agentmods.dev

universal-remote-control: Instructions file for Claude Code

CLAUDE.md

universal-remote-control CLAUDE.md is an instructions file for Claude Code from sidkandan/universal-remote-control. It costs 3,795 tokens per session, scanned C, original, MIT.

A guide for Universal Remote Control, a bridge that connects command-line coding sessions with other sessions or a phone. It uses terminal panes to relay communication.

In plain words
What is it for?
Use it to start or connect Codex and Gemini sessions, relay messages, follow the project's tmux rules, and validate plugin changes.
Why use it?
It provides the project's commands, architecture, and safety rules so agents can connect sessions without breaking the communication setup.

Instructions file for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths; mentions .claude-plugin; positional $N argument.

This is sidkandan/universal-remote-control's own configuration. It tells Claude Code how to work on universal-remote-control itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything universal-remote-control configures →

not rated 14repo 1mo ago C scan 3,795 tokens original MIT
View source ↗ sidkandan/universal-remote-control
Reuse

Borrowing it

Nothing to install: this file belongs to sidkandan/universal-remote-control. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sidkandan/universal-remote-control/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sidkandan/universal-remote-control

Made for: Claude Code.

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 universal-remote-control CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sidkandan/universal-remote-control/claude-md/github.svg)](https://agentmods.dev/instructions/sidkandan/universal-remote-control/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sidkandan/universal-remote-control/claude-md"><img src="https://agentmods.dev/badge/instructions/sidkandan/universal-remote-control/claude-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.

agentmods 80×15 button for universal-remote-control CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sidkandan/universal-remote-control/claude-md"><img src="https://agentmods.dev/badge/instructions/sidkandan/universal-remote-control/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,795 This file is loaded in full into every session.
When invoked 3,795 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.03795 $0.03795
Opus 5.5 $0.01518 $0.01518
Sonnet 5.5 $0.00759 $0.00759
Haiku 4.5 $0.00380 $0.00380

Measured 1mo ago against content hash f5c87bcfe12a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

universal-remote-control CLAUDE.md scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- This file contains instructions for Claude Code AI agents working on this project. For human documentation, see README.md -->
CLAUDE.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

URC — RC Bridge + CLI-to-CLI Communication

Quick Start

  • /urc codex — spawn Codex pane + bridge it to your phone
  • /urc gemini — spawn Gemini pane + bridge it to your phone
  • /urc %NNN — bridge an existing pane by ID
  • Aliases: /rc-bridge, /rc-any, /rc-relay all work
  • From Codex: activate rc-bridge skill — spawns relay, bridges back to Codex pane
  • From Gemini: /rc command — spawns relay, bridges back to Gemini pane

Development Rules

  • Git: All work on master branch
  • Core edits (urc/core/) require planning first — read docs/design-decisions.md before modifying core (tmux timing lessons, rejected approaches)
  • Never use raw tmux send-keys — always use send.sh
  • Commit frequently with descriptive messages
  • Plugin validation: Run bash scripts/validate-plugin.sh (23 checks, works from any context)
  • Never claude --plugin-dir . from inside Claude Code — the CLAUDECODE env var blocks nested sessions. Use the validation script instead.

Architecture (v3)

  • Coordination server: urc/core/server.py (11 MCP tools)
  • Teams protocol: urc/core/teams_protocol.py (DORMANT — removed from .mcp.json)
  • Teams MCP server: urc/core/teams_server.py (DORMANT — removed from .mcp.json)
  • RC Bridge agent: .claude/agents/rc-bridge.md (Haiku passthrough — hook-based dispatch + push reading via additionalContext, Bash fallback for terminal/error paths)
  • Bridge push hook: hooks/scripts/bridge-push-hook.sh (UserPromptSubmit — dispatches messages via send.sh, reads push files, returns via additionalContext. Registered in .claude/settings.json, NOT plugin hooks — project-level hooks fire on independent sessions, plugin hooks do NOT)
  • URC Spawn script: urc/core/urc-spawn.sh (fire-and-forget bash spawner — pre-sets tmux state + DB registration, /rename for session naming, no text bootstrap)
  • RC Bridge skill: .claude/skills/urc/SKILL.md (thin dispatcher → runs urc-spawn.sh in background)
  • CLI adapter: urc/core/cli-adapter.sh (CLI-specific field mapping)
  • Dispatch composite: urc/core/dispatch-and-wait.sh (atomic dispatch + wait + read)
  • Response schema: urc/schemas/response.md

Read the full file on GitHub · 181 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. 1mo ago First seen · 181 lines · 3,795 tokens per session scan C f5c87bcfe12a

Subscribe to this mod's changes

universal-remote-control CLAUDE.md is an instructions file published in the GitHub repository sidkandan/universal-remote-control (14 stars, last pushed 1mo ago), licensed MIT. It adds 3,795 tokens to every session, about $0.0152 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeProductivityai-agentscodexdeveloper-toolsgeminimcp
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,786 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens