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 rules/vinayaklatthe/microsoft-security-agent-toolkit/cursorrulesgit clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-agent-toolkitWhat 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 | $0.00308 | $0.00308 |
| Opus 5 | $0.00154 | $0.00154 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
cursorrules 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.
What it actually says
microsoft-security-agent-toolkit — agent rules
Read HANDOFF.md first. It is the single source of truth for design decisions, conventions, tool surface, and open work.
Hard rules
- Never log or commit tenant secrets.
.envstays gitignored. - Every write tool requires
confirm: true+ separate write-app registration (seedocs/permissions-required.md). - Skills only declare
tools_required; they do not bundle this toolkit. - Defensive / governance content only — no offensive (red-team) tooling.
- No live-tenant calls in tests, demos, samples — use synthetic data.
Conventions
- Branch off
main, PR intomain. One server / snippet pack / demo per PR. - Conventional-commit-ish messages with
Co-authored-by: Copilot <[email protected]>when AI-assisted. - KQL files require the header in
kql-snippets/README.md. - MCP server READMEs follow the contract in
HANDOFF.md.
Pairs with
microsoft-security-skills v0.2.0, 88 skills. Tool ID renames must update INTEGRATIONS.md in both repos simultaneously.
Where to start
Topmost unchecked item from HANDOFF.md "Open work". Phase 1 = sentinel-mcp implementation.
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.
- 2d ago First seen · 27 lines · 308 tokens per session scan A 2d055c8a10fe
cursorrules is a cursor rule published in the GitHub repository vinayaklatthe/microsoft-security-agent-toolkit (2 stars, last pushed 2mo ago), licensed MIT. It adds 308 tokens to every session, about $0.0015 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 2026-08-31.
Other cursor rules, from other repositories
read-xlsx
Reading, writing, diffing, and repairing spreadsheets (.xlsx) for AI agents via the xfa MCP server.
cursorrules
Cursor rule "cursorrules" from me2resh/agent-decision-record, covering agent decision records (agdr) — cursor rules, purpose, see: https://github.com/me2resh/agent-decision-record, decision detection and adding a new dependency → stop, document decision first.
agdr
Agent Decision Records - enforces structured documentation of technical decisions before implementation.
core
Rails 8 Core Principles Guide.
services
Rails Service Objects Guide.
mintlify
Cursor rule "mintlify" from TheSethRose/Copilot-Skills, covering mintlify technical writing assistant, core writing principles, language and style requirements, content organization standards and user-centered approach.