Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsnpx agentmods add skills/huaweicloud/huaweicloud-skills/huawei-cloud-ecs-shutdown-experimentWrote 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/huaweicloud/huaweicloud-skills/huawei-cloud-ecs-shutdown-experiment)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ecs-shutdown-experiment"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ecs-shutdown-experiment/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/huaweicloud/huaweicloud-skills/huawei-cloud-ecs-shutdown-experiment"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ecs-shutdown-experiment.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 | $0.00209 | $0.03657 |
| Opus 5.5 | $0.00084 | $0.01463 |
| Sonnet 5.5 | $0.00042 | $0.00731 |
| Haiku 4.5 | $0.00021 | $0.00366 |
Grade A, and why
huawei-cloud-ecs-shutdown-experiment 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 1mo 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud ECS Shutdown Chaos Experiment
⚠️ This skill performs real ECS shutdown operations in Phase 2. Ensure target instances can tolerate downtime. Emergency rollback is always available.
Overview
Full lifecycle ECS shutdown fault injection experiment for Huawei Cloud chaos engineering, covering three phases:
| Phase | Name | Action | Key Output |
|---|---|---|---|
| 1 | Prepare | Discover, validate, generate config | experiment.json + rollback_experiment.sh |
| 2 | Execute | Shutdown → hold → rollback → verify | execution-log.json + execution-report.md |
| 3 | Analyze | Collect CES metrics + LTS logs, analyze patterns | log-analysis-result.json + log-analysis-report.md |
Scope: standalone ECS instances in any availability zone (non-CCE).
Prerequisites
- hcloud CLI (KooCLI) — installed and configured with AK/SK. See
references/cli-installation-guide.md. - Python 3 — for discovery, validation, execution, and analysis scripts.
- Environment variables:
HW_ACCESS_KEY,HW_SECRET_KEY,HW_REGION_NAME(optional, defaultcn-north-4). - IAM permissions: varies by phase — see
references/iam-policies.mdfor the full matrix. - Phase 3 only: LTS log group ID (find via
hcloud LTS ListLogGroupsor LTS console).
Environment check (run before any phase):
bash scripts/check_env.sh --cli-region <region>
Phase 1: Prepare
Does NOT start the experiment. Only discovers targets, validates compatibility, and generates configuration files.
Step 1.1: Discover Target ECS Instances
python3 scripts/discover_ecs.py --cli-region <region>
python3 scripts/discover_ecs.py --cli-region <region> --az cn-north-4a --status ACTIVE
python3 scripts/discover_ecs.py --cli-region <region> --name-pattern "web-"
Output: JSON with instance ID, name, status, AZ, flavor, charging mode, and tags.
Step 1.2: Validate Compatibility [CRITICAL GATE]
python3 scripts/validate_targets.py --instances-file instances.json --cli-region <region>
What ships with it
23 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.
- references/acceptance-criteria.md 5.4 KB
- references/analysis-workflow.md 9.0 KB
- references/cli-installation-guide.md 2.8 KB
- references/ecs-validation-rules.md 3.8 KB
- references/execution-workflow.md 6.3 KB
- references/experiment-template-guide.md 3.9 KB
- references/iam-policies.md 3.7 KB
- references/managed-service-logs.md 8.4 KB
- references/monitoring-guide.md 3.9 KB
- references/verification-method.md 5.7 KB
- scripts/analyze_logs.py 14 KB runs code
- scripts/check_env.sh 3.5 KB runs code
- scripts/collect_ces_metrics.py 15 KB runs code
- scripts/collect_logs.py 27 KB runs code
- scripts/deploy_experiment.sh 5.3 KB runs code
- scripts/discover_ecs.py 7.7 KB runs code
- scripts/execute_experiment.py 19 KB runs code
- scripts/generate_analysis_report.py 10 KB runs code
- scripts/generate_experiment.py 10 KB runs code
- scripts/generate_report.py 7.6 KB runs code
- scripts/monitor_instances.py 10 KB runs code
- scripts/rollback_experiment.py 6.8 KB runs code
- scripts/validate_targets.py 11 KB runs code
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.
- 1mo ago First seen · 312 lines · 209 tokens per session scan A 3e868aeafccb
huawei-cloud-ecs-shutdown-experiment is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 209 tokens to every session and 3,657 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
chaos-engineering-resilience
Chaos engineering principles, controlled failure injection, resilience testing, and system recovery validation. Use when testing distributed systems, building confidence in fault tolerance, or validating disaster recovery.
Advanced Chaos Engineering
Advanced chaos engineering patterns using Chaos Monkey, Litmus, and Gremlin for testing distributed system resilience under failure conditions.
huawei-cloud-apig-instance-management
Manage Huawei Cloud APIG (API Gateway, dedicated instances) via hcloud CLI: instance lifecycle (create/list/delete), API groups, API create/update/delete, publish/offline, request throttling policies, signature keys, access control (ACL) policies, and public ingress EIP binding, plus read-only diagnosis of public…
huawei-cloud-deployment-task-management
Huawei Cloud CloudDeploy (CodeArts Deploy / 部署) management, execution, and failure analysis using the KooCLI hcloud command-line client. Covers deploy application listing and creation, deployment task listing/detail/creation, task start, task deletion, deployment failure root-cause analysis (agent offline, timeout…
cis-aws-compute-3.1
Ensure Amazon ECS task definitions using 'host' network mode do not allow privileged or root user access to the host.