switchboard AGENTS.md

switchboard AGENTS.md is an instructions file for Codex, OpenCode from newtv-ai/switchboard. It costs 667 tokens per session, scanned A, original, MIT.

Shared project guidance for Switchboard, a self-hosted web app that relays AI coding tools so they can be used from a phone browser over a local network or Tailscale.

In plain words
What is it for?
Use it to understand the npm workspace package layout, follow project conventions, and keep feature changes reflected in SPEC.md.
Why use it?
It keeps different coding agents aligned on the repository's architecture, commands, and source-of-truth specification. A monorepo is one repository containing several related packages.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/newtv-ai/switchboard/agents-md
Clone the repo
git clone --depth 1 https://github.com/newtv-ai/switchboard

Made for: Codex, OpenCode.

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 switchboard AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/newtv-ai/switchboard/agents-md.svg)](https://agentmods.dev/instructions/newtv-ai/switchboard/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/newtv-ai/switchboard/agents-md"><img src="https://agentmods.dev/badge/instructions/newtv-ai/switchboard/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 667 This file is loaded in full into every session.
When invoked 667 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00667 $0.00667
Opus 5 $0.00333 $0.00333
Sonnet 5 $0.00133 $0.00133
Haiku 4.5 $0.00067 $0.00067

Measured 4d ago against content hash 23745f234888, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

switchboard AGENTS.md 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 4d 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.

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Switchboard — Agent Guide (AGENTS.md)

Project-level instructions for any AI coding CLI working in this repo. Codex reads AGENTS.md; Claude Code reads CLAUDE.md (which points here); Gemini CLI reads GEMINI.md (add one as a pointer if/when Gemini is used). Keep shared guidance here only so the agents don't drift.

What this project is

Switchboard ("总机") — a self-hostable web app that lets you drive AI coding CLIs (Claude Code, Codex, Antigravity, …) on your dev machine from a phone browser over LAN / Tailscale. Agent-agnostic PTY-relay core + plugin adapter system. MIT.

Source of truth

SPEC.md is the design source of truth. Any new feature, scope change, or architectural decision must be reflected in SPEC.md before/during implementation (see SPEC §11). If code and SPEC diverge, fix one — never let them drift silently.

Repo layout (monorepo, npm workspaces)

  • packages/sdk — public AgentAdapter contract (what 3rd-party adapters import)
  • packages/coreSession, RingBuffer, backends — agent-agnostic PTY relay
  • packages/server — Fastify HTTP+WS server + sw run CLI + built-in adapters
  • packages/web — React + xterm.js frontend (the PWA)
  • packages/camera — optional go2rtc sidecar for camera streaming

Commands (from repo root)

  • npm run dev — start server + web in dev mode (concurrently)
  • npm run build — build all workspaces
  • npm run typecheck — TypeScript typecheck across workspaces
  • npm run lint — Biome check (lint + format)
  • npm run lint:fix — Biome safe auto-fix

No test runner is configured yet. When adding one, document it here and in SPEC.

Conventions

  • Linter/formatter: Biome. Run npm run lint before committing; lint:fix for safe fixes.
  • Line endings: LF (Biome-enforced).
  • docs/ is gitignored — local working notes only (planning/, audit/, architecture/). Anything that must reach GitHub goes in tracked files (README, SPEC, source).
  • Adapters live in packages/server/src/adapters/. A new agent works in raw ("passthrough") mode on day one; add an adapter for structured UX. See SPEC §4.3.
  • Don't build an LLM API proxy / gateway — Switchboard drives existing CLIs, it doesn't replace them (SPEC §1.2).

Read the full file on GitHub · 47 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. 4d ago First seen · 47 lines · 667 tokens per session scan A 23745f234888

Subscribe to this mod's changes

switchboard AGENTS.md is an instructions file published in the GitHub repository newtv-ai/switchboard (4 stars, last pushed 1mo ago), licensed MIT. It adds 667 tokens to every session, about $0.0033 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.