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/stefanthecode/dotnet-ai-toolkit/span-memory-refactornpx skills add StefanTheCode/dotnet-ai-toolkit --skill span-memory-refactorgit clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkitWhat 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 | $0.00109 | $0.00691 |
| Opus 5 | $0.00055 | $0.00345 |
| Sonnet 5 | $0.00022 | $0.00138 |
| Haiku 4.5 | $0.00011 | $0.00069 |
Grade A, and why
span-memory-refactor 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Span / Memory Refactor Advisor
Rewrite hot parsing/slicing/buffer code to use Span<T>/ReadOnlySpan<T> (and Memory<T> for async) so it stops allocating intermediate strings and arrays — safely, and only where it pays.
Input — point it at your code
Works on a target: a file, folder, project, or GitHub URL. Find candidates: grep -rn "Substring\|Split(\|ToCharArray\|new byte\[\|Buffer" --include=*.cs <target>.
Common refactors
Substring → slice (no allocation):
// allocates a new string per call
var year = date.Substring(0, 4);
// no allocation: a view over the original
ReadOnlySpan<char> year = date.AsSpan(0, 4);
int y = int.Parse(year);
Split in a hot loop → MemoryExtensions enumerator / manual slicing:
ReadOnlySpan<char> rest = line;
int comma;
while ((comma = rest.IndexOf(',')) >= 0)
{
ReadOnlySpan<char> field = rest[..comma];
// use field without allocating
rest = rest[(comma + 1)..];
}
Small temporary buffer → stackalloc (no heap):
Span<byte> buffer = stackalloc byte[32]; // keep small; this is stack memory
Async boundaries → Memory<T> (you can't store a Span<T> across await; use Memory<T>/ReadOnlyMemory<T>).
Guardrails the skill enforces
Span<T>is aref struct: can't be a field, captured in a lambda, used acrossawait, or boxed. UseMemory<T>there.- Keep
stackallocsmall and bounded (no user-controlled size) to avoid stack overflow. - Don't return a span over
stackalloc/local memory — it dangles.
Principles
- Only refactor hot paths. Spans add cognitive cost; cold code stays readable.
- The win is eliminating intermediate allocations (substrings, split arrays), not raw arithmetic.
- Measure with
[MemoryDiagnoser]— confirm allocations actually dropped.
How to use it & best prompts
"Make this parser allocation-free with Span", "replace these Substring calls with slices", "use stackalloc for this buffer", "why can't I use Span across await here". Pairs with memory-allocation-analyzer and 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.
- 2d ago First seen · 56 lines · 109 tokens per session scan A b3bf4c2ba705
span-memory-refactor is a skill published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (19 stars, last pushed 23d ago), licensed MIT. It adds 109 tokens to every session and 691 once invoked, about $0.0005 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
geo-technical
Technical SEO audit with GEO-specific checks — crawlability, indexability, security, performance, SSR, and AI crawler access.
evalscope
LLM evaluation & inference performance testing via the evalscope CLI. Translates natural language requests into evalscope commands for: (1) Model accuracy evaluation — runs 160+ benchmarks against local checkpoints or API endpoints (OpenAI-compatible, Anthropic, LiteLLM); (2) Performance stress testing — TTFT, TPOT…
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.
database-performance
Database access patterns for performance. Separate read/write models, avoid N+1 queries, use AsNoTracking, apply row limits, and never do application-side joins. Works with EF Core and Dapper.