What is claude-code-session-bot CLAUDE.md?

Project instructions for a Telegram bot that manages Claude Code usage sessions and scheduled warmups.

Useful when changing the bot, its Telegram commands, SQLite database, session scheduling, or deployment setup.

They give a coding agent the project structure, commands, data storage details, and important limits so it can work consistently in the repository.

claude-code-session-bot CLAUDE.md — Instructions file by sleeyax

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/sleeyax/claude-code-session-bot/claude-md

Clone the repo

git clone --depth 1 https://github.com/sleeyax/claude-code-session-bot

Per session 449 This file is loaded in full into every session.

When invoked 449 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.

Model	Per session	Once invoked
Fable 5	$0.00449	$0.00449
Opus 5	$0.00225	$0.00225
Sonnet 5	$0.00090	$0.00090
Haiku 4.5	$0.00045	$0.00045

Measured 3d ago against content hash eba50269737e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-session-bot 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 3d 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.

CLAUDE.md · 43 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

Telegram bot that manages Claude Code Pro 5-hour session cooldowns. Schedules automated warmups via claude CLI so you have remaining usage at a target time.

Commands

pnpm dev            # run with tsx --watch (hot reload)
pnpm build          # tsc → dist/
pnpm start          # run compiled dist/main.js
docker compose up -d --build  # production deploy

No test or lint setup exists yet.

Architecture

TypeScript (ES2022/CommonJS, strict), SQLite via better-sqlite3 (WAL mode), Telegram API via node-telegram-bot-api.

All source files are located in src/:

main.ts — entry point; inits DB, bot, restores pending schedules
bot.ts — Telegram command handlers (/warmup, /schedule, /session, /cancel, /history, /schedules)
warmup.ts — spawns claude -p "ready" --output-format json subprocess; parses token usage
scheduler.ts — in-memory setTimeout timers + DB persistence; restores timers on restart
db.ts — SQLite CRUD for sessions and schedules tables
config.ts — env var validation (TELEGRAM_BOT_TOKEN, TELEGRAM_ALLOWED_USER_IDS, optional TIMEZONE, DB_PATH)
types.ts — interfaces: Session, Schedule, WarmupResult

See README.md for full usage details.

Key Details

Session duration fixed at 5 hours (SESSION_DURATION_MS)
Only tracks sessions the bot starts (no external session tracking)
Auth: only Telegram user IDs in TELEGRAM_ALLOWED_USER_IDS can use commands
Date parsing via chrono-node (natural language: "tomorrow 9am", "jan 30 8:00")
Requires claude CLI installed and authenticated on host

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.

3d ago First seen · 43 lines · 449 tokens per session scan A eba50269737e

Subscribe to this mod's changes

claude-code-session-bot CLAUDE.md is an instructions file published in the GitHub repository sleeyax/claude-code-session-bot (11 stars, last pushed 7mo ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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.

claude claude-code telegrambot

claude-telegram-bot-bridge CLAUDE.md

Claude Code instructions for terranc/claude-telegram-bot-bridge, covering claude.md, project overview, code style, setup and run (foreground, default).

terranc/claude-telegram-bot-bridge · 1,883 tokens

nonebot-plugin-codex AGENTS.md

AGENTS.md instructions for ttiee/nonebot-plugin-codex, covering repository guidelines, project scope, repository layout, working norms and development commands.

ttiee/nonebot-plugin-codex · 539 tokens

codex-telegram-bot AGENTS.md

AGENTS.md instructions for JJPanda4590/codex-telegram-bot, covering agents.md, highest priority rule, project overview, key files and runtime commands.

JJPanda4590/codex-telegram-bot · 699 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens