setup-remote-project

setup-remote-project is a skill for Claude Code, Codex from matteblack9/coding-agent-fabric. It costs 28 tokens per session (898 once invoked), scanned A, original, MIT.

A setup workflow for placing a listener on another computer or Kubernetes environment so an orchestrator can run a project there.

In plain words
What is it for?
Use it to deploy and register a remote workspace, verify the required coding-agent runtime, and preserve the remote project's existing instructions.
Why use it?
It handles the checks and registration needed when the project files and runtime are remote. This avoids trying to run the project on the wrong machine or with an unavailable agent tool.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/matteblack9/coding-agent-fabric/setup-remote-project
Any agent
npx skills add matteblack9/coding-agent-fabric --skill setup-remote-project
Clone the repo
git clone --depth 1 https://github.com/matteblack9/coding-agent-fabric

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 setup-remote-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteblack9/coding-agent-fabric/setup-remote-project.svg)](https://agentmods.dev/skills/matteblack9/coding-agent-fabric/setup-remote-project)
Your own site
<a href="https://agentmods.dev/skills/matteblack9/coding-agent-fabric/setup-remote-project"><img src="https://agentmods.dev/badge/skills/matteblack9/coding-agent-fabric/setup-remote-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00028 $0.00898
Opus 5 $0.00014 $0.00449
Sonnet 5 $0.00006 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 3d ago against content hash b93f8521ac3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-remote-project scanned grade A 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://$HOST:$LISTENER_PORT/health
skills/setup-remote-project/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

setup-remote-project

When To Use

  • The user wants the orchestrator to execute a project or workspace on a different host
  • Remote runtime binaries and project files already live on the target machine
  • A listener must be deployed and registered in remote_workspaces

The listener runs on the remote machine itself. Claude uses the Python SDK there, while Cursor/Codex/OpenCode use their own CLIs there.

Runtime Adaptation

  • claude Verify claude-agent-sdk is importable on the remote host before deployment.
  • cursor Verify cursor-agent exists on the remote host and the remote machine is authenticated in Cursor.
  • codex Verify codex exists on the remote host and works non-interactively.
  • opencode Verify opencode exists, provider login is complete, and any project-local .opencode/ config is already on the remote machine.

Rules

  • Never deploy a remote listener silently; confirm the target first
  • Present detected values as numbered choices whenever possible
  • Use one listener per remote workspace; the same host can run multiple listeners on different ports
  • Preserve existing runtime guidance on the remote project: AGENTS.md, CLAUDE.md, .claude/, .cursor/rules, .cursorrules, opencode.json, .opencode/
  • The listener must remain running after setup; nohup is acceptable, but a service manager is better

Procedure

1. Local Preflight

Verify:

  • orchestrator.yaml exists
  • orchestrator/remote/deploy.py and orchestrator/remote/listener.py exist
  • at least one remote access path is available: ssh or kubectl
  • current remote_workspaces entries are reviewed to avoid duplicate host/port conflicts

If orchestrator.yaml is missing, stop and run the setup-orchestrator skill first.

2. Collect Connection Details

Gather:

  • workspace_name in project/workspace format
  • remote access method: ssh or kubectl
  • host, user, key file for SSH
  • namespace, pod, container, kubeconfig for kubectl

Run an immediate connectivity test after collecting the transport details.

Read the full file on GitHub · 128 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. 3d ago First seen · 128 lines · 28 tokens per session scan A b93f8521ac3f

Subscribe to this mod's changes

setup-remote-project is a skill published in the GitHub repository matteblack9/coding-agent-fabric (2 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 898 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

cloud-sync

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.

thedotmack/claude-mem · 64 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

yandex-cloud

Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.

Tracer-Cloud/opensre · 71 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

rule

Skill "rule" from x-cmd/x-cmd, covering rule — rules to rule, 核心命令, 规则文件格式, 示例 and 验证规则文件格式.

x-cmd/x-cmd · 0 tokens

cve

Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.

x-cmd/x-cmd · 49 tokens