Borrowing it
Nothing to install: this file belongs to philogicae/torrent-search-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/philogicae/torrent-search-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/philogicae/torrent-search-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/philogicae/torrent-search-mcp/agents-md)<a href="https://agentmods.dev/instructions/philogicae/torrent-search-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/philogicae/torrent-search-mcp/agents-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/philogicae/torrent-search-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/philogicae/torrent-search-mcp/agents-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 | $0.00911 | $0.00911 |
| Opus 5.5 | $0.00364 | $0.00364 |
| Sonnet 5.5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
torrent-search-mcp AGENTS.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 10d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Audience. AI agents working inside the torrent-search-mcp repository.
Project overview
Torrent search MCP server - a Python-based torrent search service with MCP (Model Context Protocol) API, a static HTML frontend, and Telegram integration.
torrent_search/mcp_server.py: MCP tools (FastMCP) and the untrusted-data fencing of scraped output.torrent_search/api_server.py: REST API, Web UI hosting, Telegram auth and forward endpoints.torrent_search/wrapper/parser.py: per-source parsers (fetch + normalize to the shared CSV text pipeline).torrent_search/wrapper/scraper.py:WEBSITESregistry, search/popular orchestration, per-source popular caches.torrent_search/wrapper/api_client.py:TorrentSearchApifacade used by the MCP tools and the CLI (caches, magnet resolution).torrent_search/wrapper/models.py:Torrentmodel, id/field validation.telegram_auth.py: session store, pairing challenges, rate limiter.utils.py: magnet pruning, encoding helpers.torrent_search/static/index.html: the whole frontend (inline CSS/JS, no build step; minified when served).
Setup commands
- Lint/format:
uv run ruff format && uv run ruff check --fix - Typecheck:
uv run ty check - Tests (100% coverage gate):
uv run pytest -n 2 --dist worksteal --cov=torrent_search --cov-fail-under=100 - Full local pipeline:
./dev.sh(lock+sync, ruff, ty, prettier on md/html, then pytest - prettier runs before the tests because the served page is minified fromindex.html) - Never run destructive docker commands against volumes (
torrent-search-dataholds auth tokens) - Deploy:
docker compose up -d --build torrent-search-api torrent-search-mcp(rebuild required for static changes; plainrestartreuses the old image)
Testing instructions
- 100% coverage gate enforced via
--cov-fail-under=100; CI runs ruff/ty/pytest on push. - Keep the suite hermetic against ambient env: the autouse
hermetic_envfixture pins the Telegram/prune constants (uv runauto-loads.env, which otherwise flips module constants and breaks assertions). playwright-cliverification standard: DOM snapshot + screenshot + console (+requests when network-relevant) recorded in the verification log with.playwright-cli/artifact paths (gitignored, local-only).approve.sh- helper to approve a Web UI pairing code viaPOST /telegram/auth/register.
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.
- 10d ago Changed · +8 lines · +226 tokens per session c2a8a21a1901
- 1mo ago Changed · -29 lines · -539 tokens per session 5a025c5467cc
- 1mo ago Changed 97eaebace140
- 1mo ago Changed · -7 tokens per session 9baed9b3336f
- 1mo ago First seen · 67 lines · 1,231 tokens per session scan A 362138c88ce0
torrent-search-mcp AGENTS.md is an instructions file published in the GitHub repository philogicae/torrent-search-mcp (43 stars, last pushed 11d ago), licensed MIT. It adds 911 tokens to every session, about $0.0036 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 2026-09-06.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.