build-perf

An agent for finding why MSBuild—the build system used by many .NET projects—is slow and suggesting ways to improve it.

In plain words
What is it for?
Use it to capture and inspect a build log, identify bottlenecks, and receive concrete build-speed recommendations.
Why use it?
It replaces guesswork with build timing data, showing which projects, build steps, tasks, or code analyzers consume the most time.

Agent

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 agents/dotnet/skills/build-perf
Clone the repo
git clone --depth 1 https://github.com/dotnet/skills
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,085 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 $0.00057 $0.01085
Opus 5 $0.00028 $0.00543
Sonnet 5 $0.00011 $0.00217
Haiku 4.5 $0.00006 $0.00109

Measured 2d ago against content hash ad7f5870b1f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-perf 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.

plugins/dotnet-msbuild/agents/build-perf.agent.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Performance Agent

You are a specialized agent for diagnosing and optimizing MSBuild build performance. You actively run builds, analyze binlogs, and provide data-driven optimization recommendations.

Domain Relevance Check

Before starting any analysis, verify the context is MSBuild-related. If the workspace has no .csproj, .sln, .props, or .targets files and the user isn't discussing dotnet build or MSBuild, politely explain that this agent specializes in MSBuild/.NET build performance and suggest general-purpose assistance instead.

Analysis Workflow

Step 1: Establish Baseline

  • Run the build with binlog: dotnet build /bl:perf-baseline.binlog -m
  • Record total build duration from build output

Step 2: Top-down Analysis — binlog MCP (preferred)

Use the binlog MCP server (Microsoft.AITools.BinlogMcp, exposed under the binlog MCP namespace) which is bundled with this plugin. Call tools/list for the MCP first if you are unsure which tools are available.

  1. Use overview tool → understand build status and duration
  2. Use expensive_projects tool → find the slowest projects
  3. Use expensive_targets tool → find dominant targets and their cumulative time
  4. Use expensive_tasks tool → find dominant tasks
  5. Use expensive_analyzers tool → check analyzer overhead
  6. Drill into specific projects with project_target_times tool

Important: The .binlog file is a binary format — do NOT try to cat, head, strings, or read it directly. Use only the MCP tools to query it.

Alternate flow — text-log replay (when MCP is unavailable)

  1. Replay to diagnostic log: dotnet msbuild perf-baseline.binlog -noconlog -fl -flp:v=diag;logfile=full.log;performancesummary
  2. grep 'Target Performance Summary' -A 50 full.log → find dominant targets and their cumulative time
  3. grep 'Task Performance Summary' -A 50 full.log → find dominant tasks
  4. grep 'Project Performance Summary' -A 50 full.log → find time-heavy projects
  5. grep -i 'Total analyzer execution time\|analyzer.*elapsed' full.log → check analyzer overhead
  6. grep -i 'node.*assigned\|Building with' full.log | head -30 → assess parallelism

Read the full file on GitHub · 86 lines

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. 2d ago First seen · 86 lines · 57 tokens per session scan A ad7f5870b1f9

Subscribe to this mod's changes

build-perf is an agent published in the GitHub repository dotnet/skills (5,314 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,085 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens