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 aliyun/alibabacloud-agent-toolkit --skill alibabacloud-executing-plansgit clone --depth 1 https://github.com/aliyun/alibabacloud-agent-toolkitWrote 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/aliyun/alibabacloud-agent-toolkit/alibabacloud-executing-plans)<a href="https://agentmods.dev/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-executing-plans"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-executing-plans/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/aliyun/alibabacloud-agent-toolkit/alibabacloud-executing-plans"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-executing-plans.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 | $0.00053 | $0.06668 |
| Opus 5 | $0.00026 | $0.03334 |
| Sonnet 5 | $0.00011 | $0.01334 |
| Haiku 4.5 | $0.00005 | $0.00667 |
Grade A, and why
alibabacloud-executing-plans 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 — 633 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud Executing Plans
AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE
This skill executes validated Terraform code via Alibaba Cloud IaC Service (remote execution). It creates real cloud resources that cost money. Safety gates are non-negotiable.
ALL CLI operations MUST use MCP tool
AlibabaCloud___CallCLI— never use Bash to runaliyuncommands directly.
PREREQUISITE CHECK — MANDATORY
Before proceeding, verify BOTH prerequisites:
- Validation passed — check
tasks/status.jsonhasstatus: "validated"(internal check, don't expose to user)- User explicitly confirmed they want to execute
If EITHER is missing, STOP IMMEDIATELY:
- Not validated? → Invoke alibabacloud:validate first
- No user confirmation? → Ask user before proceeding
Triggers
Activate when:
- User explicitly asks to execute/apply the Terraform plan
- User confirms they want to proceed after validation passes
NEVER activate automatically. This skill requires explicit user intent.
Rules
- Single deploy approval, granted upstream — The user authorizes deployment ONCE in
alibabacloud-validate's gate. Inside this skill the entireplan → applychain runs automatically. Never add a second confirmation between plan and apply. - Plan before apply, results always shown — Always run terraform plan first AND surface its output to the user before apply. The user can interrupt mid-stream if the plan reveals something unexpected, but the default flow does not stop to ask.
- MCP only — ALL
aliyunCLI commands MUST go throughAlibabaCloud___CallCLI, never through Bash - Inline content — Read .tf files locally, then pass content as string to
--code(MCP cannot access local files) - Record everything — All outputs recorded to tasks/
- Support rollback — Provide destroy option if apply fails
- Poll for completion — IaC Service is async; use sequential MCP calls to poll
- ⚠️ Destructive operations (destroy) require double confirmation
- Persist
state_id— IaC Service keeps the Terraform state remotely keyed bystate_id. This skill MUST write it back totasks/status.json(understate.state_id) on every Plan / Apply / Destroy and MUST pass the saved value on every subsequent Day-2 call. Losing thestate_idorphans the remote state and forces a fresh deploy (potential duplicate resources). - Source-of-truth integrity — Some failures are only discoverable at apply time (SKU offline in target AZ, zone out-of-capacity, etc.). Any spec change forced by such a failure MUST be written back to BOTH
designs/design.md(with a Decisions Log entry) ANDdesigns/terraform/*.tfBEFORE re-running plan/apply. Never hot-patch the in-flight apply — Day-2 iterations re-read these files and will redeploy the broken spec if it isn't fixed at the source.
What ships with it
2 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 · 633 lines · 53 tokens per session scan A 2dacdfb9c62c
alibabacloud-executing-plans is a skill published in the GitHub repository aliyun/alibabacloud-agent-toolkit (21 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 6,668 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 2026-08-30.
Other skills, from other repositories
alibabacloud-ecs-windows-os-troubleshooting
Troubleshoot and repair Alibaba Cloud ECS Windows instances from inside the GuestOS or remotely via Cloud Assistant. Use whenever the user reports any Windows symptom or asks for a health check on an ECS Windows instance, even vague ones like "check this machine": boot failures (BSOD, black screen, boot loop, stuck at…
alibabacloud-ecs-linux-os-troubleshooting
Troubleshoot an Alibaba Cloud ECS Linux OS. Use when a user needs to diagnose a specified ECS Linux instance, such as instance stuck in Starting, boot stuck, SSH/VNC/Workbench login failure, network issues, disk/FS issues, performance anomalies, suspected mining or hidden processes, crash/hang, clock drift, or…
bailian-managed-agent
A command-line tool for managing Alibaba Cloud Bailian hosted agents and deployments from an agents.yaml file. This file acts as the single description of the remote resources, similar to infrastructure-as-code configuration.
cloud-administration
Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that arrives as a surprise, and what the provider does not do for you. Use this to structure subscriptions or tenants, get…
network-administration
Designs and operates the corporate network — segmentation, remote access, wireless, DNS and addressing, and diagnosing network problems. Use this to segment a network, set up or fix remote access, diagnose intermittent connectivity, plan addressing or DNS, or assess whether the network's trust assumptions still hold.
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…