AG-UI is an event-based protocol that lets AI agent backends communicate with user-facing applications. It standardizes agent events and inputs while supporting transports such as server-sent events, WebSockets, and webhooks. The catalogue add-ons help developers build integrations and applications around the protocol.
Borrowing it
Nothing to install: this file belongs to ag-ui-protocol/ag-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ag-ui-protocol/ag-ui/main/.github/skills/agui-dotnet-code-review/SKILL.mdgit clone --depth 1 https://github.com/ag-ui-protocol/ag-uiWrote 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/ag-ui-protocol/ag-ui/agui-dotnet-code-review)<a href="https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dotnet-code-review"><img src="https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dotnet-code-review/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/ag-ui-protocol/ag-ui/agui-dotnet-code-review"><img src="https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dotnet-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 209 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00183 | $0.03793 |
| Opus 5.5 | $0.00073 | $0.01517 |
| Sonnet 5.5 | $0.00037 | $0.00759 |
| Haiku 4.5 | $0.00018 | $0.00379 |
Grade A, and why
agui-dotnet-code-review 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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AG-UI .NET SDK Code Review
Encodes the AG-UI .NET SDK's house rules so a reviewer flags real violations a
generic C# reviewer misses. Authoritative sources: sdks/dotnet/AGENTS.md
(house rules) and sdks/dotnet/docs/architecture.md (design boundaries). Each
rule cites a real enforcement example in the repo; full BAD→GOOD examples and
per-rule exceptions live in references/rules.md. The
change-footprint and test rules below distil the minimize-change-footprint,
ensure-test-coverage, and ensure-test-quality review conventions for this SDK.
Reviewer discipline
- High signal-to-noise. Only flag a genuine violation of a rule below, tied to its cited convention. Don't invent nits or restate analyzer output.
- Verify before flagging. Read the actual changed code and confirm the rule applies. Automated reviewers have high false-positive rates.
- Scope. Review only files under
sdks/dotnet/. Skip generic style already enforced byTreatWarningsAsErrors, nullable, and EditorConfig. - Blast radius. Fix nothing — this skill only reports. Local convention violations get a finding; codebase-wide concerns are noted as out-of-scope follow-ups, not per-line nits.
- Severity: ❌ must fix (breaks AOT/wire/build/boundary); ⚠️ should fix (convention drift); 💡 optional polish.
The review process
Step 0 — Ground truth & file classification. Derive the package map from
AGUI.slnx; skim AGENTS.md + docs/architecture.md. Classify each changed
file: production | test | sample | proto | csproj | public-api | docs. Rules
are gated by class.
Step 1 — Determine and summarize the change set. Resolve what is under
review, in order: an explicit target (PR number / branch / commit range); else
the current branch vs. its tracking/base branch (git merge-base <base> HEAD);
plus staged, unstaged, and untracked working-tree changes. Then write a short
summary of what the diff does — new types, wire/protocol changes, public-surface
changes, new dependencies, src-vs-sample placement. This frames every phase and
catches scope creep early.
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 · 259 lines · 183 tokens per session scan A 598fde0ac5da
agui-dotnet-code-review is a skill published in the GitHub repository ag-ui-protocol/ag-ui (16,881 stars, last pushed yesterday), licensed MIT. It adds 183 tokens to every session and 3,793 once invoked, about $0.0007 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.
Other skills, from other repositories
dotnet-design-pattern-review
Review the C#/.NET code for design pattern implementation and suggest improvements.
analyzing-dotnet-performance
Scans .NET code for 50 performance anti-patterns across async, memory, strings, collections, LINQ, regex, serialization, and I/O with tiered severity classification. Use when analyzing .NET code for optimization opportunities, reviewing hot paths, or auditing allocation-heavy patterns.
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".
refactoring-csharp
Rename and refactor C# symbols in a .NET solution or multi-solution monorepo with a one-shot Roslyn CLI. Use when the user asks to rename a symbol, preview impact, update references across a solution, or refactor shared projects across several solutions.
resharper-clt
Use the free official JetBrains ReSharper Command Line Tools for .NET repositories. USE FOR: jb inspectcode; jb cleanupcode; stronger C# inspections, cleanup profiles, and CI-friendly JetBrains analysis. DO NOT USE FOR: replacing tests with inspection output; ad-hoc formatting-only work when the repo intentionally…
roslynator
Use the open-source free Roslynator analyzer packages and optional CLI for .NET. USE FOR: Roslynator.Analyzers setup; Roslynator CLI checks or cleanup; C# linting, static analysis, and code-fix automation. DO NOT USE FOR: overlapping analyzer packs with no consolidation plan; formatting-only work owned by another…