Borrowing it
Nothing to install: this file belongs to nullnumber1/Telegram-Community-MCP. 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/nullnumber1/Telegram-Community-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/nullnumber1/Telegram-Community-MCPWrote 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/nullnumber1/telegram-community-mcp/claude-md)<a href="https://agentmods.dev/instructions/nullnumber1/telegram-community-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nullnumber1/telegram-community-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00518 | $0.00518 |
| Opus 5 | $0.00259 | $0.00259 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
Telegram-Community-MCP 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 7d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — agent instructions
Development commands
Run tests
uv run pytest -x -v
Linting and formatting
uv run ruff check . --fix uv run ruff format .
Test MCP server locally
uv run mcp dev server.py
Architectural decisions
- Telethon: strictly v1.42.x. DO NOT use v2 alpha. Parameter is
api_hash, NOTapi_secret. - MCP FastMCP: import ONLY from
mcp.server.fastmcp. NOT from standalonefastmcppackage. - sqlite-vec: KNN query MUST contain
k = N. Without it — OperationalError. - SentenceTransformer.encode(): parameter
normalize_embeddings=True, NOTreturn_tensors. - All paths in claude_desktop_config.json must be absolute.
- DB always in WAL mode:
PRAGMA journal_mode=WAL. - Message ID: composite
chat_id * 10_000_000_000 + message_idto avoid cross-chat collisions. - Semantic search is two-phase: coarse Hamming KNN over
vec_messages_bin(binarybit[384], ~32x smaller, kills cold-scan latency) then exact fp32 rerank overvec_messages. Both tables are dual-written on insert. Rerank MUST fetch fp32 via per-id point lookups (message_id = ?), NOTIN (...)— vec0 full-scans an IN-list (~14x slower). Build the bit index from existing fp32 without re-embedding:python scripts/ingest.py --build-binary.
Project structure
src/db.py — DB initialization, CRUD, FTS queries, sqlite-vec queries src/embedder.py — model loading, embed(texts) -> np.ndarray src/telegram.py — TelegramClient wrapper, iter_messages with checkpoint src/search.py — hybrid search: FTS + KNN + RRF fusion server.py — FastMCP entry point, tool definitions scripts/auth.py — first-time Telegram authorization scripts/ingest.py — full import / incremental import via --chat-id scripts/list_chats.py — list all account dialogs
What NOT to do
- Do NOT index media files, stickers, polls — only message.text
- Do NOT use transport="sse" — only transport="stdio"
- Do NOT store api_hash or session in git
- Do NOT make sync synchronous — it must be async
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.
- 7d ago First seen · 43 lines · 518 tokens per session scan A 2ee8f929dc3f
Telegram-Community-MCP CLAUDE.md is an instructions file published in the GitHub repository nullnumber1/Telegram-Community-MCP (2 stars, last pushed 3mo ago), licensed MIT. It adds 518 tokens to every session, about $0.0026 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.
Other instructions, from other repositories
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.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.