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-live-ram-policy-change-guardgit 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-live-ram-policy-change-guard)<a href="https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-live-ram-policy-change-guard"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-live-ram-policy-change-guard/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-live-ram-policy-change-guard"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-live-ram-policy-change-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.01358 |
| Opus 5 | $0.00038 | $0.00679 |
| Sonnet 5 | $0.00015 | $0.00272 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
alibaba-live-ram-policy-change-guard 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud Live RAM Policy Change Guard
Purpose
Act as the guarded live Alibaba Cloud operator for alibaba-live-ram-policy-change-guard work. Gate every RAM policy mutation, role change, and Control Policy modification with explicit blast-radius assessment and authority approval. Treat AdministratorAccess assignment as the highest-risk category — it is account-wide and irreversible without deliberate rollback.
When to Use
Use this skill when:
- A RAM policy must be created, modified, or deleted
- A RAM role is being created, deleted, or having policies attached/detached
- A RAM user is being granted or revoked access to a policy
- AdministratorAccess or any system policy with broad permissions is being assigned
- A Resource Directory Control Policy constraint is being created, modified, or deleted for an OU
- An operator needs to audit the current RAM policy and role inventory before making changes
- Detecting and remediating over-privileged RAM users, roles, or stale policy attachments
When NOT to Use
Do not use this skill when:
- The task is a read-only RAM audit with no mutation intent
- The task involves Kubernetes RBAC within ACK only (no RAM changes)
- The task is creating a new RAM user with read-only access (low risk, no live-guard required)
- The task is unrelated to Alibaba Cloud identity and access management
Pre-Flight Checklist
Before executing any RAM mutation, verify all of the following:
- Account identity confirmed — explicitly state the target Alibaba Cloud account ID. Confirm via
aliyun ram GetAccountAliasor the console. - Active RAM principal confirmed — confirm the identity executing the change and its current policy scope.
- Current policy/role inventory captured — list current policies attached to the target user/role before any change using
aliyun ram ListPoliciesForRoleoraliyun ram ListPoliciesForUser. - Blast-radius assessed — for AdministratorAccess assignment, the blast radius is the entire account. For Control Policy changes, the blast radius is all member accounts in the target OU. Document this explicitly.
- Active STS token impact — RAM policy deletion does not invalidate existing STS tokens immediately, but operations using the deleted policy's permissions will fail when the token is next used for that action. List any services or applications known to be using STS tokens derived from the policy being changed.
- Change justification documented — the operator must state the business reason, the specific principal(s) affected, and the policy being added or removed.
- Rollback plan documented — identify the current policy version or attachment state that will be restored if the change must be reverted.
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 · 98 lines · 76 tokens per session scan A d641b185665a
alibaba-live-ram-policy-change-guard is a skill published in the GitHub repository VincentChuWaiChow/vanguard-frontier-agentic (22 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 1,358 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 2026-08-30.
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…
m365-entra-attack
Microsoft 365 / Entra ID red-team attack chain — current 2026 reality. AADSTS code reference, user enumeration vectors (with hardening status), Smart Lockout math, Conditional Access bypass options, ROPC + SAML SSO browser flow, Burp/Playwright templates. Built from authorized red-team work where ROPC spray surfaced…
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.
codex-agent-collaboration
Delegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI perspective, want to explore different approaches, or need specialized Codex capabilities for complex coding tasks.
founder-quiz
Take a behavioral self-assessment to discover where you sit on the founder mode spectrum. 15 questions that reveal your actual operating mode — not what you think you do, but what you actually do. Use for honest self-reflection.