a string then write.
4. Utf8JsonWriter/Utf8JsonReader for the hottest custom paths — work on byte/UTF-8 directly, skip the string.
5. Trim the payload — [JsonIgnore], DefaultIgnoreCondition = WhenWritingNull, shorter property names where appropriate.
6. Custom converters only when needed — and make them allocation-light.
Principles
- Options reuse + source generation are 80% of the wins — do those first.
- Stream large payloads; don't materialize giant strings.
- Measure with
[MemoryDiagnoser]— serialization is often an allocation story. - Don't hand-roll converters the built-in serializer already handles.
How to use it & best prompts
"Speed up my JSON serialization", "add System.Text.Json source generation", "why does serializing this allocate so much", "stream this large JSON response". Pairs with benchmarkdotnet-setup.
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.
- 2mo ago First seen · 39 lines · 95 tokens per session scan A 1f3b9fe179e2
stj-serialization-optimizer is a skill published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (26 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 571 once invoked, about $0.0004 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 2026-08-30.
stj-serialization-optimizer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stj-serialization-optimizerStefanTheCode/dotnet-ai-toolkit | Skill | 26 | 2mo ago | MIT | A | 95 | Claude Code |
| opentelemetry-net-instrumentationAaronontheweb/dotnet-skills | Skill | 1.3k | 9d ago | MIT | A | 56 | Claude Code |
| build-and-testmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 26 | Claude Code, Codex |
| agui-dotnet-streaming-chatag-ui-protocol/ag-ui | Skill | 17k | yesterday | MIT | A | 223 | Claude Code |
| azure-mgmt-apicenter-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 97 | Claude Code |
| migrate-xunit-to-xunit-v3dotnet/skills | Skill | 5.8k | yesterday | MIT | A | 149 | Claude Code |
| migrate-dotnet8-to-dotnet9dotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |