What is opentui AGENTS.md?

Repository instructions for OpenTUI, a toolkit for building text-based apps in a terminal. They describe engineering practices, supported runtimes, formatting, testing, and handling native resources.

Use them when modifying the OpenTUI codebase, running its Bun commands, writing regression tests, formatting code, or checking resource cleanup and terminal text widths.

They give the coding agent the project's local rules, helping changes fit the repository and avoid mistakes across TypeScript, Zig, and framework code.

opentui AGENTS.md — Instructions file by anomalyco

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/anomalyco/opentui/agents-md

Clone the repo

git clone --depth 1 https://github.com/anomalyco/opentui

Made for: Codex, OpenCode.

Per session 958 This file is loaded in full into every session.

When invoked 958 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	$0.00958	$0.00958
Opus 5	$0.00479	$0.00479
Sonnet 5	$0.00192	$0.00192
Haiku 4.5	$0.00096	$0.00096

Measured 3d ago against content hash 506ce119580e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opentui 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 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.

AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenTUI Agent Guide

Engineering

Reuse existing seams; do not duplicate policy, ownership, or state across TypeScript, Zig, and framework layers.
For bug fixes, first add a focused regression test of observable behavior or invariants. If automation is impossible, record the evidence and remaining manual verification; do not substitute contract sketches or guesses.
Make native ownership explicit; clean up handles, callbacks, buffers, and listeners on every exit path. Bound input-driven work and test lifecycle failures.
Do not interchange byte lengths, code points, graphemes, and terminal display-cell widths.
oxfmt is the formatting source of truth (semi: false, printWidth: 120); avoid unrelated formatting churn.

Tooling And Runtimes

Use Bun for dependency management and development commands: bun install, bun run <script>, bun test, and bun <file>.
Run package scripts from the package directory unless the script is defined at the repository root.
Shared runtime code must preserve the supported Bun and Node paths. Keep runtime-specific behavior behind existing platform/runtime/build seams; do not introduce Bun-only APIs into shared modules. Node checks use the minimum version enforced by scripts/node26.mjs.

Verification

Run the narrowest relevant test first, then the affected package suite.
Ordinary TypeScript source changes do not require the root build. Use the affected package's test, typecheck, build, or validation scripts as applicable.
Run bun run build from the repository root after native or cross-package build/output changes, or when tests report a missing/stale native artifact. It does not build web or examples; use their package scripts.
For native changes, run bun run test:native from packages/core. Filter with bun run test:native -Dtest-filter="test name" while iterating.
For runtime, FFI, build, or export changes, run the relevant Node and packed-distribution scripts from that package (such as test:js:node or test:dist) when present.
Use root bun run fmt:check and bun run lint for final static checks when relevant.

Read the full file on GitHub · 56 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.

3d ago First seen · 56 lines · 958 tokens per session scan A 506ce119580e

Subscribe to this mod's changes

opentui AGENTS.md is an instructions file published in the GitHub repository anomalyco/opentui (13,206 stars, last pushed yesterday), licensed MIT. It adds 958 tokens to every session, about $0.0048 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.

opencode opentui tui

opentui AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

OpenTUI Agent Guide

Engineering

Tooling And Runtimes

Verification

What this file has done since we first saw it

Other instructions, from other repositories

critique AGENTS.md

Monoloth AGENTS.md

goder AGENTS.md

plannotator AGENTS.md

golembot CLAUDE.md

solo AGENTS.md