agentmods.dev

tailscale-compute-fleet

tailscale-compute-fleet is a skill for Claude Code, Codex from dylantirandaz/tailscale-compute-mcp. It costs 29 tokens per session (1,069 once invoked), scanned A, original, MIT.

Instructions for choosing Tailscale-connected computers for separate jobs and running a declared workflow across multiple nodes.

In plain words
What is it for?
Use it when two or more compute servers are available and jobs need explicit node selection. It can reject unsuitable or busy nodes instead of silently changing the requested setup.
Why use it?
It prevents unclear or unsafe scheduling by checking each computer’s availability, platform, memory, accelerator, and required tools before placement.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo 27d ago A scan 29 tokens original MIT

Good fit Use it when two or more compute servers are available and jobs need explicit node selection. It can reject unsuitable or busy nodes instead of silently changing the requested setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dylantirandaz/tailscale-compute-mcp/tailscale-compute-fleet
View source ↗ dylantirandaz/tailscale-compute-mcp
Install

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.

Any agent
npx skills add dylantirandaz/tailscale-compute-mcp --skill tailscale-compute-fleet
Clone the repo
git clone --depth 1 https://github.com/dylantirandaz/tailscale-compute-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tailscale-compute-fleet

README.md
[![agentmods](https://agentmods.dev/badge/skills/dylantirandaz/tailscale-compute-mcp/tailscale-compute-fleet/github.svg)](https://agentmods.dev/skills/dylantirandaz/tailscale-compute-mcp/tailscale-compute-fleet)
Your own site
<a href="https://agentmods.dev/skills/dylantirandaz/tailscale-compute-mcp/tailscale-compute-fleet"><img src="https://agentmods.dev/badge/skills/dylantirandaz/tailscale-compute-mcp/tailscale-compute-fleet/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.

agentmods 80×15 button for tailscale-compute-fleet

Your own site · 80×15
<a href="https://agentmods.dev/skills/dylantirandaz/tailscale-compute-mcp/tailscale-compute-fleet"><img src="https://agentmods.dev/badge/skills/dylantirandaz/tailscale-compute-mcp/tailscale-compute-fleet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.01069
Opus 5 $0.00015 $0.00535
Sonnet 5 $0.00006 $0.00214
Haiku 4.5 $0.00003 $0.00107

Measured 11d ago against content hash e41bf9114afd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tailscale-compute-fleet 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 11d 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.

skills/tailscale-compute-fleet/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tailscale Compute Fleet

Use this skill when two or more MCP servers expose Tailscale Compute tools. Each MCP server controls one node. The MCP server does not pool CPU, GPU, or memory. It does not make a command distributed.

Invariants

  • Keep one named MCP server for each node.
  • An explicit user target overrides each placement rule.
  • Refuse a node that does not meet the platform, architecture, memory, accelerator, or toolchain requirements of the command.
  • Never replace a requested accelerator with a CPU or another backend.
  • Never use a hidden queue. Return a node-busy result or select a different eligible node explicitly.
  • Use the distributed runtime that the repository declares. Do not install or infer a runtime only to distribute a command.
  • Do not claim that memory or accelerator resources are combined across Macs.
  • Keep the control connection on the Tailscale address. Use a Thunderbolt data path only when the project supplies or requests a valid runtime host file.

Independent job placement

  1. Identify each available MCP server that exposes compute_status and compute_job_start.
  2. Call compute_status on each node. Reject unavailable nodes and nodes with incompatible hardware or operating systems.
  3. Call compute_job_list for active states when current durable-job load is not available.
  4. Build the task dependency graph. Send only independent tasks to different nodes at the same time.
  5. Select the eligible node with the lowest active-job count. Then use the lowest reported load. Use the MCP server name as the stable final tie-breaker.
  6. Start each task with a stable idempotencyKey, a workflow label, and each required artifactPath.
  7. Record the selected MCP server name and returned job ID. Poll, cancel, delete, and fetch through that same server.
  8. Fetch immutable artifacts by job ID. Check each fetched SHA-256 value against the terminal receipt before a dependent task uses the files.

Do not move an active durable job between nodes. A retry must use the same MCP server and the same request data. This lets idempotency return the first job.

Read the full file on GitHub · 102 lines

Changes

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.

  1. 11d ago First seen · 102 lines · 29 tokens per session scan A e41bf9114afd

Subscribe to this mod's changes

tailscale-compute-fleet is a skill published in the GitHub repository dylantirandaz/tailscale-compute-mcp (1 stars, last pushed 27d ago), licensed MIT. It adds 29 tokens to every session and 1,069 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 2026-08-31.

CloudDevOps and cloud
Related

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…

google/skills · 83 tokens

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 disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

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".

microsoft/skills · 78 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

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…

Jeffallan/claude-skills · 71 tokens