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.
npx agentmods add instructions/sidkandan/universal-remote-control/agents-mdgit clone --depth 1 https://github.com/sidkandan/universal-remote-controlWhat 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 | $0.03467 | $0.03467 |
| Opus 5 | $0.01733 | $0.01733 |
| Sonnet 5 | $0.00693 | $0.00693 |
| Haiku 4.5 | $0.00347 | $0.00347 |
Grade C, and why
universal-remote-control AGENTS.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 2d 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 Codex CLI agents. For human documentation, see README.md --> How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
URC — CLI-to-CLI Communication & RC Bridge
URC enables cross-CLI communication between Claude Code, Codex, and Gemini panes via MCP tools, and provides RC Bridge for phone-to-CLI remote control.
RC Bridge System
The RC Bridge lets you control this Codex pane from the Claude Code phone app:
- A Claude Code Haiku relay pane spawns alongside your pane
- It's pre-configured with your pane ID and CLI type via tmux pane options (set by
urc-spawn.sh) - Phone messages are dispatched to your pane via a
UserPromptSubmithook — no model turn consumed - Your output is captured by
hook.shand written to a push file, which the relay picks up on its next wake and displays on the phone
Launch with: /rc-bridge
Available MCP Tools
urc-coordination (pane communication — 11 tools)
| Tool | Purpose |
|---|---|
register_agent |
Register a pane (auto-called on first tool use — no manual registration needed) |
heartbeat |
Send heartbeat update for a pane |
get_fleet_status |
List all registered agents and their status |
rename_agent |
Set display label for a pane |
dispatch_to_pane |
Send a message to a tmux pane via send.sh |
read_pane_output |
Capture recent output from a pane's tmux buffer |
send_message |
Send inter-agent message (use notify=true to include wake nudge) |
receive_messages |
Get unread messages |
kill_pane |
Kill a tmux pane (requires explicit confirmation) |
cancel_dispatch |
SIGINT target + clear signals + unblock waiting dispatcher |
bootstrap_validate |
Validate CWD/directories/hook/tmux setup |
urc-teams (DORMANT — removed from .mcp.json)
Teams protocol is dormant. The code exists in urc/core/teams_server.py but the MCP server is not loaded. Use send_message/receive_messages from urc-coordination for cross-CLI messaging instead.
Turn Completion
Your notify hook in .codex/config.toml fires urc/core/hook.sh after each turn. This:
- Writes response to
.urc/responses/{PANE}.json - Touches signal file
.urc/signals/done_{PANE} - Fires
tmux wait-forto wake blocking dispatchers - Appends to JSONL audit stream
.urc/streams/{PANE}.jsonl
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.
- 2d ago First seen · 200 lines · 3,467 tokens per session scan C 58cd464efa43
universal-remote-control AGENTS.md is an instructions file published in the GitHub repository sidkandan/universal-remote-control (13 stars, last pushed 5mo ago), licensed MIT. It adds 3,467 tokens to every session, about $0.0173 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.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
ima2-gen AGENTS.md
Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).
InvestSkill copilot-instructions.md
Instructions for yennanliu/InvestSkill, covering investskill — github copilot setup & usage guide, installation & setup, automatic setup, verify setup and core stock analysis (6 frameworks).
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…