Borrowing it
Nothing to install: this file belongs to Mark-Life/telegram-claude-codex. 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/Mark-Life/telegram-claude-codex/main/CLAUDE.mdgit clone --depth 1 https://github.com/Mark-Life/telegram-claude-codexWrote 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/mark-life/telegram-claude-codex/claude-md)<a href="https://agentmods.dev/instructions/mark-life/telegram-claude-codex/claude-md"><img src="https://agentmods.dev/badge/instructions/mark-life/telegram-claude-codex/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/mark-life/telegram-claude-codex/claude-md"><img src="https://agentmods.dev/badge/instructions/mark-life/telegram-claude-codex/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 | $0.04138 | $0.04138 |
| Opus 5.5 | $0.01655 | $0.01655 |
| Sonnet 5.5 | $0.00828 | $0.00828 |
| Haiku 4.5 | $0.00414 | $0.00414 |
Grade A, and why
telegram-claude-codex 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 1mo 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 — 118 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.
Commands
bun install # install dependencies
bun run src/index.ts # start bot
bun --watch run src/index.ts # dev mode (auto-reload on changes)
bun test # run tests
bun run typecheck # tsc --noEmit
bun run lint # check lint/format (ultracite/biome)
bun run fix # auto-fix lint/format issues
bun run backup # snapshot .data/bot.db into .data/backups/
Architecture
Telegram bot that bridges coding-agent CLIs (Claude Code + OpenAI Codex) with Telegram. Runs the active provider (SDK in-process for Claude, spawned CLI for Codex), normalizes its output to a provider-agnostic event model, and renders it into the chat. The active provider is swappable at runtime via /provider.
Two things shape the whole layout: every conversation is a route — user + chat + forum topic — so topics run in parallel with their own session, project, queue and compose draft; and output is quiet by default — a typing indicator, then one message with the answer, unless /verbose is on. All durable state is SQLite (.data/bot.db).
Module Overview (src/)
- index.ts — Entry point. Opens/migrates
.data/bot.dband runs the one-time legacy JSON import before any update is served; bootsAppConfig+BotServicethrough the Effect runtime (env validation fails fast); warns (non-blocking) oncodex login statusand on the BotFather flagsgetMeexposes read-only (privacy mode, join-groups); registers the command list in four scopes; starts polling. Shutdown: stop all runs →runtime.dispose()(stops the bot) →closeDb(). - bot.ts —
createBot(token, allowedUserId, projectsDir): grammy instance, access-control middleware, reply-keyboard-button → command rewriting, then theregister*()groups fromhandlers/. Registration order matters (topic-title bookkeeping → compose interceptor → commands → text → uploads) and is documented in place. - state.ts — Thin wrapper over the settings table:
loadPersistedState()plus setters for active project/provider and per-provider model/effort.BotStateis derived fromloadBotState, so the two can't drift. - telegram.ts —
streamToTelegram({ctx, events, policy, route, …}): typing ticker (the only progress signal under the quiet policy), 1.5s deferred-edit flush,dispatchEventper event,finalizeStream. Re-exportssplitText/sendRichMarkdown/StreamResult. - config.ts / runtime.ts / logger.ts / telemetry.ts / observability.ts — Effect layers: env config (
AppConfig), theManagedRuntimeall Promise-land code bridges through, console logging, optional OTLP forwarding, and the one-wide-event-per-run ledger. - transcribe.ts — Voice message transcription via Groq Whisper (
whisper-large-v3-turbo).
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.
- 1mo ago Changed · +48 lines · +2,185 tokens per session 0afaf0cdcc72
- 1mo ago Changed · +1 lines · +234 tokens per session eaa1300f1812
- 1mo ago First seen · 69 lines · 1,719 tokens per session scan A 72bfc684c6d7
telegram-claude-codex CLAUDE.md is an instructions file published in the GitHub repository Mark-Life/telegram-claude-codex (10 stars, last pushed 1mo ago), licensed MIT. It adds 4,138 tokens to every session, about $0.0166 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 2026-08-31.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.