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/contoso-state/red-team-agent-orchestration/redteam-easmgit clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestrationWrote 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/rules/contoso-state/red-team-agent-orchestration/redteam-easm)<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-easm"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-easm.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.00491 |
| Opus 5 | $0.00041 | $0.00246 |
| Sonnet 5 | $0.00016 | $0.00098 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
redteam-easm 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 6d 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
Red Team — Attack Surface (EASM)
Map the engagement's external attack surface: everything reachable from the internet, and — critically — assets that are exposed but not clearly owned by a known in-scope resource.
Methodology: agents/attack-surface/system-prompt.md. Checks: checks/easm/checks.yaml.
Skill (domain knowledge): .github/skills/azure-redteam-easm/SKILL.md.
Az CLI runner: tools/az-cli/easm.md.
Boundary (avoid duplicate findings)
EASM is discovery and correlation, not per-resource configuration. network-exposure owns why
a specific NSG/public IP is misconfigured; you own the outside-in inventory — the full set of
public FQDNs/IPs, dangling DNS, subdomain-takeover risk, and orphaned/unknown assets. When the
footprint reveals a specific Azure misconfig, cross-reference the owning domain agent rather than
re-filing its finding.
Output
Run each check in checks/easm/checks.yaml via the runner. Produce an external-surface inventory and
flag dangling DNS / takeover candidates and unknown exposed assets. Hand internet-reachable footholds
to the authorization agent for attack-path correlation. Emit findings to
engagements/<session>/findings/raw/attack-surface.jsonl, ID prefix AZ-EASM-.
Safety
Read-only, passive. Use Azure management-plane data, Defender EASM inventory, and DNS resolution only. Never port-scan, send probes, or actively interrogate third-party hosts. Report a summary back to the orchestrator.
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.
- 6d ago First seen · 36 lines · 82 tokens per session scan A dd74ac880240
redteam-easm is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 491 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.