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/peteromallet/Arnoldnpx agentmods add skills/peteromallet/arnold/cloudWrote 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/peteromallet/arnold/cloud)<a href="https://agentmods.dev/skills/peteromallet/arnold/cloud"><img src="https://agentmods.dev/badge/skills/peteromallet/arnold/cloud/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/peteromallet/arnold/cloud"><img src="https://agentmods.dev/badge/skills/peteromallet/arnold/cloud.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 | $0.00105 | $0.07517 |
| Opus 5.5 | $0.00042 | $0.03007 |
| Sonnet 5.5 | $0.00021 | $0.01503 |
| Haiku 4.5 | $0.00011 | $0.00752 |
Grade D, and why
megaplan-cloud scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- The entrypoint writes `preferred_auth_method = "chatgpt"` (and `forced_login_method = "chatgpt"`) into `~/.codex/config.toml`, so codex uses the ChatGPT-subscription endpoint (`chatgpt.com/backend-api/codex`) **even wh Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
10. **Stalled `chain_state` makes a relaunch resume a dead plan (session alive, milestone stuck at "none").** An aborted run leaves `.megaplan/plans/.chains/<spec>-<digest>.json` with `last_state: "stalled"`; the next `c How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authority status (M11): Zero-authority history. All cloud deployment and repair authority has been migrated to canonical delegation. This skill is retained as non-runnable reference — it must not be used to materialize commands or grant deployment/repair authority.
Megaplan Cloud
megaplan cloud runs a plan inside a provider-managed container with a persistent workspace volume, so the run survives the user's terminal session. For this environment, use provider: ssh against the Hetzner agentbox. Do not launch Megaplan work on other cloud providers unless the user explicitly asks for legacy-provider debugging. local is scaffolded; the ssh provider is the working path. See SSH provider — Hetzner agentbox below.
Reach for cloud mode when at least one of these is true:
- The plan is long-running and would outlast a local terminal session.
- The work spans multiple repos that all need to be mounted side-by-side (
extra_repos:). - The user wants an isolated persistent sandbox separate from their laptop.
- A chain needs to keep running while the laptop is asleep or on the move.
Skip cloud mode when the plan finishes in a sitting, the work fits in one repo, and a local megaplan run would do the same job.
SSH provider — Hetzner agentbox (the working on-prem path)
provider: ssh targets a remote box (host/user/port/identity_file in cloud.yaml under ssh:) that runs the megaplan worker in a docker container. The working on-prem setup is a Hetzner VM with a long-lived megaplan-cloud-agent container + a persistent /workspace volume; an arnold-watchdog (tmux session watchdog) keeps chains alive and a meta-loop supervises it (see docs/hetzner-watchdog-meta-loop.md).
A minimal ssh cloud.yaml:
provider: ssh
repo:
url: https://github.com/org/repo.git
branch: <base-branch>
workspace: /workspace/<unique-per-chain> # unique — the box runs concurrent chains
mode: chain
chain_session: <unique-per-chain> # unique tmux session on the box
chain:
spec: /workspace/<unique-per-chain>/<path-to-chain.yaml>
megaplan:
ref: main
codex_auth: chatgpt # any codex phases bill to ChatGPT subscription
ssh:
host: <box-ip>
user: root
port: 22
remote_dir: /opt/megaplan-cloud/deploy
workspace_dir: /opt/megaplan-cloud/workspace
container: megaplan-cloud-agent
secrets: [] # leave empty if pre-set on the box; listing would overwrite box values with local env
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 · 362 lines · 105 tokens per session scan D cf762b78b192
megaplan-cloud is a skill published in the GitHub repository peteromallet/Arnold (98 stars, last pushed yesterday), licensed Apache-2.0. It adds 105 tokens to every session and 7,517 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".