remote-agents

remote-agents is a skill for Claude Code, Codex from JairoTorregrosa/jaiskills. It costs 120 tokens per session (1,596 once invoked), scanned B, original, MIT.

A skill for starting and monitoring headless Claude Code or Codex agents on a remote computer over SSH, a protocol for securely running commands on another machine.

In plain words
What is it for?
Use it to launch remote coding agents, check their status, gather their output, and combine the results.
Why use it?
It allows work to run on the remote machine's files and hardware while the local agent coordinates the jobs and collects their results.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also runs codex exec. Also seen: mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the jaiskills plugin — 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to launch remote coding agents, check their status, gather their output, and combine the results.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add JairoTorregrosa/jaiskills
Claude Code
/plugin install jaiskills

Made for: Claude Code, Codex.

Or install jaiskills, the plugin that ships this one along with the rest of its 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server.

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-agents

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/remote-agents"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/remote-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,596 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.
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 $0.00120 $0.01596
Opus 5 $0.00060 $0.00798
Sonnet 5 $0.00024 $0.00319
Haiku 4.5 $0.00012 $0.00160

Measured 11d ago against content hash ff790b270bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

remote-agents 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 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- **Permissions default.** Jobs run with permissions bypassed (it's Jairo's own Jetson). Use `--safe` when the task only edits files and shouldn't run arbitrary commands.
skills/orchestration/remote-agents/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the orchestrator on macOS. Workers are headless claude -p / codex exec processes on a remote SSH host (default jetson; Tailscale fallback jetson-ts). Both CLIs are already logged in on the remote. You never implement remotely yourself — you spawn jobs, poll, collect results, and synthesize.

Engines and roles (harness-agnostic)

Both engines are invoked the same way: headless CLI, prompt on stdin, answer as final message — never via the Codex MCP server or any other harness-specific channel. Role is orthogonal to engine: any engine can be implementer, reviewer, or judge; only the prompt changes. Model policy:

Role Engine / model Spawn flags
Orchestrator Fable 5 — this session, always. Never delegated.
Implementer (default) Codex gpt-5.6-sol at high reasoning -e codex -m gpt-5.6-sol -r high
Implementer (alt, when the user asks for claude) Claude Code headless -e claude [-m opus]
Reviewer The engine that did NOT write the work per engine above
Judge (final verdict on a review loop) Codex gpt-5.6-sol -r high — cross-provider bias-free -e codex -m gpt-5.6-sol -r high

-r/--effort maps to Codex model_reasoning_effort; it is codex-only (claude headless has no effort flag — the script rejects it).

All mechanics go through one script:

REMOTO="${CLAUDE_PLUGIN_ROOT}/scripts/remoto.sh"

CLI quick reference

Command Purpose
$REMOTO hosts Probe hosts (up/down, CLI versions, load)
$REMOTO spawn -e claude|codex -d <remote-dir> [-m model] [-r effort] [-n name] [--safe] - Launch worker, prompt on stdin. Prints job id
$REMOTO ls / status <id>... Fleet / job state: RUNNING, DONE, FAILED(rc), DEAD
$REMOTO wait [-t secs] <id>... Block until all finish (poll 15s). Exit 0 all DONE, 1 any failed, 124 timeout
$REMOTO logs [-f] <id> Tail stderr + stdout
$REMOTO result <id> Final answer (claude: parsed from stream-json; codex: last message)
$REMOTO kill <id> / clean Kill process group / delete finished job dirs
$REMOTO push <local> <remote> / pull <remote> <local> rsync payloads and artifacts

Read the full file on GitHub · 68 lines

Files

What ships with it

1 file 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. 11d ago First seen · 68 lines · 120 tokens per session scan B ff790b270bac

Subscribe to this mod's changes

remote-agents is a skill published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 10d ago), licensed MIT. It adds 120 tokens to every session and 1,596 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). 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

swarmclaw

AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.

swarmclawai/swarmclaw · 67 tokens

eliza

Skill "eliza" from aomi-labs/skills, covering elizaos, what you probably got wrong, installation, cli (recommended for new projects) and from source (contributor workflow).

aomi-labs/skills · 51 tokens

update-harness

Update an existing Claude Code harness — check for outdated components, duplication with official features, missing patterns, and improvement opportunities, then apply approved changes. Use whenever: 'update harness', 'update my harness', 'is my harness up to date', 'harness outdated', 'optimize harness', 'check my…

bzantium/meta-harness · 112 tokens

agent-orchestrator

Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.

lingxling/awesome-skills-cn · 41 tokens

create-harness

Generate a complete, project-specific Claude Code harness — agents, skills, hooks, CLAUDE.md rules — tailored to any codebase. Use whenever someone says 'create a harness', 'set up agents for this project', 'configure Claude Code', 'build an agent team', 'make this project AI-ready', 'harness this project', or any…

bzantium/meta-harness · 117 tokens

help

Get oriented with the solopreneur plugin — see your AI team, check project status, and get suggestions for what to do next. Use when you're getting started or need a refresher.

pcatattacks/solopreneur-plugin · 41 tokens