What is tuitube AGENTS.md?

Project-specific instructions for AI coding agents working on tuitube, a Go application with a text-based user interface. They describe where screens and commands belong and how the project is checked.

Adding screens and keyboard commands, connecting them to the application, recording important events, and running the project's tests and build.

They reduce guesswork when adding features by documenting the existing structure, logging approach, and required checks.

tuitube AGENTS.md — Instructions file by gitcoder89431

Install

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.

agentmods

npx agentmods add instructions/gitcoder89431/tuitube/agents-md

Clone the repo

git clone --depth 1 https://github.com/gitcoder89431/tuitube

Made for: Codex, OpenCode.

Per session 1,807 This file is loaded in full into every session.

When invoked 1,807 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01807	$0.01807
Opus 5	$0.00903	$0.00903
Sonnet 5	$0.00361	$0.00361
Haiku 4.5	$0.00181	$0.00181

Measured 2d ago against content hash 4784c02e91c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tuitube 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 2d 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.

AGENTS.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents working in projects based on this template.

Project Intent

This is a personal Go TUI template built on the Charm stack (Bubble Tea v2, Lip Gloss v2, Bubbles). Treat the existing structure as the application shell — build product features on top of it, don't bypass the patterns it establishes.

Checklist for Adding a New Feature

Follow these steps in order. Run the verification commands before finishing.

Add a screen in internal/screens/ implementing the screens.Screen interface (Init, Update, View, Title, KeyBindings).
Register the screen in internal/app/app.go → registerScreens. Add its ID to the preferred slice in refreshScreenOrder if it belongs in the primary sidebar.
Register a command in registerCommands (same file) so the screen is reachable via ctrl+k. Command Run functions must return a tea.Cmd that emits a message defined in internal/app/messages.go.
Log key events via logs.Info / logs.Error so behavior is visible in the Logs screen (see Logging section below).
Verify: go test ./... and go build ./cmd/tuitube must pass before committing.

Key Packages

Package	Role
`internal/app`	Root model — routing, overlays, keymap, theme, message dispatch
`internal/screens`	Feature screens implementing `screens.Screen`
`internal/commands`	Command palette entries and registry
`internal/app/messages.go`	All app-level message types — add new ones here
`internal/debug`	In-memory log surfaced in the Logs screen
`internal/theme`	Semantic styles and theme definitions
`internal/layout`	Terminal size and region calculations

Logging

Always log via internal/debug.Log — never fmt.Println or panic. Use the prefix convention package.Operation so log entries are easy to grep.

// info
logs.Info("myscreen.Load: loaded 42 items")

// error
logs.Error("myscreen.Load", err)
// produces: "ERROR myscreen.Load: <err message>"

Read the full file on GitHub · 216 lines

Changes

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.

2d ago First seen · 216 lines · 1,807 tokens per session scan A 4784c02e91c0

Subscribe to this mod's changes

tuitube AGENTS.md is an instructions file published in the GitHub repository gitcoder89431/tuitube (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,807 tokens to every session, about $0.0090 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.

Databases Languages Testing bubbletea go lipgloss mpv sqlite tui

tuitube AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Project Intent

Checklist for Adding a New Feature

Key Packages

Logging

What this file has done since we first saw it

Other instructions, from other repositories

bagent AGENTS.md

zot AGENTS.md

pvetui AGENTS.md

waveloom AGENTS.md

pvetui CLAUDE.md

ssm AGENTS.md