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 agentmods add skills/qwencloud/qwencloud-deploy/skillnpx skills add QwenCloud/qwencloud-deploy --skill skillgit clone --depth 1 https://github.com/QwenCloud/qwencloud-deployWhat 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 | $0.00176 | $0.01588 |
| Opus 5 | $0.00088 | $0.00794 |
| Sonnet 5 | $0.00035 | $0.00318 |
| Haiku 4.5 | $0.00018 | $0.00159 |
Grade C, and why
qwencloud-deploy scanned grade C with 1 finding 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 2d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
| Auth | OAuth (recommended) or AK/SK; never collect credentials via chat | How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qwen Cloud Deploy
Quick Path
- Route the task — Match to one of 4 modes: Full-Stack Deploy · Hot Update · Delete · HTTPS Setup.
- Deploy (default) — Execute steps 1→13 in order; each step has a reference doc.
- Confirm cost before creating anything — Show hourly price in USD, get user confirmation.
- Record state — On success write
.qwencloud-deploy.
Scope
| In Scope | Out of Scope |
|---|---|
| Local project / Git → Alibaba Cloud International | China site → use qianwenai-deploy |
| Full-stack ROS, hot update, cleanup | AWS/GCP/Azure/other clouds |
| ECS + optional RDS + OSS + public IP | K8s/Serverless/container orchestration |
| OAuth/AK auth (no credential collection) | — |
Assumptions
aliyunCLI 3.x installed; when no valid credential, followreference/deploy/01_env_check.md.- Default region
ap-southeast-1(Singapore).
Task Routing
| Signal | Mode |
|---|---|
.qwencloud-deploy exists + user says "update" |
Hot Update |
.qwencloud-deploy exists + "delete"/"cleanup" |
Delete |
| "bind domain"/"HTTPS"/"SSL" (deployment exists) | HTTPS Setup |
| Git URL or local project (no existing deployment) | Full-Stack Deploy |
On trigger, display welcome message first (see reference/rules/rule_interaction.md).
Full-Stack Deploy (Steps 1–13)
Phase 1 · Preparation
| Step | Action | Reference |
|---|---|---|
| 1 | Environment check | reference/deploy/01_env_check.md |
| 2 | Git clone (if Git URL) | reference/deploy/02_git_clone.md |
| 3 | Project analysis | reference/deploy/03_analyze_project.md |
Phase 2 · Resource Planning
| Step | Action | Reference |
|---|---|---|
| 4 | Existing deployment scan | reference/deploy/04_check_existing.md |
| 5 | Database identification | reference/deploy/05_database.md |
| 6 | ECS instance type selection | reference/deploy/06_instance_type.md |
| 7 | Generate ROS template | reference/deploy/07_generate_template.md |
| 8 | Stock check | reference/deploy/08_check_stock.md |
| 9 | Template validation + cost estimate | reference/deploy/09_estimate_cost.md |
What ships with it
34 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.
- reference/cleanup/delete_stack.md 2.5 KB
- reference/deploy/01_env_check.md 3.3 KB
- reference/deploy/02_git_clone.md 1.3 KB
- reference/deploy/03_analyze_project.md 8.1 KB
- reference/deploy/04_check_existing.md 1.9 KB
- reference/deploy/05_database.md 1.2 KB
- reference/deploy/06_instance_type.md 941 B
- reference/deploy/07_generate_template.md 4.1 KB
- reference/deploy/08_check_stock.md 1.4 KB
- reference/deploy/09_estimate_cost.md 1.9 KB
- reference/deploy/10_upload_artifacts.md 3.1 KB
- reference/deploy/11_create_stack.md 3.5 KB
- reference/deploy/12_wait_stack.md 4.6 KB
- reference/deploy/13_record_state.md 4.3 KB
- reference/hotfix/update_app.md 3.1 KB
- reference/hotfix/update_recipe.md 5.6 KB
- reference/https/https_setup.md 15 KB
- reference/rules/rule_error_handling.md 6.9 KB
- reference/rules/rule_interaction.md 14 KB
- scripts/create_stack.sh 5.2 KB runs code
- scripts/delete_stack.sh 6.6 KB runs code
- scripts/generate_template.py 8.9 KB runs code
- scripts/record_state.py 6.5 KB runs code
- scripts/setup_domain.sh 24 KB runs code
- scripts/update_app.sh 19 KB runs code
- scripts/upload_artifacts.py 9.6 KB runs code
- scripts/wait_and_probe.py 12 KB runs code
- templates/ros_single_rds.yaml 7.5 KB
- templates/ros_single.yaml 4.1 KB
- templates/userdata/docker.sh 3.5 KB runs code
- templates/userdata/nginx_proxy.sh 1.6 KB runs code
- templates/userdata/nginx_static_proxy.sh 2.3 KB runs code
- templates/userdata/nginx_static.sh 1.8 KB runs code
- templates/userdata/systemd.sh 5.9 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.
- 2d ago First seen · 175 lines · 176 tokens per session scan C 9a1b8f1aeab2
qwencloud-deploy is a skill published in the GitHub repository QwenCloud/qwencloud-deploy (3 stars, last pushed 28d ago), licensed Apache-2.0. It adds 176 tokens to every session and 1,588 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
kagent-dev
Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.
timoni
Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.
azmon-mirroredcatalogs-operations-cli
Brings Azure Monitor, Application Insights, and Log Analytics telemetry into Fabric as Eventhouse external delta tables and correlates it with business data. Use to onboard observability data, judge whether latency or availability affected revenue, or build a Real-Time dashboard and Operations Agent over it.
durable-objects
Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases…
ship-web-games
Package, deploy, and verify a playable Three.js or web game. Use for release builds, asset delivery, private/public deployment, production smoke tests, browser proof, release notes, rollback readiness, and cleanup of temporary QA resources.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…