Borrowing it
Nothing to install: this file belongs to IvanWng97/TradingAgents-Telegram. 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/IvanWng97/TradingAgents-Telegram/main/CLAUDE.mdgit clone --depth 1 https://github.com/IvanWng97/TradingAgents-TelegramWrote 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/ivanwng97/tradingagents-telegram/claude-md)<a href="https://agentmods.dev/instructions/ivanwng97/tradingagents-telegram/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanwng97/tradingagents-telegram/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/ivanwng97/tradingagents-telegram/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanwng97/tradingagents-telegram/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 | $0.09679 | $0.09679 |
| Opus 5.5 | $0.03872 | $0.03872 |
| Sonnet 5.5 | $0.01936 | $0.01936 |
| Haiku 4.5 | $0.00968 | $0.00968 |
Grade A, and why
TradingAgents-Telegram 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 2mo 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TradingAgents-Telegram — Architecture Reference
Telegram bot wrapping the TradingAgents library. Users curate a watchlist via Telegram, tap a ticker, and the bot runs TradingAgentsGraph.propagate(...) and posts a finviz chart + Telegraph link with the verdict. Per-step pipeline progress is streamed back into the message caption while the analysis runs.
Layout
src/tg_bot/ — package, organized as 4 subpackages + a small number of single-concept files at parent level. Each subpackage has a documented membership rule; the parent-level files are leaf primitives that don't fit into any single subpackage's concept.
src/tg_bot/
├── __init__.py
├── __main__.py # python -m tg_bot
├── app.py # PTB Application + BOT_COMMANDS + lifecycle hooks
├── config.py # env-driven Config (read once at process start)
├── auth.py # authorize TypeHandler (group=-1 gate)
├── validation.py # yfinance ticker check + shared TICKER_RE
├── history.py # disk reader for past tradingagents logs
├── digest.py # /digest picker UI builder (no I/O, no globals)
├── market_calendar.py # per-ticker exchange-session gate (exchange_calendars)
│
├── storage/ # JSON persistence — terminal in the dep DAG
│ ├── _base.py # JsonStorage (atomic + fsync)
│ ├── watchlist.py # WatchlistStorage singleton
│ └── user_config.py # UserConfigStorage singleton (digest schedule + email mirror opt-in)
│
├── handlers/ # PTB handlers — register dispatch surfaces
│ ├── commands.py # slash commands (/add, /watch, /list, /email, etc.)
│ ├── callbacks.py # prefix-dispatched callback handlers
│ ├── analysis_runner.py # manual /watch + digest fan-out orchestration
│ └── pickers.py # shared keyboard/response builders for commands+callbacks
│
├── pipeline/ # LLM execution hot path
│ ├── analysis.py # run_trading_analysis + GraphPool + .env overlay (build_config)
│ ├── cache.py # same-day result cache, keyed by AnalysisConfigKey
│ ├── config_key.py # AnalysisConfigKey (frozen) — slug/caption/title
│ └── progress.py # cancel-aware LangChain callback
│
└── rendering/ # data → user-visible output
├── formatters.py # HTML + MarkdownV2 captions (Invariant #4)
├── telegraph_client.py # Telegraph publish (offloaded + resilient)
├── email_client.py # digest email mirror via Resend (opt-in)
└── chart.py # finviz URL builder
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.
- 2mo ago First seen · 262 lines · 9,679 tokens per session scan A de569d80cd68
TradingAgents-Telegram CLAUDE.md is an instructions file published in the GitHub repository IvanWng97/TradingAgents-Telegram (47 stars, last pushed 2mo ago), licensed MIT. It adds 9,679 tokens to every session, about $0.0387 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.
TradingAgents-Telegram CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| TradingAgents-Telegram CLAUDE.mdIvanWng97/TradingAgents-Telegram | Instructions file | 47 | 2mo ago | MIT | A | 9,679 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |