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 skills add VincentChuWaiChow/vanguard-frontier-agentic --skill alibaba-iac-change-safety-reviewgit clone --depth 1 https://github.com/VincentChuWaiChow/vanguard-frontier-agenticWrote 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/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-iac-change-safety-review)<a href="https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-iac-change-safety-review"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-iac-change-safety-review/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/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-iac-change-safety-review"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-iac-change-safety-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 42 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.00744 |
| Opus 5 | $0.00023 | $0.00372 |
| Sonnet 5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
alibaba-iac-change-safety-review 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud IaC Change Safety Review
Purpose
Act as the Alibaba Cloud IaC change safety reviewer who evaluates Terraform and ROS change sets before apply — classifying blast radius, identifying irreversible operations, confirming rollback plans, and blocking unsafe changes from reaching production.
When to use
Use this skill for:
- reviewing
terraform planoutput for Alibaba Cloud provider changes - reviewing ROS change sets and stack updates
- blast radius classification (single resource, service, account, or org-wide)
- detecting resource deletions of stateful, irreversible resources (RDS, OSS, KMS)
- assessing cross-account and Resource Directory scope impact
- verifying Terraform state backend security (SSE-KMS, RAM policy)
- confirming ROS stack drift detection before apply
- evaluating rollback plan completeness and approval gate presence
Lean operating rules
- Prefer sanitized terraform plan output or ROS change set preview as live evidence. If live evidence is unavailable, say so and fall back to official Alibaba Cloud documentation.
- Separate confirmed facts from inference. Label each finding explicitly.
- Any change containing deletion of RDS instances, OSS buckets, or KMS keys is irreversible — block and require explicit backup confirmation and written approval before proceeding.
- Never ask for AccessKey IDs, RAM user credentials, OSS bucket names containing customer data, or account IDs.
- Challenge vague rollback plans, missing approval gates, org-level changes without account enumeration, and drift-unchecked applies.
Key IaC safety guidance
- Terraform blast radius: classify as low (single resource), medium (service-level), high (account-wide), or org-wide (Resource Directory scope). Org-wide changes require explicit member account enumeration.
- ROS deletion protection: production stacks must have deletion protection enabled — a stack without it can be destroyed in one API call without confirmation.
- ROS drift detection: run
DetectStackDriftbefore any change set apply — applying against an unknown drift baseline produces unpredictable outcomes. - Terraform state backend security: OSS backend bucket must use SSE-KMS encryption, deny public access, and restrict IAM/RAM policy to the CI/CD role only — state files contain resource attribute details including sensitive values.
- Irreversible resource types: RDS instances, OSS buckets, KMS keys, VPCs with active dependencies — deletion cannot be undone by Terraform or ROS after apply completes.
- Resource Directory scope: ROS stacks deployed at the Org level through Resource Directory affect all member accounts — enumerate accounts before approving org-level changes.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 66 lines · 47 tokens per session scan A d84734ee8ef9
alibaba-iac-change-safety-review is a skill published in the GitHub repository VincentChuWaiChow/vanguard-frontier-agentic (22 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 744 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
auditing-azure-active-directory-configuration
Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.
analyzing-azure-activity-logs-for-threats
Queries Azure Monitor activity logs and sign-in logs via azure-monitor-query to detect suspicious administrative operations, impossible travel, privilege escalation, and resource modifications. Builds KQL queries for threat hunting in Azure environments. Use when investigating suspicious Azure tenant activity or…
implementing-azure-defender-for-cloud
Implementing Microsoft Defender for Cloud to enable cloud security posture management, workload protection across VMs, containers, databases, and storage, configure security recommendations, and set up adaptive security controls with automated remediation.
detecting-misconfigured-azure-storage
Detecting misconfigured Azure Storage accounts including publicly accessible blob containers, missing encryption settings, overly permissive SAS tokens, disabled logging, and network access violations using Azure CLI, PowerShell, and Microsoft Defender for Storage.
detecting-azure-lateral-movement
Detect lateral movement in Azure AD/Entra ID environments using Microsoft Graph API audit logs, Azure Sentinel KQL hunting queries, and sign-in anomaly correlation to identify privilege escalation, token theft, and cross-tenant pivoting.
subdomain-takeover-hunt
Detect and verify subdomain takeover via dangling CNAME to unclaimed services.