Borrowing it
Nothing to install: this file belongs to newtv-ai/switchboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/newtv-ai/switchboard/main/AGENTS.mdgit clone --depth 1 https://github.com/newtv-ai/switchboardWrote 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/instructions/newtv-ai/switchboard/agents-md)<a href="https://agentmods.dev/instructions/newtv-ai/switchboard/agents-md"><img src="https://agentmods.dev/badge/instructions/newtv-ai/switchboard/agents-md/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/instructions/newtv-ai/switchboard/agents-md"><img src="https://agentmods.dev/badge/instructions/newtv-ai/switchboard/agents-md.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 | $0.00667 | $0.00667 |
| Opus 5.5 | $0.00267 | $0.00267 |
| Sonnet 5.5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
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 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.
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— publicAgentAdaptercontract (what 3rd-party adapters import)packages/core—Session,RingBuffer, backends — agent-agnostic PTY relaypackages/server— Fastify HTTP+WS server +sw runCLI + built-in adapterspackages/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 workspacesnpm run typecheck— TypeScript typecheck across workspacesnpm 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 lintbefore committing;lint:fixfor 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).
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.
- 2mo ago First seen · 47 lines · 667 tokens per session scan A 23745f234888
switchboard AGENTS.md is an instructions file published in the GitHub repository newtv-ai/switchboard (4 stars, last pushed 3mo ago), licensed MIT. It adds 667 tokens to every session, about $0.0027 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.