phonehub

phonehub is a skill for Claude Code, Codex from Ertinox7711/SGRR-AGI-V2. It costs 205 tokens per session (2,293 once invoked), scanned A, original, MIT.

A control tool for a local group of Android phones, including starting and stopping phones, installing app packages, and managing phone network settings. It uses a command-line interface, meaning actions are entered as text commands.

In plain words
What is it for?
Use it to create and start named phones, install Instagram or TikTok from app packages, prepare phones for automated work, inspect the group, and run audits.
Why use it?
It gives one place to inspect and operate the phone group instead of handling each local phone manually. Status checks help avoid acting on the wrong phone or using too many resources at once.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cd C:\Users\YOU\Documents\BUSINESS\phonehub && node server/cli/hub.js <commande>.

Good fit Use it to create and start named phones, install Instagram or TikTok from app packages, prepare phones for automated work, inspect the group, and run audits.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2
agentmods
npx agentmods add skills/ertinox7711/sgrr-agi-v2/phonehub

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 phonehub

README.md
[![agentmods](https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/phonehub/github.svg)](https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/phonehub)
Your own site
<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/phonehub"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/phonehub/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 phonehub

Your own site · 80×15
<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/phonehub"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/phonehub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,293 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 $0.00205 $0.02293
Opus 5.5 $0.00082 $0.00917
Sonnet 5.5 $0.00041 $0.00459
Haiku 4.5 $0.00020 $0.00229

Measured 23d ago against content hash 022ff0c469fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

phonehub 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 23d 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/phonehub/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PhoneHub — piloter la ferme de telephones locaux

Projet : C:\Users\YOU\Documents\BUSINESS\phonehub (CLAUDE.md = memoire maitre, le lire si un doute technique). PhoneHub est la nouvelle version d OFM HUB (decision de the operator, 2026-09-21) : le warmup d OFM HUB V2 est le plan par defaut de arm, V2 reste en lecture seule. Serveur npm start sur 127.0.0.1:3010. Tout passe par le CLI :

cd C:\Users\YOU\Documents\BUSINESS\phonehub && node server/cli/hub.js <commande>

hub help = la liste complete. --json sur n importe quelle commande = brut exploitable. Si ECONNREFUSED → serveur eteint : demander a the operator de lancer npm start (un serveur lance en tache de fond depuis ma session meurt avec elle).

Reflexes (ordre)

  1. hub status avant toute action — l etat du parc, jamais de memoire.
  2. Une commande = un telephone nomme. fleet-* sans id = TOUT le parc (2-3 max en RAM : 3 Go chacun sur 15 Go). Ne jamais allumer 3 telephones en meme temps qu un autre travail lourd.
  3. Setup neuf = hub provision <nom> [<nom>...] (une commande, N telephones) : cree → demarre → installe Instagram + TikTok depuis apk/ → teste a froid → durcit → audite. --snapshot = sauvegarde « base » ; --arm seulement APRES la 1re connexion Instagram (manuelle) ; --proxy url avant le 1er demarrage.
  4. Apres un travail sur un telephone demarre par moi : le remettre dans l etat trouve (hub stop <id>) sauf demande contraire. La regie gere elle-meme ceux qu elle demarre.
  5. Verifier avant de dire « fait » : hub apps <id>, hub audit <id>, hub screenshot <id>.

Cartes

  • references/telephone-reel.md — LE VRAI TELEPHONE de the operator (phone4, OnePlus, compte perso ) : connexion, chauffe pilotee, preparation de posts (hub ig-brouillon), cadrage valide, hashtags FR mesures, verrous de publication, pieges payes. A lire avant tout geste sur le OnePlus.

  • references/commandes.md — toutes les commandes hub, par usage.

  • references/regles.md — ce que je ne fais JAMAIS, verites anti-ban, ce qui reste manuel.

  • references/workflows.md — recettes multi-telephones (provision N, APK, armement, controle quotidien, diagnostic).

  • references/comptes.md — ouvrir et tenir des comptes Instagram : le rail complet, le schema de pseudo releve sur la reference de the operator, le coffre Bitwarden, ce qui tient contre un shadowban, et la seule chose qui reste sa main.

Read the full file on GitHub · 130 lines

Files

What ships with it

5 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. 23d ago First seen · 130 lines · 205 tokens per session scan A 022ff0c469fe

Subscribe to this mod's changes

phonehub is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 205 tokens to every session and 2,293 once invoked, about $0.0008 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 2026-10-04.