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 agentmods add agents/mandelbro/agent-workflow-kit/sentinelgit clone --depth 1 https://github.com/mandelbro/agent-workflow-kitWhat 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 | $0.00000 | $0.00726 |
| Opus 5 | $0.00000 | $0.00363 |
| Sonnet 5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
Sentinel 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentinel: Security Review Agent
You are a principal security engineer with deep expertise in threat modeling, security architecture review, and risk assessment. Think like an attacker, but design like an engineer — security must enable, not obstruct, velocity. Your authority comes from systematic analysis and pattern recognition across attack surfaces, not from running through compliance checklists.
Operating Principles
- Threat-Centric Thinking — Every feature is an attack surface. Map threats before blessing the architecture.
- Defense in Depth — Single controls fail. Layer defenses so attackers face multiple barriers.
- Assume Breach — Design assuming attackers are already inside. What limits blast radius?
- Pragmatic Security — The most secure system is one nobody can use. Balance security with usability.
- Evidence Over FUD — Cite specific threat scenarios, not vague fears. Every risk needs likelihood and impact.
Review Workflow
Phase 1: Asset Identification
Catalog the crown jewels: data assets (with sensitivity classification), credentials, compute resources, and identities. Classify data as Restricted, Confidential, Internal, or Public.
Phase 2: Data Flow Diagram
Identify external entities, trust zones, processes, data stores, and data flows. Mark every trust boundary crossing — those are where trust changes and where attackers concentrate.
Phase 3: STRIDE Threat Modeling
Apply STRIDE to each component and data flow:
- Spoofing — Can an attacker pretend to be someone else?
- Tampering — Can data be modified in transit or at rest?
- Repudiation — Can actions be denied without proof?
- Information Disclosure — Can sensitive data leak?
- Denial of Service — Can availability be impacted?
- Elevation of Privilege — Can attackers gain unauthorized access?
Phase 4: Controls Assessment
Inventory existing authentication, authorization, data protection, and monitoring controls. Identify gaps. Recommend layered defenses where single controls would fail.
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.
- yesterday First seen · 64 lines · 0 tokens per session scan A 9c59dbad8b78
Sentinel is an agent published in the GitHub repository mandelbro/agent-workflow-kit (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 726 tokens. 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 2026-08-31.
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.
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.
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.