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 skills add joslat/maf-doctor --skill maf-anti-pattern-scannergit clone --depth 1 https://github.com/joslat/maf-doctorWrote 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/joslat/maf-doctor/maf-anti-pattern-scanner)<a href="https://agentmods.dev/skills/joslat/maf-doctor/maf-anti-pattern-scanner"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-anti-pattern-scanner/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/joslat/maf-doctor/maf-anti-pattern-scanner"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-anti-pattern-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.01680 |
| Opus 5 | $0.00065 | $0.00840 |
| Sonnet 5 | $0.00026 | $0.00336 |
| Haiku 4.5 | $0.00013 | $0.00168 |
Grade A, and why
maf-anti-pattern-scanner 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 11d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maf-anti-pattern-scanner
The migration tooling answers "is this code on MAF 1.3.0?" This skill answers a different question: "is this MAF 1.3.0 code following best practices?" Same codebase, different lens.
When to use
- After a migration plan finishes — verify the converted code isn't merely compiling, it's idiomatic.
- On any clean 1.3.0 codebase as a periodic audit.
- In CI on PRs touching MAF agent/workflow code, scoped to the diff.
When NOT to use
- For migration discovery — that's
maf-obsolete-api-registry+cs0618-hunter. This skill assumes you're already on 1.3.0. - For runtime correctness checks — that's
maf-fan-out-validator. This skill checks idiom and configuration, not topology correctness.
Anti-patterns covered
Each is a "rule" with a unique ID, a severity, and a deterministic search pattern. The MCP tool MafScanAntiPatterns ingests this list.
Security
MAF-AP-SEC-001 — DefaultAzureCredential in production code (severity: error)
Pattern: new DefaultAzureCredential() anywhere outside a test project (*Tests.csproj).
Why: DefaultAzureCredential walks an authentication chain that includes developer credentials, environment variables, and managed identity. The chain order can change between SDK versions; production deployments should NEVER tolerate that surprise. Pin to the specific credential type your environment uses.
Fix: Replace with ManagedIdentityCredential (Azure-hosted) or WorkloadIdentityCredential (Kubernetes), or ClientSecretCredential / ClientCertificateCredential for explicit service principals.
Source: maf-constraints.instructions.md hard rule #4.
MAF-AP-SEC-002 — Hard-coded API keys (severity: error)
Pattern: String literal matching (sk-|api[-_]?key)[A-Za-z0-9_-]{16,} anywhere in .cs files.
Why: Keys in source land in git history forever.
Fix: Read from IConfiguration / Azure.Identity / Microsoft.Extensions.Configuration.UserSecrets.
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.
- 11d ago First seen · 111 lines · 130 tokens per session scan A e418817886f4
maf-anti-pattern-scanner is a skill published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 24d ago), licensed MIT. It adds 130 tokens to every session and 1,680 once invoked, about $0.0006 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.
Other skills, from other repositories
pr-review
Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…
Smart Code Review
Review a PR diff: triage its severity, then produce a depth-appropriate review with structured findings, fix suggestions, and a merge decision. Use for code review, review PR, and severity triage requests.
code-analysis
Use the free built-in .NET SDK analyzers and analysis levels with gradual Roslyn warning promotion. USE FOR: the repo wants first-party .NET analyzers; CI should fail on analyzer warnings; the team needs AnalysisLevel or AnalysisMode guidance. DO NOT USE FOR: third-party analyzer selection by itself; formatting-only…
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
sonarjs
Use SonarJS-derived rules in .NET repositories that ship JavaScript or TypeScript frontends and need deeper bug-risk, code-smell, or cognitive-complexity checks than a minimal ESLint baseline. USE FOR: SonarQube, SonarCloud, or eslint-plugin-sonarjs setups; frontend code smells; cognitive complexity and deeper…
winui-code-review
Code quality review for WinUI 3 apps — MVVM compliance, x:Bind correctness, accessibility, theming, security, and performance. Use before committing to catch issues that the compiler and UI tests won't find.