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 instructions/rjmurillo/ai-agents/csharpgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/instructions/rjmurillo/ai-agents/csharp)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/csharp"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/csharp.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 | $0.01177 | $0.01177 |
| Opus 5 | $0.00589 | $0.00589 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
ai-agents csharp.instructions.md 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 yesterday.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C# and .NET Rules
These rules apply when you write or review C#. Baseline is C# 13 on .NET 9 (the
target for new work). Where a newer feature helps, name the version so the
reader can check their SDK. Defer to the repo's .editorconfig, Directory.Build.*,
and any analyzer config over personal preference.
Language Level
- Prefer modern syntax that reduces noise: collection expressions (
[1, 2, 3]), primary constructors,requiredmembers, target-typednew, pattern matching, andswitchexpressions. They state intent with less ceremony. - Use
recordfor immutable value-like data;record structwhen the value is small and copied often. Useclasswhen identity or mutability is the point. - Make reference types non-nullable by default. Keep
<Nullable>enable</Nullable>on and treat nullable warnings as errors. A?is a contract, not decoration. - Use
file-scoped namespaces andglobal usingfor the handful of namespaces every file needs. Do not hide domain types behind global usings.
Allocation and Performance
- Operate on
Span<T>/ReadOnlySpan<T>andMemory<T>for slicing without copying. Rent large transient buffers fromArrayPool<T>.Sharedand return them in afinally. - Avoid allocations on hot paths: no LINQ in tight loops, no
paramsarrays per call, no closures captured in inner loops. Measure with BenchmarkDotNet before and after; do not optimize on a hunch. - Prefer
structfor small, short-lived values to keep them off the heap, but pass large structs byinto avoid defensive copies. A struct over ~16 bytes passed by value is usually a mistake. - Use
StringBuilderorstring.Createfor multi-step string building; interpolation is fine for one-shot formatting.
Async
- Every awaitable that crosses an I/O or process boundary takes a
CancellationTokenand honors it. A method that ignores its token is a bug. - Return
ValueTaskonly for hot paths that frequently complete synchronously; default toTask. Never await aValueTasktwice. - In libraries, use
ConfigureAwait(false)on every await. In app or test code with a synchronization context you control, you may omit it. - Never block on async with
.Resultor.Wait(); that deadlocks under a synchronization context and wastes a thread otherwise. Make the caller async.
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.
- yesterday First seen · 92 lines · 1,177 tokens per session scan A e7dcf9b434a1
ai-agents csharp.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 1,177 tokens to every session, about $0.0059 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 2026-09-03.
Other instructions, from other repositories
Roslyn-Backed-MCP copilot-instructions.md
Copilot instructions for darylmcd/Roslyn-Backed-MCP, covering copilot instructions, code style (c#), layering rules, roslyn mcp (ai sessions in this repo) and mutation safety.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.