fenestra: Instructions file for Codex

AGENTS.md

fenestra AGENTS.md is an instructions file for Codex, OpenCode from richer-richard/fenestra. It costs 3,064 tokens per session, scanned A, original, Apache-2.0.

A development guide for building Fenestra user interfaces, or UIs, without needing a display server. It uses a test harness to drive the real app, renders views to images, and locks finished layouts with golden tests—saved reference images for comparison.

In plain words
What is it for?
Writing Fenestra views, testing them through semantic queries instead of screen coordinates, checking accessibility structure and messages, rendering previews, and creating visual regression tests.
Why use it?
A UI may behave correctly while still having clipped text, poor spacing, or structural problems. Headless interaction and image rendering make those issues testable and visible during development.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is richer-richard/fenestra's own configuration. It tells Codex and OpenCode how to work on fenestra itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fenestra configures →

Reuse

Borrowing it

Nothing to install: this file belongs to richer-richard/fenestra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/richer-richard/fenestra/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/richer-richard/fenestra

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for fenestra AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/richer-richard/fenestra/agents-md/github.svg)](https://agentmods.dev/instructions/richer-richard/fenestra/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/richer-richard/fenestra/agents-md"><img src="https://agentmods.dev/badge/instructions/richer-richard/fenestra/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.

agentmods 80×15 button for fenestra AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/richer-richard/fenestra/agents-md"><img src="https://agentmods.dev/badge/instructions/richer-richard/fenestra/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,064 This file is loaded in full into every session.
When invoked 3,064 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03064 $0.03064
Opus 5 $0.01532 $0.01532
Sonnet 5 $0.00613 $0.00613
Haiku 4.5 $0.00306 $0.00306

Measured 9d ago against content hash ef32033ffde0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fenestra 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 9d 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 · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building fenestra UIs as an agent

fenestra is designed so that an agent authoring a UI can see and verify its work without a display server. This file is the working manual.

The loop

  1. Write a view (or a full App).
  2. Drive it with the harness — semantic queries, not coordinates — and assert structure and messages.
  3. Render it headlessly to a PNG. Open and look at the PNG. Layout bugs, clipped text, and bad spacing are visible; do not skip this.
  4. Iterate until it looks right, then lock it with a golden test.
use fenestra::prelude::*;
use fenestra::shell::render_element;

let view: Element<()> = col().p(SP6).gap(SP4).children([
    text("Hello").size(TextSize::Xl2).weight(Weight::Semibold),
    button("Save").into(),
]);
let image = render_element(view, &Theme::light(), (480, 240));
image.save("preview.png").unwrap(); // now actually look at it

Headless rendering is deterministic: embedded Inter fonts, scale 1.0, reduced motion, in-memory clipboard. The same tree renders the same pixels on every machine of the same GPU class (cross-rasterizer runs use a small tolerance; see Golden tests).

Driving a real app: the harness

Harness runs the full Elm loop — dispatch, state, focus, editing — driven by semantic queries (find things the way a user would; never hardcode coordinates):

use fenestra::prelude::*;
use fenestra::shell::Harness;

let mut h = Harness::new(MyApp::default(), Theme::light(), (800, 600));
h.click(&by::role(Semantics::Button).name("Add"));   // strict: 0 or 2+ matches panic
h.type_text("hello");                                 // into the focused input
h.key(KeyInput::plain(Key::Enter));

assert_eq!(h.app().items.len(), 1);                   // state
assert!(h.query(&by::label("hello")).is_some());      // structure (None = absent)
let msgs = h.take_messages();                          // behavior: what the UI emitted
h.render().save("after.png").unwrap();                 // pixels — now look at it

Read the full file on GitHub · 251 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.

  1. 9d ago First seen · 251 lines · 3,064 tokens per session scan A ef32033ffde0

Subscribe to this mod's changes

fenestra AGENTS.md is an instructions file published in the GitHub repository richer-richard/fenestra (12 stars, last pushed 26d ago), licensed Apache-2.0. It adds 3,064 tokens to every session, about $0.0153 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens