agentmods.dev

untether copilot-instructions.md

Project instructions for Untether, a program that connects AI coding-agent command-line tools to Telegram so users can send tasks and read results from a phone.

In plain words
What is it for?
Use them when developing, testing, or reviewing Untether's Python code and its connections between agents and Telegram.
Why use it?
They give coding agents the project's programming rules, architecture, logging style, and testing expectations.

Instructions file for GitHub Copilot

66 3d ago A scan 496 tokens original MIT
View the source file littlebearapps/untether
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/littlebearapps/untether/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/untether

Made for: GitHub Copilot.

Per session 496 This file is loaded in full into every session.
When invoked 496 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00496 $0.00496
Opus 5 $0.00248 $0.00248
Sonnet 5 $0.00099 $0.00099
Haiku 4.5 $0.00050 $0.00050

Measured 2d ago against content hash 6d8c60984ad6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

untether copilot-instructions.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 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.

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.

.github/copilot-instructions.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Untether — Copilot Instructions

Untether is a Telegram bridge for AI coding agents (Claude Code, Codex, OpenCode, Pi, Gemini CLI, Amp). It runs on the user's machine and bridges agents to Telegram, so users can send tasks by voice or text, approve changes, and read results from their phone — while agents work in the background.

Stack

  • Python 3.12+, anyio (async), msgspec (JSONL parsing), structlog (logging)
  • Ruff (linting/formatting), pytest + anyio (testing), 80% coverage threshold
  • pydantic-settings for config, httpx for HTTP, typer for CLI

Code style

  • Australian English in user-facing strings (realise, colour, behaviour, licence)
  • Type hints on all public functions
  • Use match/case, type | None unions, and other Python 3.12+ features
  • Use anyio for async (not raw asyncio)
  • Use msgspec.Struct for data classes (not dataclasses or pydantic models for schemas)
  • Use structlog for logging (not stdlib logging)

Architecture

Runners (src/untether/runners/) manage engine subprocesses, emit events via the 3-event contract (StartedEvent → ActionEvent(s) → CompletedEvent). RunnerBridge connects runners to the TelegramPresenter which handles message rendering and inline keyboards.

All Telegram writes go through TelegramOutbox — never call Bot API directly.

Testing patterns

  • Stub subprocess runners with fake CLI scripts for engine tests
  • FakeTransport protocol doubles instead of real Telegram clients
  • Verify the 3-event contract: StartedEvent → ActionEvent(s) → CompletedEvent
  • Use pytest-anyio for async tests

Commit conventions

  • Conventional commits: feat:, fix:, docs:, refactor:, test:
  • Feature branches: feature/*, fix/*, docs/*
  • Every bug fix references a GitHub issue
  • Update CHANGELOG.md for user-facing changes

Commands

Key Telegram commands: /cancel, /agent, /model, /planmode, /usage, /stats (session statistics), /auth (Codex re-auth), /export, /browse, /config, /verbose, /restart.

Read the full file on GitHub · 43 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. 2d ago First seen · 43 lines · 496 tokens per session scan A 6d8c60984ad6

Subscribe to this mod's changes

untether copilot-instructions.md is an instructions file published in the GitHub repository littlebearapps/untether (66 stars, last pushed 3d ago), licensed MIT. It adds 496 tokens to every session, about $0.0025 per session on Opus 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.

ai-agentsclaude-codecli-toolscodexdeveloper-toolsopencode
Related

Other instructions, from other repositories

golembot CLAUDE.md

Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.

0xranx/golembot · 1,141 tokens

OpenCode-GraphAgent CLAUDE.md

Instructions for LeXwDeX/OpenCode-GraphAgent, covering claude.md, what this is, commands, quality gates and build & codegen.

LeXwDeX/OpenCode-GraphAgent · 4,083 tokens

superset CLAUDE.md

Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

superset-sh/superset · 4 tokens

give-me-job AGENTS.md

Instructions for kyoungbinkim/give-me-job, covering give-me-job repository instructions, default workflow, skill routing, working on this repository and development loop.

kyoungbinkim/give-me-job · 1,106 tokens

nexus-mcp AGENTS.md

Instructions for j7an/nexus-mcp, covering agents.md - guidelines for ai coding agents, project overview, build, lint, test commands, setup (first time) and run all tests (unit + e2e, fast).

j7an/nexus-mcp · 1,449 tokens

claude-tui AGENTS.md

Instructions for slima4/claude-tui, covering agents.md, quick commands, testing, gotchas (hard-won knowledge) and local development.

slima4/claude-tui · 546 tokens