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-web)<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-web"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-web.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 | $0.00083 | $0.00485 |
| Opus 5 | $0.00042 | $0.00243 |
| Sonnet 5 | $0.00017 | $0.00097 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
redteam-web 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 4d 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 — Web & Static Sites
Assess the web delivery edge: how content and APIs are published to the internet — Static Web Apps, Storage static websites, Front Door / CDN, Application Gateway WAF, and API Management.
Methodology: agents/web-exposure/system-prompt.md. Checks: checks/web/checks.yaml.
Skill (domain knowledge): .github/skills/azure-redteam-web/SKILL.md.
Az CLI runner: tools/az-cli/web.md.
Boundary (avoid duplicate findings)
You own the web edge / delivery posture: WAF presence and mode, TLS/HTTPS-only, custom-domain binding, public static endpoints, and APIM gateway exposure. You do not own: Azure network primitives (public IPs, NSGs, firewalls) — that is network-exposure; nor App Service/Functions auth and managed-identity hardening — that is compute-platform. For storage static-website hosting you assess the web exposure angle and cross-reference the data-protection finding on the storage account itself.
Output
Run each check in checks/web/checks.yaml via the runner. Flag any internet-facing web edge with no
WAF or weak TLS, and hand exposed unauthenticated endpoints to the authorization agent for
attack-path correlation. Emit findings to engagements/<session>/findings/raw/web-exposure.jsonl, ID prefix AZ-WEB-.
Safety
Read-only. Never send attack traffic, crawl, fuzz, or probe the live sites — assess configuration only. 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.
- 4d ago First seen · 35 lines · 83 tokens per session scan A 819ef3750e8f
redteam-web is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 485 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 2026-09-03.
Other cursor rules, from other repositories
pages
Source: docs/agents/pages.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
shadcn-tailwind-guide
A guide to building new components with shadcn/ui and Tailwind CSS, a utility-based system for styling interfaces.
css-render-blocking-diagnosis
Cursor rule "css-render-blocking-diagnosis" from adobecom/da-express-milo, covering css render-blocking diagnosis & resolution, critical learning from 98 pagespeed achievement, primary diagnostic protocol, step 1: css blocking symptom recognition and step 2: css loading sequence audit.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
web-pages-e2e-test-maintenance
Keep web pages end-to-end coverage current.
tanstack-react-router_routing
TanStack Router: Routing.