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/gc-pressure-auditornpx skills add StefanTheCode/dotnet-ai-toolkit --skill gc-pressure-auditorgit 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/gc-pressure-auditor)<a href="https://agentmods.dev/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor"><img src="https://agentmods.dev/badge/skills/stefanthecode/dotnet-ai-toolkit/gc-pressure-auditor.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.00662 |
| Opus 5 | $0.00053 | $0.00331 |
| Sonnet 5 | $0.00021 | $0.00132 |
| Haiku 4.5 | $0.00011 | $0.00066 |
Grade A, and why
gc-pressure-auditor 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 6d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GC Pressure Auditor
Diagnose why the garbage collector is working hard in a .NET service and recommend concrete fixes — config, allocation reduction, and pooling — based on the symptoms.
Input — point it at your project / paste the symptoms
Works on a target (a project or GitHub URL) and/or counters the user shares (Gen0/1/2 counts, % Time in GC, allocation rate, LOH size). Check config: grep -rn "ServerGarbageCollection\|ConcurrentGarbageCollection\|GCHeapHardLimit" <target> and the .csproj/runtimeconfig.
What to check
- Server vs Workstation GC — a throughput server should use Server GC (
<ServerGarbageCollection>true</ServerGarbageCollection>). Workstation GC on a busy server = avoidable pauses. - Concurrent GC — keep background GC on for latency-sensitive services.
- Allocation rate — high Gen0 churn means too many short-lived allocations. Trace the sources (
memory-allocation-analyzer). - Gen2 churn — objects surviving to Gen2 then dying = mid-lifetime objects; often caching done wrong or large graphs held too long.
- Large Object Heap (LOH) — arrays/strings ≥ 85 KB go to the LOH, which fragments and is collected with Gen2. Pool large buffers (
ArrayPool<T>), stream instead of buffering, chunk large payloads. - Pinning / fragmentation — long-lived pinned buffers fragment the heap.
- Hard limits in containers — set
GCHeapHardLimit/honor cgroup limits so the GC sizes correctly in k8s.
Common fixes
- Switch to Server GC + concurrent for throughput services.
- Pool large/short-lived buffers with
ArrayPool<T>.Shared/RecyclableMemoryStream. - Cut steady-state allocations on hot paths.
- Avoid LOH: stream large files, chunk, reuse buffers.
Principles
- GC pressure is an allocation problem first. Config tuning helps, but reducing what you allocate helps more.
- Diagnose with data (
dotnet-counters,dotnet-trace, GC stats) — don't tune blind. - LOH is the usual culprit for big, periodic pauses.
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.
- 6d ago First seen · 37 lines · 105 tokens per session scan A 8b7d0556290e
gc-pressure-auditor is a skill published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (19 stars, last pushed 27d ago), licensed MIT. It adds 105 tokens to every session and 662 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
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.
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.
hardwood-pr-git
Rebase, rewrite, squash, reword and push Hardwood PR history — including contributor PRs whose author and committer identity must survive the rewrite. Use whenever the user asks to "rebase", "rebase onto main", "fix the commit message", "prefix with the issue key", "squash the commits", "force push (with lease)"…