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/HybridAIOne/hybridclawnpx agentmods add skills/hybridaione/hybridclaw/t-cloud-publicWrote 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/hybridaione/hybridclaw/t-cloud-public)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/t-cloud-public"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/t-cloud-public/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/hybridaione/hybridclaw/t-cloud-public"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/t-cloud-public.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 | $0.00029 | $0.02746 |
| Opus 5 | $0.00015 | $0.01373 |
| Sonnet 5 | $0.00006 | $0.00549 |
| Haiku 4.5 | $0.00003 | $0.00275 |
Grade A, and why
t-cloud-public 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 8d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
T Cloud Public
Use this skill for T Cloud Public, formerly Open Telekom Cloud, infrastructure
inventory, deployment-readiness checks, incident summaries, and guarded DevOps
request planning. Invoke it as t-cloud-public. The helper path uses the
current product name; credential names intentionally keep established OTC_*
identifiers because the public API docs, domains, and customer terminology
still use OTC/Open Telekom Cloud names.
Default Workflow
- Start with read-only inventory or
plan. V1 helper operations are read/list/describe only. - Treat
t_cloud_public.cjsas the API wrapper. Do not handcraft OTC API URLs, service endpoints, signing metadata, request tiers, or SecretRefs from memory. - For prompt/user testing, stop after
planor helperhttp-requestpayload generation. Do not call helperrunor the built-inhttp_requesttool. - For real user requests that need live OTC data, use helper
run. The helper constructs an allowlisted request and sends it through the HybridClaw gatewayhttp_requestroute. For IaaS/API inventory, the gateway resolvesOTC_ACCESS_KEY_ID,OTC_SECRET_ACCESS_KEY, optionalOTC_SECURITY_TOKEN, andOTC_PROJECT_ID, then signs the request server-side. - Use
http-requestonly to inspect the generated gateway payload or when the active runtime cannot give the helper gateway access. - If a live helper
runorhttp_requestcall returns 401, 403, or a signature/authentication failure, stop after that first failed call. Do not retry or fan out to more OTC endpoints. Ask the operator to verify credentials, project ID, region, IAM permissions, and clock skew. - If a live call returns 429, stop fan-out and report retry guidance from
Retry-Afteror rate-limit response headers when present. - For account billing, current spend, charges, and consumption, use the
documented Enterprise Dashboard API v2 through helper operations
billing-daily-consumptionandbilling-hourly-consumption. These calls usehttps://api-enterprise-dashboard.otc-service.com/, bearer secretOTC_ENTERPRISE_DASHBOARD_TOKEN, and NDJSON responses from/v2/daily/consumption/or/v2/hourly/consumption/. - Mutating actions are outside v1 execution. For create/delete/reboot, network/security group, volume/backup restore, DNS/load-balancer, IAM/KMS, database, or container mutations, produce a plan with exact region, project, resource IDs, intended action, rollback, blast radius, and the required F8/F14 operator approval text. Do not execute the mutation.
- Never paste, print, inspect, or ask for OTC signing material, passwords, API tokens, AK/SK pairs, project IDs stored as secrets, or session tokens.
- Treat region as plain configuration. Pass
--region eu-deexplicitly or setOTC_REGION=eu-dein the helper environment; do not store region in the encrypted secret store.
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.
- 8d ago First seen · 254 lines · 29 tokens per session scan A e61a19721649
t-cloud-public is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,746 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
remote-compute-modal
Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
managed-model-endpoints
Register a model service in the managed family — a local model server container the daemon starts/stops on demand, or a remote upstream model API (https). Read the runbook, allocate a port (local only), compose idempotent start/stop scripts (local only), register once. Load when the user wants a model service…
aws-bedrock
AWS Bedrock — fully managed foundation models on AWS infrastructure. Use when deploying AI in AWS-native environments, needing enterprise compliance (SOC2, HIPAA), running Claude, Llama, Titan, or Mistral on AWS, leveraging Knowledge Bases for RAG, or applying Guardrails for content safety.
cloudflare-vectorize
Serverless vector database at the edge with Cloudflare Vectorize. Use when: building semantic search on Cloudflare Workers, RAG pipelines at the edge, low-latency vector similarity search, or storing and querying embeddings without managing a separate vector database.
cloudflare-ai
You are an expert in Cloudflare Workers AI, the serverless AI inference platform running on Cloudflare's global network. You help developers run LLMs, embedding models, image generation, speech-to-text, and translation models at the edge with zero cold starts, pay-per-use pricing, and integration with Workers, Pages…