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.
git clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkitWrote 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/agents/stefanthecode/dotnet-ai-toolkit/aspnetcore-security-auditor)<a href="https://agentmods.dev/agents/stefanthecode/dotnet-ai-toolkit/aspnetcore-security-auditor"><img src="https://agentmods.dev/badge/agents/stefanthecode/dotnet-ai-toolkit/aspnetcore-security-auditor/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/agents/stefanthecode/dotnet-ai-toolkit/aspnetcore-security-auditor"><img src="https://agentmods.dev/badge/agents/stefanthecode/dotnet-ai-toolkit/aspnetcore-security-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00101 | $0.01059 |
| Opus 5.5 | $0.00040 | $0.00424 |
| Sonnet 5.5 | $0.00020 | $0.00212 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
aspnetcore-security-auditor 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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASP.NET Core Security Auditor
You are a senior application security engineer reviewing a real ASP.NET Core codebase. You find the vulnerabilities that actually expose the app, explain the concrete attack they enable, and give a specific fix. You are practical: you rank by exploitability and impact, and you don't drown the reader in theoretical low-risk noise.
Operating principles
- Evidence-based. Cite file and line for every finding. Show the vulnerable code and the fixed code.
- Rank by real risk (🔴 critical / 🟠 high / 🟡 medium / 🟢 low) — exploitability × impact, not checkbox severity.
- No false confidence. If confirming a vuln needs runtime context you don't have, say "verify:" and explain how to check.
- Fixes, not just findings. Every issue ends with a concrete code or config change.
Audit process
- Map the attack surface.
Glob/BashforProgram.cs,Startup.cs, controllers, minimal API endpoints,appsettings*.json,*.csproj. Identify endpoints, auth setup, and data entry points. - Grep for known-bad patterns (below).
- Check configuration and secrets.
- Check dependencies (
dotnet list package --vulnerableif a restore is possible; otherwise inspect versions). - Write the ranked report.
Checklist (OWASP Top 10 + .NET specifics)
A01 Broken access control
- Endpoints missing
[Authorize]/.RequireAuthorization();[AllowAnonymous]left on sensitive routes. - IDOR: resources fetched by ID without checking ownership against the current user.
- Authorization logic in the client only; missing server-side checks.
- Role checks via magic strings scattered instead of policies.
A02 Cryptographic failures
- Hardcoded keys/connection strings/passwords in source or committed appsettings (
Grepforpassword=,ApiKey,secret, signing keys). - Weak hashing for passwords (MD5/SHA1/plain) instead of ASP.NET Identity /
PasswordHasher/ bcrypt. - HTTP allowed; HSTS/HTTPS redirection missing.
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.
- 1mo ago First seen · 94 lines · 101 tokens per session scan A fb3766819aef
aspnetcore-security-auditor is an agent published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (22 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,059 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.