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 instructions/mycrl/turn-rs/agents-mdgit clone --depth 1 https://github.com/mycrl/turn-rsWrote 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/mycrl/turn-rs/agents-md)<a href="https://agentmods.dev/instructions/mycrl/turn-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/mycrl/turn-rs/agents-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 | $0.03098 | $0.03098 |
| Opus 5 | $0.01549 | $0.01549 |
| Sonnet 5 | $0.00620 | $0.00620 |
| Haiku 4.5 | $0.00310 | $0.00310 |
Grade A, and why
turn-rs 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 today.
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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document targets two audiences:
- LLMs/agents: quickly understand project structure, entry points, run flow, configuration, and risks.
- Human developers/operators: follow the steps to build, configure, start, and verify the service.
Project Overview
turn-rs is a TURN/STUN server implemented in Rust for WebRTC NAT traversal and media relay. It focuses on high performance and low configuration cost, and provides optional gRPC management APIs, Prometheus metrics, and Hook callbacks.
Core Capabilities
- TURN/STUN protocol support with TCP/UDP transport.
- Long-term credential mechanism with static users and hook-based dynamic auth.
- Optional gRPC management API and Prometheus metrics exporter.
- Multi-interface listeners and external address announcement.
Key Entry Points and Directories
- Runtime entry: src/main.rs
- Library entry: src/lib.rs
- Service and session logic: src/service
- Protocol handling and codecs: src/codec
- Transport providers (UDP/TCP): src/server/provider
- Config and logging: src/config.rs, src/logger.rs
- gRPC API and client SDK: sdk/protos/server.proto, sdk/src/lib.rs
- Sample config: turn-server.toml
- Docs entry: docs/README.md
Source Code Architecture (Modules and Responsibilities)
This section explains how the server is organized internally and how the main data flow works.
High-level runtime flow
-
src/main.rs loads config, initializes logging, and builds the Tokio runtime.
-
src/lib.rs
start_server()constructsStatistics, aHandler, and aService, then spawns:
- transport servers (UDP/TCP) via src/server
- optional Prometheus exporter via src/prometheus.rs
- optional gRPC API via src/api.rs
Core modules
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.
- today Changed · +3 lines · +2 tokens per session e226a3f97840
- 6d ago First seen · 287 lines · 3,096 tokens per session scan A a1803b6e7d01
turn-rs AGENTS.md is an instructions file published in the GitHub repository mycrl/turn-rs (510 stars, last pushed yesterday), licensed MIT. It adds 3,098 tokens to every session, about $0.0155 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 instructions, from other repositories
chroma CLAUDE.md
Claude Code instructions for chroma-core/chroma, covering chroma codebase guidelines, commit message style, 50/72 rule and tilt-backed tests.
chroma AGENTS.md
AGENTS.md instructions for chroma-core/chroma: See CLAUDE.md for codebase conventions (commit message format, etc.).
lmnr CLAUDE.md
Claude Code instructions for lmnr-ai/lmnr, covering claude.md, project overview, repository structure, development commands and frontend (next.js).
start-technologies AGENTS.md
AGENTS.md instructions for Start9Labs/start-technologies, covering agents.md, layout, build & test (run from the repo root), branches and channels and releases.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
azure-sdk-for-rust github-pullrequest.instructions.md
Instructions for Azure/azure-sdk-for-rust, covering instructions for github pull requests and code requirements.