repo-remote

repo-remote is a skill for Claude Code, Codex from rjwalters/kicad-tools. It costs 26 tokens per session (30,206 once invoked), scanned F, original, MIT.

A tool that starts or reuses a cloud virtual machine on Google Cloud or AWS with the current repository cloned and synchronised, then opens an SSH session. SSH is a secure command-line connection to a remote computer.

In plain words
What is it for?
Use it to launch a remote development session, configure cloud credentials and repository settings, or check the remote machine status.
Why use it?
It gives developers a ready remote copy of the repository without manually provisioning a machine and connecting to it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

Good fit Use it to launch a remote development session, configure cloud credentials and repository settings, or check the remote machine status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rjwalters/kicad-tools/repo-remote
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 rjwalters/kicad-tools --skill repo-remote
Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools

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 repo-remote

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-remote/github.svg)](https://agentmods.dev/skills/rjwalters/kicad-tools/repo-remote)
Your own site
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-remote"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-remote/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 repo-remote

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-remote"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-remote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 30,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan F 5 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 $0.00026 $0.30206
Opus 5.5 $0.00010 $0.12082
Sonnet 5.5 $0.00005 $0.06041
Haiku 4.5 $0.00003 $0.03021

Measured 5d ago against content hash 705936f6b6a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade F, and why

repo-remote scanned grade F with 5 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

passwordless-sudo drop-in is installed.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

REPO_REMOTE_SSH_KEY=~/.ssh/id_ed25519 # key used for the SSH session (fine to share)

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

path, offer to install it (`curl -fsSL https://claude.ai/install.sh | bash`).

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

`169.254.169.254`) will fail or time out. The dev container gets what it needs

Makes network callslowCapability

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

Hygiene: the client ID is the only value placed in `curl`'s arguments. The
.agents/skills/repo-remote/SKILL.md · 1,987 lines

How it starts

The opening of the file, as written. The whole thing — 1,987 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex form of the /repo:remote command. Other commands appear as $repo-<verb> skills. Helper scripts and .claude/ paths below are relative to the repository root and exist when the Claude Code surface is installed alongside this one.

$repo-remote — Remote Dev Session

Stand up (or reuse) a cloud VM with this repository cloned and synced, then open a live SSH session in a new terminal window — landing in the repo, ready to run claude and continue the work on the remote host.

Configuration is read from two layers (see below): shared cloud credentials from ~/.config/repo/remote.env (reused across every repo), with the target repo's .env layered on top for per-repo machine settings — and free to override any shared value. The provisioning credentials are used locally to drive the cloud CLI; they are never copied to the VM.

Usage

$repo-remote                   # Read .env, bring up / reuse the host, open SSH
$repo-remote --configure       # Guided setup: shared creds (~/.config/repo/remote.env) + repo .env (machine)
$repo-remote gcp               # Override REPO_REMOTE_PROVIDER for this run
$repo-remote aws
$repo-remote --status          # List instances created by this command
$repo-remote --verify          # Prove the SSH alias still reaches THIS repo's instance
$repo-remote --attach          # Reconnect: verify the host, then open a session with a FRESH GitHub credential
$repo-remote --down            # Stop instances created by this command
$repo-remote --down --delete   # Terminate/delete them

First time in a repo? Run $repo-remote --configure to build the .env below, then $repo-remote to launch.

The provisioning contract below is implemented once, as an executable script — scripts/repo/repo-remote.sh, installed to .claude/skills/repo/scripts/repo-remote.sh. The interactive flow here is a thin wrapper: it runs the wizard/cost-confirmation UX, and once you say yes it calls that script rather than re-issuing aws/gcloud calls from prose. The same script is the headless entry point a non-interactive caller (e.g. loom's fleet add-worker) invokes directly:

Read the full file on GitHub · 1,987 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. 5d ago Changed · +14 lines 705936f6b6a3
  2. 8d ago First seen · 1,973 lines · 26 tokens per session scan F 3b9f37575c7d

Subscribe to this mod's changes

repo-remote is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 30,206 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it F with 5 findings (asks for root, reaches for credential files, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.

Related

repo-remote compared with skills from other repositories

repo-remote next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-remoterjwalters/kicad-toolsSkill73yesterdayMITF26Claude Code, Codex
gke-compute-classesgoogle/skillsSkill24ktodayApache-2.0A83Claude Code, Codex
gke-workload-securitygoogle/skillsSkill24ktodayApache-2.0A171Claude Code, Codex
gke-reliabilitygoogle/skillsSkill24ktodayApache-2.0A85Claude Code, Codex
cloud-architectJeffallan/claude-skillsSkill12k10d agoMITA71Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9k2d agoApache-2.0A30Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2k3d agoMITA78Claude Code