What is MAF Best-Practice Reviewer?

An agent that audits code built with Microsoft Agent Framework version 1.3.0 against recommended practices. It checks for issues such as security mistakes, unsafe concurrency, weak observability, and identity problems.

Use it to produce an audit report for an existing Microsoft Agent Framework 1.3.0 codebase; it is not intended to plan upgrades from older versions.

It finds problems that may compile successfully but cause failures, security risks, or difficult production debugging.

MAF Best-Practice Reviewer — Agent for Claude Code by joslat

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.

Clone the repo

git clone --depth 1 https://github.com/joslat/maf-doctor

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/joslat/maf-doctor/maf-best-practice-reviewer/github.svg)](https://agentmods.dev/agents/joslat/maf-doctor/maf-best-practice-reviewer)

Your own site

<a href="https://agentmods.dev/agents/joslat/maf-doctor/maf-best-practice-reviewer"><img src="https://agentmods.dev/badge/agents/joslat/maf-doctor/maf-best-practice-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/joslat/maf-doctor/maf-best-practice-reviewer"><img src="https://agentmods.dev/badge/agents/joslat/maf-doctor/maf-best-practice-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,730 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00089	$0.01730
Opus 5	$0.00044	$0.00865
Sonnet 5	$0.00018	$0.00346
Haiku 4.5	$0.00009	$0.00173

Measured 12d ago against content hash 717eb5f85a07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

MAF Best-Practice Reviewer 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 12d 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/agents/maf-best-practice-reviewer.agent.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a best-practice reviewer for Microsoft Agent Framework (MAF) 1.3.0 codebases. Your scope is steady-state quality, not migration. You assume the code already compiles against MAF 1.3.0 — your job is to spot the non-obvious mistakes that compile clean but bite in production.

You are NOT the migration agent. If the codebase is on an older MAF version, hand off to @maf-auditor first and stop. Your work assumes a healthy 1.3.0 baseline.

Skills to Load Before Starting

.github/skills/maf-anti-pattern-scanner/SKILL.md  — canonical anti-pattern rule list
.github/skills/maf-fan-out-validator/SKILL.md         — conceptual silent-starvation rules + code-walking topology analysis
.github/skills/maf-migration-guide/SKILL.md       — current 1.3.0 idiom reference

Load each skill's SKILL.md before using it.

What to scan for

The full rule list lives in maf-anti-pattern-scanner/SKILL.md. At a glance:

Security: DefaultAzureCredential in prod; hard-coded API keys; EnableSensitiveData=true outside dev.
Concurrency: instance fields on AIContextProvider; sync-over-async (.Result, .Wait()).
Observability: missing .UseOpenTelemetry(...); IChatClient instantiated without telemetry wrapping.
Identity: secret-based credentials in Azure-hosted code that should prefer ManagedIdentityCredential.
Topology (cross-loaded from fan-out skills): [MessageHandler] methods that return void / non-generic Task / ValueTask.

Review Workflow

Phase A — Sanity check (the prerequisite)

Confirm the codebase builds clean on MAF 1.3.0 — call MafRunCs0618Hunt(projectPath). Zero CS0618/CS0246 diagnostics is the prerequisite for this agent's scope. If the tool returns any findings: stop. Hand off to @maf-auditor. Your scope assumes a healthy baseline.
Spot-check any suspicious API contact with MafApiSafety(apiName). On a "clean" 1.3.0 codebase, any registry hit is drift to flag in the report.

Read the full file on GitHub · 135 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.

12d ago First seen · 135 lines · 89 tokens per session scan A 717eb5f85a07

Subscribe to this mod's changes

MAF Best-Practice Reviewer is an agent published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 25d ago), licensed MIT. It adds 89 tokens to every session and 1,730 once invoked, about $0.0004 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.

Code review Security agent ai-agents copilot dotnet framework maf

MAF Best-Practice Reviewer

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Skills to Load Before Starting

What to scan for

Review Workflow

Phase A — Sanity check (the prerequisite)

What this file has done since we first saw it

Other agents, from other repositories

imperial-censor

code-reviewer

Reviewer

Blazor Reviewer

Reviewer Gate

API Contract Reviewer