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/largemodgames/spotatui/agents-mdgit clone --depth 1 https://github.com/LargeModGames/spotatuiWrote 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/largemodgames/spotatui/agents-md)<a href="https://agentmods.dev/instructions/largemodgames/spotatui/agents-md"><img src="https://agentmods.dev/badge/instructions/largemodgames/spotatui/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 | $0.09046 | $0.09046 |
| Opus 5 | $0.04523 | $0.04523 |
| Sonnet 5 | $0.01809 | $0.01809 |
| Haiku 4.5 | $0.00905 | $0.00905 |
Grade A, and why
spotatui 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.
This is a copy
97% identical to spotatui copilot-instructions.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
This file is maintained as three near-identical copies: CLAUDE.md, AGENTS.md, and
.github/copilot-instructions.md (only the opening lines differ). Edit all three together.
Build & Run
# Full build (native streaming + audio viz + Lua scripting + OS integrations)
cargo run
# Slim build - no librespot/audio/scripting; fastest iteration, one of CI's seven legs
cargo run --no-default-features --features telemetry,tui
# With the alternative sources (Local/Subsonic/Radio/YouTube/Qobuz). These are NOT
# in `default`, so a plain `cargo run` is Spotify-only; use the `all-sources` alias
# (or list them individually) to exercise the first-run source picker and playback.
cargo run --features all-sources
CI Checks (run before opening a PR)
cargo fmt --all
cargo clippy --no-default-features --features telemetry,tui -- -D warnings
cargo test --no-default-features --features telemetry,tui
These slim commands are the fast local gate, not the full picture. GitHub Actions
(.github/workflows/ci.yml) runs check, test, and clippy on ubuntu-latest
across a seven-leg feature matrix, plus one macos-latest job (below):
| Leg | Features |
|---|---|
default |
a plain cargo test: streaming + audio-viz-cpal + scripting + self-update + OS integrations |
all-sources |
the Linux release feature set from cd.yml (adds cover-art, mcp-server, ai-dj, audio-viz, all five sources) |
mcp-only |
telemetry,tui,mcp-server |
ai-dj-only |
telemetry,tui,ai-dj |
slim |
telemetry,tui |
headless |
telemetry - one of two legs without tui. mod tui is feature-gated, so this leg turns any crate::tui import from core/infra/cli into a compile error - what keeps a second frontend from silently re-coupling to the terminal one |
headless-streaming |
telemetry,streaming - check + clippy only, no test job. Proves native-streaming startup (runtime/streaming/) and the player-event wiring type-check and pass clippy with no terminal frontend in scope. Its two entry points carry allow(dead_code) there, so the leg does not prove they are live |
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 · +82 lines · +1,535 tokens per session 99fbb6d0da8d
- 4d ago First seen · 501 lines · 7,511 tokens per session scan A 27947f3495df
spotatui AGENTS.md is an instructions file published in the GitHub repository LargeModGames/spotatui (1,302 stars, last pushed yesterday), licensed MIT. It adds 9,046 tokens to every session, about $0.0452 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to spotatui copilot-instructions.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
spotify-mcp-server CLAUDE.md
Claude Code instructions for WisetechySolutions/spotify-mcp-server, covering claude.md, project overview, commands, architecture and rules.
wedeo CLAUDE.md
Claude Code instructions for sharifhsn/wedeo, covering wedeo - ffmpeg rust rewrite, project overview, philosophy, build & verify and debugging h.264 differences.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
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.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.