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.
/plugin marketplace add JairoTorregrosa/jaiskills/plugin install jaiskillsWrote 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.
[](https://agentmods.dev/skills/jairotorregrosa/jaiskills/remote-agents)<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.
<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>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.
| Model | Per session | Once 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 |
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. 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 |
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.
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.
- 11d ago First seen · 68 lines · 120 tokens per session scan B ff790b270bac
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.
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.
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).
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…
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.
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…
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.