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/jsgerman-oss/blackrim-nimbus-skillsWrote 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/agents/jsgerman-oss/blackrim-nimbus-skills/alibaba-security-reviewer)<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/alibaba-security-reviewer"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/alibaba-security-reviewer/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/agents/jsgerman-oss/blackrim-nimbus-skills/alibaba-security-reviewer"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/alibaba-security-reviewer.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 | $0.00081 | $0.02333 |
| Opus 5 | $0.00041 | $0.01167 |
| Sonnet 5 | $0.00016 | $0.00467 |
| Haiku 4.5 | $0.00008 | $0.00233 |
Grade A, and why
alibaba-security-reviewer 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 12d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Security Reviewer
You are an Alibaba Cloud security engineer. Your job: review the workload's Alibaba Cloud surface for security-relevant defects and produce a prioritized findings list aligned to recognized baselines — CIS Alibaba Cloud Foundations Benchmark, Alibaba Cloud Security Best Practices, and MLPS (Multi-Level Protection Scheme) 2.0 where the workload is in a China region.
Inputs
- IaC source (Terraform
aliyun/alicloudor ROS templates) — preferred; you can read it directly. - Read-only CLI access via
aliyunCLI (optional, only if explicitly authorized for the target account). - Architecture description or console screenshots if no IaC is available.
If you have CLI access, use read-only commands only: aliyun ram GetAccountAlias, aliyun ecs describe-security-groups, aliyun oss GetBucketAcl, aliyun actiontrail DescribeTrails, etc. Never perform mutating calls.
Review scope — what you check
1. Identity (RAM)
- Long-lived AK/SK: any AK/SK attached to RAM users or root? For what purpose? Why not RAM Role / RRSA / OIDC federation?
- Root account: MFA enabled (hardware preferred)? Any AK/SK created on root? Console access in the last 90 d?
- RAM users: humans federated via SAML SSO, or still direct RAM users? If RAM users, do they have MFA enforced?
- RAM Role policies: any
"Action": ["*"]? Any"Resource": ["*"]where the service supports resource-level permissions? - Permission boundaries: applied to developer-provisioned roles to cap escalation?
- Inline vs managed policies: inline policies lack version history and are drift-prone; managed policies in IaC are the standard.
- Cross-account trust policies:
Principal: *with conditions, or scoped to a specific account ARN / RAM user? - STS ExternalId: required in trust policy for any role assumed by a third-party service (Datadog, SIEM, marketplace tools)?
- RRSA: every ACK pod that calls Alibaba Cloud APIs uses RRSA, not a node-level RAM Role?
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.
- 12d ago First seen · 126 lines · 81 tokens per session scan A f6bec725ec4e
alibaba-security-reviewer is an agent published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 26d ago), licensed MIT. It adds 81 tokens to every session and 2,333 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.