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.
npx agentmods add rules/groupultra/telegram-search/architecturegit clone --depth 1 https://github.com/groupultra/telegram-searchWrote 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/rules/groupultra/telegram-search/architecture)<a href="https://agentmods.dev/rules/groupultra/telegram-search/architecture"><img src="https://agentmods.dev/badge/rules/groupultra/telegram-search/architecture.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 | $0.02756 | $0.02756 |
| Opus 5 | $0.01378 | $0.01378 |
| Sonnet 5 | $0.00551 | $0.00551 |
| Haiku 4.5 | $0.00276 | $0.00276 |
Grade A, and why
architecture 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 344 lines · 2,756 tokens per session scan A 454cf96d3e7c
architecture is a cursor rule published in the GitHub repository groupultra/telegram-search (4,087 stars, last pushed yesterday), licensed AGPL-3.0. It adds 2,756 tokens to every session, about $0.0138 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.
Other cursor rules, from other repositories
database
Database, embeddings, and chunking patterns for Textrawl.
pinecone_intelligent_filtering
Comprehensive guide for implementing intelligent Pinecone filtering with LangChain, LCEL chains, and Pydantic models for production-grade vector search systems.
vectorization-defaults
This rule helps prevent common search and indexing issues by ensuring that content is properly vectorized and stored in Weaviate.
use-mcp-server-qdrant
Grounded Vibe Coding with Model Context Protocol and Qdrant.
AGNO_VectorDB_Integration
AGNO, Python, vector databases, and AI-powered knowledge management systems.
decision-database-chromadb
Decision Date: 2025-12-16 (afternoon - REVISED after comprehensive benchmarking) Status: ✅ Complete (Developer Action Item 00) Impact: Critical - Foundational for all semantic search implementation.