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/termly-dev/termly-cli/claude-mdgit clone --depth 1 https://github.com/termly-dev/termly-cliWhat 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 | $0.03437 | $0.03437 |
| Opus 5 | $0.01718 | $0.01718 |
| Sonnet 5 | $0.00687 | $0.00687 |
| Haiku 4.5 | $0.00344 | $0.00344 |
Grade C, and why
termly-cli 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.termly How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Termly CLI is a universal NPM utility that enables remote terminal access to AI coding assistants (Claude Code, Aider, GitHub Copilot, Gemini, Grok, Cody, and 10+ more) from mobile devices. It works by:
- Spawning AI tools in a PTY (pseudo-terminal) on the developer's computer
- Streaming terminal I/O through WebSocket to a server with end-to-end encryption
- Supporting session resume with circular buffering and sequence numbers
- Managing multiple independent sessions simultaneously
Key constraint: Each CLI session supports exactly ONE mobile device connection.
Multi-Environment Architecture
The CLI supports three environments with hardcoded server URLs:
- Production (
@termly-dev/cli):termlycommand →wss://api.termly.dev - Development (
@termly-dev/cli-dev):termly-devcommand →wss://dev-api.termly.dev - Local:
TERMLY_ENV=local→ws://localhost:3000
Environments are detected by:
TERMLY_ENV=localenvironment variable (highest priority)- Binary name (
cli-dev.js= dev,cli.js= production) - Default to production
Critical: Users CANNOT change server URLs. They are immutable per environment.
Development Commands
# Install dependencies
npm install
# Test production package
node bin/cli.js [command]
node bin/cli.js config # Should show "Production" environment
# Test development package
node bin/cli-dev.js [command]
node bin/cli-dev.js config # Should show "Development" environment
# Test local environment
TERMLY_ENV=local node bin/cli.js config # Should show "Local Development"
# Link for global testing
npm link # Creates 'termly' command
# Debug mode (enables verbose logging)
DEBUG=1 node bin/cli.js start --debug
node bin/cli.js start --debug
# View logs
tail -f ~/.termly/logs/cli.log
# Clean up test sessions
rm -rf ~/.termly
Publishing
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.
- yesterday First seen · 339 lines · 3,437 tokens per session scan C e8500bac1b4b
termly-cli CLAUDE.md is an instructions file published in the GitHub repository termly-dev/termly-cli (298 stars, last pushed 1mo ago), licensed MIT. It adds 3,437 tokens to every session, about $0.0172 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
paseo CLAUDE.md
Claude Code instructions for getpaseo/paseo, covering claude.md, repository map, docs, writing docs and doc voice.
paseo AGENTS.md
AGENTS.md instructions for getpaseo/paseo, a project described as: Orchestrate multiple coding agents from desktop and mobile.
lovable-boilerplate design.instructions.md
Instructions for chihebnabil/lovable-boilerplate, covering design system guidelines, critical design rules, never create, always create and core design philosophy.
codeagent-mobile-clients CLAUDE.md
Instructions for edgar-durand/codeagent-mobile-clients, covering claude.md, cuestiona lo que se te pide cuando veas algo mejor, repo layout, commands and root.
android-harness-kit AGENTS.md
Instructions for rabee-elkholy/android-harness-kit, covering android-harness-kit — agent instructions, environment, delivery gate (do not skip), on-demand specialists and phase boundaries & high-signal chat.
android-harness-kit GEMINI.md
Instructions for rabee-elkholy/android-harness-kit: Follow AGENTS.md and .agents/rules/harness-rules.md. That file wins.