agui-dotnet-code-review

agui-dotnet-code-review is a skill for Claude Code, Codex from ag-ui-protocol/ag-ui. It costs 183 tokens per session (3,793 once invoked), scanned A, original, MIT.

A review guide for C# changes in the AG-UI .NET SDK. It checks the project’s own architecture, compatibility, and coding rules.

In plain words
What is it for?
Use it to review files under `sdks/dotnet/`, including serialization, project boundaries, public API changes, wire compatibility, and test coverage.
Why use it?
Generic code review may miss rules specific to this SDK, while automated warnings can produce irrelevant findings. The guide focuses reviews on confirmed violations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

About the project

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.

ag-ui-protocol/ag-ui · 15,739 stars · on GitHub · ag-ui.com

Install

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.

agentmods
npx agentmods add skills/ag-ui-protocol/ag-ui/agui-dotnet-code-review
Any agent
npx skills add ag-ui-protocol/ag-ui --skill agui-dotnet-code-review
Clone the repo
git clone --depth 1 https://github.com/ag-ui-protocol/ag-ui

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agui-dotnet-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dotnet-code-review.svg)](https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dotnet-code-review)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,793 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00183 $0.03793
Opus 5 $0.00092 $0.01896
Sonnet 5 $0.00037 $0.00759
Haiku 4.5 $0.00018 $0.00379

Measured 6d ago against content hash 598fde0ac5da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

.github/skills/agui-dotnet-code-review/SKILL.md · 259 lines

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 by TreatWarningsAsErrors, 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.

Read the full file on GitHub · 259 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 259 lines · 183 tokens per session scan A 598fde0ac5da

Subscribe to this mod's changes

agui-dotnet-code-review is a skill published in the GitHub repository ag-ui-protocol/ag-ui (15,739 stars, last pushed yesterday), licensed MIT. It adds 183 tokens to every session and 3,793 once invoked, about $0.0009 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.