Borrowing it
Nothing to install: this file belongs to TentacleOpera/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/TentacleOpera/switchboard/main/AGENTS.mdgit clone --depth 1 https://github.com/TentacleOpera/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/tentacleopera/switchboard/agents-md)<a href="https://agentmods.dev/instructions/tentacleopera/switchboard/agents-md"><img src="https://agentmods.dev/badge/instructions/tentacleopera/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/tentacleopera/switchboard/agents-md"><img src="https://agentmods.dev/badge/instructions/tentacleopera/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 | $0.01933 | $0.01933 |
| Opus 5.5 | $0.00773 | $0.00773 |
| Sonnet 5.5 | $0.00387 | $0.00387 |
| Haiku 4.5 | $0.00193 | $0.00193 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- switchboard CLAUDE.md — 86% identical, 98 lines differ
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switchboard — agent rules
NEVER add confirmation dialogs. NO EXCEPTIONS.
Delete buttons delete immediately. No confirm(), no window.confirm(), no modal showWarningMessage, no two-click patterns, no "Are you sure?". The user has demanded this repeatedly. Buttons are deliberately hard to misclick.
Also a hard technical reason: window.confirm() is a silent no-op in VS Code webviews (sandboxed iframe without allow-modals — it always returns false). Any confirm gate added to src/webview/planning.js, src/webview/kanban.html, etc. makes the button do literally nothing. This exact bug broke the kanban delete-plan button (fixed 2026-06-11).
If you find a confirm gate in this codebase, it is a bug — remove it. Multi-choice decision dialogs (e.g. 3-way conflict resolution) are allowed; plain confirm gates are not.
What this product is
A Raspberry Pi product. Switchboard is being rebuilt as an appliance: a board host running on a small box, with agent seats running on other machines. That is the shape every decision should serve.
- The standalone host is primary.
src/standalone/bootstrap.ts— theswitchboard/npx CLI — is what actually runs on the Pi, on :7777, and is what a board deployment means. Measured: 182 MB RSS on a Pi 400 with no seats, so board-only fits 1 GB; board plus local agents wants 2 GB minimum, 4 GB comfortable. - One store, one host. One better-sqlite3 database owned by that host. Not libSQL (rejected), not a git-carried board (rejected). Other machines never open the database — they reach it over HTTP.
- Multi-machine means seats, not stores. A seat's startup command carries an
ssh/moshtransport prefix; the pty stays local and the agent process runs on the other box. - The VS Code extension (
src/extension.ts) is the legacy host. It still ships and still has to work, but it is no longer the thing being designed for. Do not describe this product as a VS Code extension.
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.
- 1mo ago Changed · +1 lines · +13 tokens per session 666c86056000
- 1mo ago Changed · -112 lines · -2,922 tokens per session 4a061e6508d6
- 1mo ago Changed · +27 lines · +372 tokens per session bf4be1ea60c9
- 1mo ago First seen · 193 lines · 4,470 tokens per session scan A b707f1141d71
switchboard AGENTS.md is an instructions file published in the GitHub repository TentacleOpera/switchboard (215 stars, last pushed 1mo ago), licensed MIT. It adds 1,933 tokens to every session, about $0.0077 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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.