Run commands on a REMOTE server through a persistent shell that survives disconnects, by driving a tmux session that lives ON THE REMOTE.

Custom licenceAuto-check: warnings

Install Rsess

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add JCLiuGroup/AI-Computational-Chemist --skill rsess -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JCLiuGroup/AI-Computational-Chemist rsess --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JCLiuGroup/AI-Computational-Chemist.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tools/rsess .claude/skills/rsess && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
rsess
GitHub stars
145
Token cost
~570 tokens
SKILL.md length
237 words
Files
8 (incl. scripts, references)
Skills in repo
21
Repo updated
First seen
Licence
Custom licence

At a glance

Run commands on a REMOTE server through a persistent shell that survives disconnects, by driving a tmux session that lives ON THE REMOTE.

  • Works in 4 steps: Confirm the explicit remote target, then… → Open one topic session and retain the… → Use run for commands, peek for the live… → …
  • You need shell state (cwd
  • SKILL.md covers Required inputs, Route map, Workflow and Hard guardrails
  • Activated venvs

What it does

Rsess is an agent skill from JCLiuGroup/AI-Computational-Chemist. Run commands on a REMOTE server through a persistent shell that survives disconnects, by driving a tmux session that lives ON THE REMOTE. Use when you need shell state (cwd, env vars, activated venvs, a running REPL/daemon) to persist across multiple commands on an SSH-reachable host — instead of ssh host cmd, which starts a fresh shell every time and loses all state. Do NOT use rsess when the agent is already running on the target machine — run commands directly with the native shell.

Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/errors.md`, `references/resources.md` and `references/running.md`).

It works with tmux.

When your agent uses it

  • You need shell state (cwd
  • Activated venvs
  • A running REPL/daemon) to persist across multiple commands on an SSH-reachable host — instead of ssh host cmd
  • Which starts a fresh shell every time and loses all state

Example prompts

  • “/rsess”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the explicit remote target, then run the probe and validation in
  2. Open one topic session and retain the exact printed session name.
  3. Use run for commands, peek for the live pane, and the configured scp/rsync route
  4. Close the session deliberately; use recovery guidance rather than recreating a

What it can do on your machine

Read from SKILL.md and the folder at commit e27b555. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Rsess loads about 570 tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 125 tokens; SKILL.md has 237 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~570
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:14
    SSH-reachable host (`Host` alias from `~/.ssh/config`, or `user@host`).

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 237 words (~570 tokens).

“Use rsess only to drive a remote tmux-backed shell whose state must persist across SSH calls and disconnects. If the agent already runs on the target, use the native shell instead.”

— opening of SKILL.md by JCLiuGroup, Custom licence
name
rsess

Read the full SKILL.md on GitHub

Files

SKILL.md and 7 other files (scripts, references) in tools/rsess of JCLiuGroup/AI-Computational-Chemist.

  • SKILL.md
  • config.example
  • references/errors.md
  • references/resources.md
  • references/running.md
  • references/validation.md
  • scripts/rsess
  • scripts/tmux

Open the folder on GitHubat commit e27b555

Compare with similar skills

Rsess next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Rsess compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rsess this skillJCLiuGroup/AI-Computational-Chemist145—~570Automated safety check: WarnCustom licence
Codex Plugin QAcode-yeongyu/oh-my-openagent70k1 repos~1.9kAutomated safety check: PassCustom licence
Tmuxopenclaw/openclaw392k2 repos~640Automated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.8k15 repos~656Automated safety check: PassApache-2.0
CodeGraph Agent Evalcolbymchenry/codegraph73k—~950Automated safety check: PassMIT
Tmuxtrpc-group/trpc-agent-go1.8k24 repos~868Automated safety check: PassApache-2.0

Similar skills

  • Codex Plugin QA

    code-yeongyu/oh-my-openagent

    Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.

    70k GitHub starsUsed in 1 repo~1.9k tokens
    Testing & QAAuto-check passed
  • Tmux

    openclaw/openclaw

    Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.

