remote-client

remote-client is a skill for Claude Code, Codex from FlowLLM-AI/flowllm. It costs 82 tokens per session (879 once invoked), scanned A, original, Apache-2.0.

A guide for using FlowLLM’s remote client to send commands to a running remote server over HTTP. HTTP is the standard protocol used to exchange requests and responses between computers.

In plain words
What is it for?
Use it to ping a remote server, run shell commands, run commands from a file, upload and run a Python file, inspect tasks, or stop remote tasks.
Why use it?
It helps run or inspect work on a configured project host while keeping control from the local terminal, with checks for the target host and port.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to ping a remote server, run shell commands, run commands from a file, upload and run a Python file, inspect tasks, or stop remote tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flowllm-ai/flowllm/remote_client
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 FlowLLM-AI/flowllm --skill remote_client
Clone the repo
git clone --depth 1 https://github.com/FlowLLM-AI/flowllm

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-client

README.md
[![agentmods](https://agentmods.dev/badge/skills/flowllm-ai/flowllm/remote_client/github.svg)](https://agentmods.dev/skills/flowllm-ai/flowllm/remote_client)
Your own site
<a href="https://agentmods.dev/skills/flowllm-ai/flowllm/remote_client"><img src="https://agentmods.dev/badge/skills/flowllm-ai/flowllm/remote_client/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-client

Your own site · 80×15
<a href="https://agentmods.dev/skills/flowllm-ai/flowllm/remote_client"><img src="https://agentmods.dev/badge/skills/flowllm-ai/flowllm/remote_client.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 879 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00082 $0.00879
Opus 5.5 $0.00033 $0.00352
Sonnet 5.5 $0.00016 $0.00176
Haiku 4.5 $0.00008 $0.00088

Measured 2mo ago against content hash 66b4aed1b906, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

remote-client scanned grade A with 0 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/remote_client/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remote Client

Overview

Use the FlowLLM lite remote_client flow to call a running remote_server over HTTP. Prefer it when work should execute on a configured remote project host instead of the local Codex shell.

The implementation lives in flowllm/lite/flow/remote_client_flow.py; the paired server endpoints live in flowllm/lite/flow/remote_server_flow.py.

Before Running

Confirm the target host and port before launching remote work:

fl --remote-client --action ping

If --host is omitted, remote_client_flow.py reads DEFAULT_REMOTE_HOST_ENV. If neither is set, it raises Remote host is required. Set DEFAULT_REMOTE_HOST_ENV or pass --host.

Use --host only when overriding DEFAULT_REMOTE_HOST_ENV. Use --port only when the server is not on the default 8765.

Actions

Run a shell command remotely and stream stdout/stderr back to the local terminal:

fl --remote-client --action exec --command "pytest tests/unit"

Run a command stored in a local file:

fl --remote-client --action exec --command-file /path/to/command.sh

Upload and run a local Python file on the remote server:

fl --remote-client --action exec --python-file /path/to/script.py

Inspect tracked remote tasks:

fl --remote-client --action tasks
fl --remote-client --action tasks --status running --tail 80

Terminate a task or all running tasks:

fl --remote-client --action kill --task-id 12
fl --remote-client --action kill_all

Parameters

  • --action: one of exec, ping, tasks, kill, kill_all; default is exec.
  • --host: remote host. Falls back to DEFAULT_REMOTE_HOST_ENV.
  • --port: remote server port; default is 8765.
  • --timeout: command timeout in seconds; default is 3600.
  • --command: shell command string for exec.
  • --command-file: local text file whose contents become the remote shell command.
  • --python-file: local Python file uploaded as code and run by the remote Python interpreter.
  • --status: optional task status filter for tasks, commonly running, finished, or killed.
  • --tail: output lines to include per task for tasks; default is 30.
  • --task-id: required for kill.

Read the full file on GitHub · 100 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. 2mo ago First seen · 100 lines · 82 tokens per session scan A 66b4aed1b906

Subscribe to this mod's changes

remote-client is a skill published in the GitHub repository FlowLLM-AI/flowllm (37 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 879 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

remote-client compared with skills from other repositories

remote-client next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
remote-clientFlowLLM-AI/flowllmSkill374mo agoApache-2.0A82Claude Code, Codex
nornweave-apiDataCovey/nornweaveSkill3010d agoApache-2.0A77Claude Code, Codex
nano-banana-pro-openrouteropensquilla/opensquillaSkill7.1k6d agoApache-2.0A49Claude Code
skill-creator-linteropensquilla/opensquillaSkill7.1k6d agoApache-2.0A84Claude Code
clinicaltrials-databasesynthetic-sciences/openscienceSkill4.3k2d agoApache-2.0A47Claude Code, Codex
glycoengineeringsynthetic-sciences/openscienceSkill4.3k2d agoApache-2.0A75Claude Code, Codex
openalex-databasesynthetic-sciences/openscienceSkill4.3k2d agoApache-2.0A76Claude Code, Codex