agentmods.dev

universal-remote-control CLAUDE.md

universal-remote-control CLAUDE.md is an instructions file for coding agents 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

not rated 13 5mo ago C scan 3,795 tokens original MIT
View the source file sidkandan/universal-remote-control
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/sidkandan/universal-remote-control/claude-md
Clone the repo
git clone --depth 1 https://github.com/sidkandan/universal-remote-control

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.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.svg" alt="Measured on agentmods" 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. 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 $0.03795 $0.03795
Opus 5 $0.01898 $0.01898
Sonnet 5 $0.00759 $0.00759
Haiku 4.5 $0.00380 $0.00380

Measured 4d ago against content hash f5c87bcfe12a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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. 4d 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 (13 stars, last pushed 5mo ago), licensed MIT. It adds 3,795 tokens to every session, about $0.0190 per session on Opus 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.

Planningagent-coordinationai-agentsclaude-codeclaude-code-plugincli-toolscodex
Related

Other instructions, from other repositories

fulcra-tools AGENTS.md

AGENTS.md instructions for ashfulcra/fulcra-tools, covering fulcra tools — agent guide, where to start, layout, setup & tests and coordinate on the bus.

ashfulcra/fulcra-tools · 27,748 tokens

token-saver CLAUDE.md

Instructions for ppgranger/token-saver, covering token-saver plugin, how it works and important rules.

ppgranger/token-saver · 145 tokens

plan-critique-skills CLAUDE.md

Instructions for serbanghita/plan-critique-skills, covering project standards, architecture, code style, versioning and releases and documentation.

serbanghita/plan-critique-skills · 1,048 tokens

cortex CLAUDE.md

Instructions for agentweave/cortex, covering cortex, project structure, key concepts, conventions and when editing skills.

agentweave/cortex · 463 tokens

all-my-ai-needs CLAUDE.md

Claude Code instructions for codingSamss/all-my-ai-needs, covering claude.md, 项目概览, 仓库结构, skill 文件格式 and skill 标题.

codingSamss/all-my-ai-needs · 1,161 tokens

all-my-ai-needs AGENTS.md

AGENTS.md instructions for codingSamss/all-my-ai-needs, covering repository guidelines, 项目结构与模块组织, 平台同步策略, readme 维护约定 and 同步与验证操作.

codingSamss/all-my-ai-needs · 3,662 tokens