x-setup

x-setup is a skill for Codex from anotb/x-signal. It costs 42 tokens per session (462 once invoked), scanned A, original, MIT.

A troubleshooting and operations guide for X Signal Docker, browser, sign-in, MCP, and tunnel setups.

In plain words
What is it for?
Use it to check service health, recover sign-in challenges, manage browser profiles and accounts, and diagnose MCP connections.
Why use it?
It helps identify whether a failure comes from the application, database, browser connection, X authentication, captured operation, or network tunnel.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to check service health, recover sign-in challenges, manage browser profiles and accounts, and diagnose MCP connections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anotb/x-signal/x-setup
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 anotb/x-signal --skill x-setup
Clone the repo
git clone --depth 1 https://github.com/anotb/x-signal

Made for: 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 x-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/anotb/x-signal/x-setup.svg)](https://agentmods.dev/skills/anotb/x-signal/x-setup)
Your own site
<a href="https://agentmods.dev/skills/anotb/x-signal/x-setup"><img src="https://agentmods.dev/badge/skills/anotb/x-signal/x-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 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 $0.00042 $0.00462
Opus 5 $0.00021 $0.00231
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 7d ago against content hash fd0404a12ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

x-setup 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 7d 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/x-setup/SKILL.md · 13 lines

What it actually says

X Signal setup

  1. Call x_status with liveProbe: true, then distinguish app, database, browser/CDP, X authentication/challenge, captured operation, and tunnel failures.
  2. Check docker compose ps, /healthz, /readyz, and redacted service logs. Use http://127.0.0.1:6080/vnc.html only for visible sign-in or challenge recovery.
  3. The persistent browser profile survives Compose and host restarts. For an alternate account, recommend a dedicated Chrome profile with the companion installed, automatic sync left on, and Use this profile selected once; the everyday Chrome profile can remain on another account. Never ask the user to paste cookies or tokens into chat. Check all named sources' lastSeenAt plus the active source's lastSyncedAt/lastAppliedAt and any pendingSessionSource. A different prepared profile is selected intentionally and automatic sync completes the switch after current runs settle. An account change inside the selected profile is detected from cookie changes and automatically deferred/retried behind active research. A same-profile one-time transfer can pause automatic sync, but X may invalidate it when that profile changes accounts.
  4. For local MCP clients use http://127.0.0.1:7345/mcp. For ChatGPT, use the Compose chatgpt profile and the hidden npm run tunnel:secure:configure prompt. Configure the tunnel ID, its owning Platform organization ID, and the runtime key so accounts with multiple organizations have an explicit control-plane context. Check the local tunnel /readyz and verify workspace association plus Tunnels Read + Use if it is not listed. Never capture or repeat a tunnel ID, organization ID, or runtime key. Use the path-gated temporary command only for an explicitly short-lived fallback, then refresh the app after schema changes.
  5. Give exact recovery commands and recheck status. Do not bypass X challenges or weaken loopback/tunnel authentication.
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. 7d ago First seen · 13 lines · 42 tokens per session scan A fd0404a12ef4

Subscribe to this mod's changes

x-setup is a skill published in the GitHub repository anotb/x-signal (1 stars, last pushed 24d ago), licensed MIT. It adds 42 tokens to every session and 462 once invoked, about $0.0002 per session on Opus 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 2026-08-31.