shadow-tg CLAUDE.md

shadow-tg CLAUDE.md is an instructions file for coding agents from ulinycoin/shadow-tg. It costs 585 tokens per session, scanned A, original, MIT.

Project instructions for Shadow TG, a tool server for reading Telegram channel information. Telegram is a messaging service, and a channel is a feed where posts are published to subscribers.

In plain words
What is it for?
It helps retrieve channel details, posts, media links, comments, search results, and basic channel quality measures such as subscribers and engagement.
Why use it?
It gives a coding agent the project structure, setup facts, and available operations in one place. This reduces guesswork when changing or using the project.

Instructions file

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/ulinycoin/shadow-tg/claude-md
Clone the repo
git clone --depth 1 https://github.com/ulinycoin/shadow-tg

Wrote 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.

agentmods badge for shadow-tg CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ulinycoin/shadow-tg/claude-md.svg)](https://agentmods.dev/instructions/ulinycoin/shadow-tg/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ulinycoin/shadow-tg/claude-md"><img src="https://agentmods.dev/badge/instructions/ulinycoin/shadow-tg/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 585 This file is loaded in full into every session.
When invoked 585 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 $0.00585 $0.00585
Opus 5 $0.00293 $0.00293
Sonnet 5 $0.00117 $0.00117
Haiku 4.5 $0.00059 $0.00059

Measured 4d ago against content hash def42bb8b035, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shadow-tg 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 4d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shadow-tg

Telegram channel tools for AI agents — part of the Shadow product line. No MTProto, no Telethon.

Tools (9)

Tool What it does
get_channel(channel) Channel metadata: subscribers_raw, title, description
get_posts(channel, limit?, before?) Post feed with pagination
get_post(channel, post_id) Single post
get_media(channel, post_id) CDN photo/video URLs
get_comments(channel, post_id, limit?, before?, after?) Comments (history + live-tail)
resolve_channel(query) Check if channel exists
search_channels(query, limit?, verify?) Search channels via DuckDuckGo
inspect_channels(channels, min_subscribers?, min_median_views?, stale_after_days?) Channel quality: subscribers_raw, median_views, engagement, flags (stale, low_engagement, tiny, etc.)
search_posts(channel, query, limit?) Search recent posts (~100, client-side)

Structure

src/tg_mcp/
  server.py            # FastMCP entry point + all tools
  tme_parser.py        # t.me/s parsing: posts, channel, media
  comment_parser.py    # Comments + loadComments API
  channel_search.py    # DuckDuckGo search
  channel_quality.py   # inspect_channel_html + engagement_flags
  cache.py             # TTL cache at /tmp/tg-mcp-cache

Setup

git clone https://github.com/ulinycoin/shadow-tg.git
cd shadow-tg
python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

Useful facts

  • mcp.run() starts the stdio server. main() is the entry point.
  • Python >= 3.10. Dependencies: lxml, httpx, mcp, ddgs.
  • Cache at /tmp/tg-mcp-cache/ (TTL 5 min). Debug: rm -f /tmp/tg-mcp-cache/*.json
  • All channel names are normalized: @, t.me/, t.me/s/ prefixes are stripped.
  • search_channels(verify=True) is slow (N HTTP requests) but gives subscribers_raw + median_views.
  • inspect_channels() is the batch version, 5 concurrent requests.
  • Channels flagged stale sort below active ones.
  • subscribers_raw is a string like on t.me/s (2.54M, 11.5K). Don't confuse with int.
  • subscribers is int, may be None. Use subscribers_raw for display.

Read the full file on GitHub · 51 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. 4d ago First seen · 51 lines · 585 tokens per session scan A def42bb8b035

Subscribe to this mod's changes

shadow-tg CLAUDE.md is an instructions file published in the GitHub repository ulinycoin/shadow-tg (0 stars, last pushed 1mo ago), licensed MIT. It adds 585 tokens to every session, about $0.0029 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 2026-08-31.

Related

Other instructions, from other repositories