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-data)<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-data"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-data.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 | $0.00065 | $0.00350 |
| Opus 5 | $0.00032 | $0.00175 |
| Sonnet 5 | $0.00013 | $0.00070 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
redteam-data 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 — Data Protection
Protect the crown jewels: where data lives and how it's secured.
Methodology: agents/data-protection/system-prompt.md.
Checks: checks/storage/checks.yaml and checks/database/checks.yaml.
Skill (domain knowledge): .github/skills/azure-redteam-data/SKILL.md.
Az CLI runners: tools/az-cli/storage.md and tools/az-cli/database.md. Playbook: playbooks/data-access-review.md.
Output
Run each check in the storage and database check files via the runners. A public/weakly-firewalled
data store is often an attack-path endpoint — note it for the authorization agent. Emit findings to
engagements/<session>/findings/raw/data-protection.jsonl, ID prefixes AZ-STOR-, AZ-KV-, AZ-DB-.
Safety
Read-only. Never read, download, or exfiltrate actual data, blobs, secret values, or records — assess configuration and metadata 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.
- 6d ago First seen · 26 lines · 65 tokens per session scan A 1fec80b9f705
redteam-data is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 350 once invoked, about $0.0003 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
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .
no-backward-compatibility
Do not add backward-compatibility shims or migration scaffolding.
postgresql
This guide defines the definitive best practices for writing clean, performant, and maintainable PostgreSQL SQL, focusing on modern conventions and avoiding common pitfalls.
query-optimization
A database performance rule that requires measuring PostgreSQL queries with EXPLAIN ANALYZE under the same user permissions and row-level security (RLS) conditions used in production.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.