    392k GitHub starsUsed in 2 repos~640 tokens
    Auto-check passed
  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.8k GitHub starsUsed in 15 repos~656 tokens
    AI & LLM EngineeringAuto-check passed
  • CodeGraph Agent Eval

    colbymchenry/codegraph

    Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.

    73k GitHub stars~950 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Tmux

    trpc-group/trpc-agent-go

    Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

    1.8k GitHub starsUsed in 24 repos~868 tokens
    Data & AnalyticsAuto-check passed
  • CodexBar Live QA

    steipete/CodexBar

    Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.

    22k GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check passed

More from JCLiuGroup/AI-Computational-Chemist

All 21 skills in this repo
  • Research Orchestrator

    JCLiuGroup/AI-Computational-Chemist

    Define and maintain machine-readable research project state for multi-stage computational chemistry work.

    145 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Comp Chem Workflow

    JCLiuGroup/AI-Computational-Chemist

    Entry point and controller for computational chemistry and materials workflows.

    145 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Cp2k

    JCLiuGroup/AI-Computational-Chemist

    Prepare, validate, run, and troubleshoot CP2K calculations for periodic and large molecular systems.

    145 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Deepmd

    JCLiuGroup/AI-Computational-Chemist

    DeePMD-kit and Deep Potential Molecular Dynamics workflows. An agent skill from JCLiuGroup/AI-Computational-Chemist.

    145 GitHub starsUsed in 1 repo~780 tokens
    Auto-check passed
  • Gaussian

    JCLiuGroup/AI-Computational-Chemist

    Prepare, validate, and troubleshoot Gaussian molecular quantum chemistry jobs.

    145 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Gromacs

    JCLiuGroup/AI-Computational-Chemist

    Prepare, validate, run, resume, troubleshoot, and analyze GROMACS molecular dynamics.

    145 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

Works with

Questions about Rsess

What does Rsess do?

Run commands on a REMOTE server through a persistent shell that survives disconnects, by driving a tmux session that lives ON THE REMOTE. Rsess is an agent skill from JCLiuGroup/AI-Computational-Chemist. Run commands on a REMOTE server through a persistent shell that survives disconnects, by driving a tmux session that lives ON THE REMOTE.

When should I use Rsess?

Rsess fits situations like: you need shell state (cwd; activated venvs; A running REPL/daemon) to persist across multiple commands on an SSH-reachable host — instead of ssh host cmd; which starts a fresh shell every time and loses all state.

How do I install Rsess in Claude Code?

Run `npx skills add JCLiuGroup/AI-Computational-Chemist --skill rsess -a claude-code`. Or copy the skill folder (tools/rsess in JCLiuGroup/AI-Computational-Chemist) into .claude/skills/rsess in your project. Claude Code loads it when a task matches its description.

How do I install Rsess in Codex?

Run `npx skills add JCLiuGroup/AI-Computational-Chemist --skill rsess -a codex`. Or copy the skill folder (tools/rsess in JCLiuGroup/AI-Computational-Chemist) into .agents/skills/rsess in your project. Codex loads it when a task matches its description.

Can I use Rsess in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JCLiuGroup/AI-Computational-Chemist --skill rsess -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rsess, .gemini/skills/rsess, .github/skills/rsess and .opencode/skills/rsess in your project.

What does Rsess need to run?

SKILL.md names no scripts, command-line tools or credentials: Rsess is instructions for the agent only.

Does Rsess access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Rsess safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Rsess use?

Rsess has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Rsess use?

About 570 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Rsess?

Skills that share tags, products or a category with Rsess: Codex Plugin QA (code-yeongyu/oh-my-openagent, 70k stars), Tmux (openclaw/openclaw, 392k stars), 1password (trpc-group/trpc-agent-go, 1.8k stars) and CodeGraph Agent Eval (colbymchenry/codegraph, 73k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rsess?

JCLiuGroup (a GitHub organization) maintains it in JCLiuGroup/AI-Computational-Chemist, which has 145 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 27, 2026.

Source: JCLiuGroup/AI-Computational-Chemist on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.