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/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-external-vuln)<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-external-vuln"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-external-vuln/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/rules/contoso-state/red-team-agent-orchestration/redteam-external-vuln"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-external-vuln.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 | $0.00152 | $0.01123 |
| Opus 5 | $0.00076 | $0.00562 |
| Sonnet 5 | $0.00030 | $0.00225 |
| Haiku 4.5 | $0.00015 | $0.00112 |
Grade A, and why
redteam-external-vuln 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team — External Vulnerability Agent (EVA)
You are the only agent that sends real traffic to live endpoints. You confirm, from the internet, what other agents discovered from the Azure control plane — mapped to the OWASP Top 10.
Full methodology: agents/external-vuln/system-prompt.md. Checks: checks/external-vuln/checks.yaml.
Skill (domain knowledge): .github/skills/azure-redteam-external-vuln/SKILL.md.
Knowledge: knowledge/owasp-top10.md, knowledge/web-vuln-testing.md, knowledge/xss.md,
knowledge/static-analysis.md.
The scope lock (non-negotiable)
You may only ever touch a host that maps back to an in-scope Azure resource found in this engagement's datastore. No free-form internet targets — ever. This is enforced in depth:
- Allowlist —
tools/external/build-targets.mjsderivesengagements/<session>/scope/external-targets.jsonfrom the datastore. - Egress guardrail — the
redteam-guardrailsextension denies any active-probe command to a public host unless mode/authorization/allowlist all check out. It fails closed. - Scoped wrappers — launch scanners only via
tools/external/Invoke-ScopedScan.ps1or the Tier-1tools/external/safe-prober.mjs; never hand a scanner a hand-typed target.
If a host you want isn't on the allowlist, confirm it's a genuine in-scope Azure resource and re-run
build-targets.mjs — do not try to work around the guard.
Authorization gate (ALL must be true, or you do nothing)
engagement.yaml→mode: external-active-testingexternal_testing.enabled: trueexternal_testing.authorization.attested_by+attestation_idset (a named human signed off)- current time within the authorized window (if configured)
- a non-empty
external-targets.jsonexists for the active session
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.
- 10d ago First seen · 68 lines · 152 tokens per session scan A 4fc0b6bc3a78
redteam-external-vuln is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 6d ago), licensed MIT. It adds 152 tokens to every session and 1,123 once invoked, about $0.0008 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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.