Borrowing it
Nothing to install: this file belongs to littlebearapps/untether. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/littlebearapps/untether/master/CLAUDE.mdgit clone --depth 1 https://github.com/littlebearapps/untetherWrote 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.
[](https://agentmods.dev/instructions/littlebearapps/untether/claude-md)<a href="https://agentmods.dev/instructions/littlebearapps/untether/claude-md"><img src="https://agentmods.dev/badge/instructions/littlebearapps/untether/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.
<a href="https://agentmods.dev/instructions/littlebearapps/untether/claude-md"><img src="https://agentmods.dev/badge/instructions/littlebearapps/untether/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02433 | $0.02433 |
| Opus 5.5 | $0.00973 | $0.00973 |
| Sonnet 5.5 | $0.00487 | $0.00487 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
untether CLAUDE.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 18d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Untether
Telegram bridge for Claude Code, Codex, OpenCode, Pi and other agent CLIs — control coding agents from your phone. Repo: littlebearapps/untether · Upstream: banteg/takopi. Untether adds interactive permission control (Telegram approval buttons, plan mode, AskUserQuestion), live sessions, cost/usage tracking and many UX fixes. Interactive features are Claude Code-only; other engines run non-interactively.
Where the detail lives (read on demand)
| Need | Read |
|---|---|
| What a feature does / which file owns it | docs/reference/feature-catalog.md |
| What each test file covers (+ counts) | docs/reference/test-catalog.md |
| Engine protocol, event mapping | docs/reference/runners/<engine>/{runner,stream-json-cheatsheet,untether-events}.md (Codex: exec-json-cheatsheet.md + untether-events.md, no runner.md) |
| Claude permission modes, live sessions, control channel | docs/reference/runners/claude/runner.md |
| Telegram transport | docs/reference/transports/telegram.md |
| Dev/staging instances | docs/reference/dev-instance.md |
| Integration-test playbook (tiers, chat IDs) | docs/reference/integration-testing.md |
| Workflow commands / loops | docs/LOOPS.md |
Area rules in .claude/rules/ load automatically when you read matching files; skills in .claude/skills/ load on demand.
Architecture
Telegram <-> TelegramPresenter <-> RunnerBridge <-> Runner (claude/codex/opencode/pi/gemini/amp)
|
ProgressTracker
- Runners (
src/untether/runners/) — engine subprocess managers;claude.pyholds all interactive features - RunnerBridge (
src/untether/runner_bridge.py) — runner ↔ presenter, preamble, auto-continue, empty-resume recovery - TelegramPresenter (
src/untether/telegram/bridge.py) — progress, inline keyboards, answers - Commands (
src/untether/telegram/commands/) — command/callback handlers - Schemas (
src/untether/schemas/) — msgspec structs for JSONL; Triggers (src/untether/triggers/) — cron/webhooks - Config:
untether.toml(withwatch_config = truemost sections hot-reload — off by default;bot_token,chat_id,session_mode,topics,message_overflowneed a restart, as does turning[triggers] enabledon)
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.
- 18d ago Changed · -284 lines · -8,067 tokens per session e11bd2d0e36d
- 1mo ago First seen · 412 lines · 10,500 tokens per session scan A 2ca3310b8386
untether CLAUDE.md is an instructions file published in the GitHub repository littlebearapps/untether (74 stars, last pushed today), licensed MIT. It adds 2,433 tokens to every session, about $0.0097 per session on Opus 5.5. 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.
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).
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.
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).
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.
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).
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.