remote-claude-session

remote-claude-session is a skill for Claude Code, Codex from sfc-gh-eraigosa/dotfiles. It costs 125 tokens per session (1,911 once invoked), scanned B, original, Apache-2.0.

A workflow for starting or connecting to a persistent Claude remote-control session on a remote computer over SSH, inside a Git repository.

In plain words
What is it for?
Use it to start, restart, or attach to Claude sessions on configured SSH hosts, choosing the remote repository and a purpose-based session name.
Why use it?
It keeps the AI session running in a named tmux session, so disconnecting from the remote computer does not end the work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Good fit Use it to start, restart, or attach to Claude sessions on configured SSH hosts, choosing the remote repository and a purpose-based session name.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sfc-gh-eraigosa/dotfiles/remote-claude-session
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 sfc-gh-eraigosa/dotfiles --skill remote-claude-session
Clone the repo
git clone --depth 1 https://github.com/sfc-gh-eraigosa/dotfiles

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 remote-claude-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/remote-claude-session/github.svg)](https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/remote-claude-session)
Your own site
<a href="https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/remote-claude-session"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/remote-claude-session/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 remote-claude-session

Your own site · 80×15
<a href="https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/remote-claude-session"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/remote-claude-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,911 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 107
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Privilege Escalation · line 55
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Agent Snooping · line 140
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00125 $0.01911
Opus 5 $0.00063 $0.00955
Sonnet 5 $0.00025 $0.00382
Haiku 4.5 $0.00013 $0.00191

Measured 10d ago against content hash 86eca4088cac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

remote-claude-session scanned grade B 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 10d 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.

- **tmux missing** → stop; tell the user to run `sudo apt install tmux` on the remote.
ai/skills/remote-claude-session/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remote Claude Session

Sets up a named tmux session on a remote SSH host with claude --remote-control running inside a specified git repository, so the session survives disconnects and can be attached or controlled at any time.

Future path: tmux-mgr remote start <alias> --repo <path> will wrap this workflow once the remote subcommand lands in tmux-mgr. Until then follow the steps below directly.

Inputs

Collect these from the user's message, conversation context, or by asking:

Input Default Notes
SSH_ALIAS (required) Must match a Host entry in ~/.ssh/config
REPO_PATH auto-detect Path to the repo on the remote host. If not given, probe ~/git/<repo-name> then ~/github/<repo-name> on the remote — both layouts exist across this user's hosts.
SESSION_NAME claude-<purpose> (e.g. claude-dns) tmux session name on the remote. Prefer a purpose-based name over the generic claude-remote — derive <purpose> from what the user is starting the session for.
RC_NAME <SSH_ALIAS>-<SESSION_NAME> (e.g. <host>-claude-dns) Display name for the Remote Control session (the /rc list). Passing it makes the session self-identifying by host and purpose — so you never end up staring at an auto-generated placeholder (e.g. <host>-linear-fiddle) and having to guess which box/task it is. Must be shell-safe (no spaces).

If REPO_PATH is not specified, derive <repo-name> from the basename of the active local repo (or ask). The actual path on the remote is then resolved in step 2.

Steps

1. Validate the SSH alias

ssh -G <SSH_ALIAS> 2>/dev/null | grep -E "^(hostname|user) "

Stop and report the error if the alias is not found in ~/.ssh/config.

2. Check the remote (tmux, Claude + version, and REPO_PATH)

# tmux + Claude detection
ssh <SSH_ALIAS> "command -v tmux 2>/dev/null && \
  (command -v claude 2>/dev/null || \
   find ~/.nvm/versions/node/*/bin -name claude 2>/dev/null | sort -V | tail -1)"

# Claude version probe (use the claude path found above; nvm prefix if needed)
ssh <SSH_ALIAS> "<NVM_PREFIX>claude --version"

# REPO_PATH probe (skip if an explicit path was supplied)
ssh <SSH_ALIAS> "for d in ~/git/<repo-name> ~/github/<repo-name>; do \
  [ -d \"\$d/.git\" ] && echo \"\$d\" && break; done"

Read the full file on GitHub · 143 lines

Files

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.

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. 10d ago First seen · 143 lines · 125 tokens per session scan B 86eca4088cac

Subscribe to this mod's changes

remote-claude-session is a skill published in the GitHub repository sfc-gh-eraigosa/dotfiles (46 stars, last pushed today), licensed Apache-2.0. It adds 125 tokens to every session and 1,911 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories