What is and-scene AGENTS.md?

A project-specific instruction file for And Scene, a toolkit for building animated browser presentations with React. It describes the project layout, browser inspection tools, workflow, and change rules.

Creating or modifying animated browser presentations, using the reusable React scene kit, running builds, capturing screenshots, and inspecting visual quality.

It gives the coding agent the context and checks needed to edit presentation scenes consistently.

and-scene AGENTS.md — Instructions file by Codagent-AI

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/codagent-ai/and-scene/agents-md

Clone the repo

git clone --depth 1 https://github.com/Codagent-AI/and-scene

Made for: Codex, OpenCode.

Per session 741 This file is loaded in full into every session.

When invoked 741 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	$0.00741	$0.00741
Opus 5	$0.00370	$0.00370
Sonnet 5	$0.00148	$0.00148
Haiku 4.5	$0.00074	$0.00074

Measured 2d ago against content hash 8596e0279321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

and-scene 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

And Scene

And Scene is an Agent Skill for building animated, morphing browser presentations. This repository contains the distributable skill, its reusable React scene kit, scaffold templates, and the worked reference presentation.

Project Map

skills/presentation/SKILL.md: agent-facing presentation workflow and quality bar
skills/presentation/templates/bootstrap/: complete app scaffold copied into new projects
skills/presentation/templates/presentation/: files for an additional presentation
src/presentation-kit/: canonical vendored React scene kit
src/presentations/: reference presentations and registry
scripts/verify.mjs: deterministic build and browser-render verification
scripts/inspect-presentation.mjs: screenshot capture and visual-quality diagnostics
openspec/: current behavioral specifications and historical changes

Browser Tooling

Use chrome-devtools-axi for agent-driven browser inspection and debugging. It is installed in the evaluation sandbox and provides a concise CLI over Chrome DevTools:

chrome-devtools-axi open http://127.0.0.1:5173/
chrome-devtools-axi snapshot
chrome-devtools-axi screenshot /tmp/and-scene.png

Start with snapshot to inspect page structure, then use screenshots for visual composition. Inspect the first, last, and dense or visually important steps; also inspect a narrow viewport when the presentation is responsive-sensitive. Use chrome-devtools-axi --help for the full command list. Do not invoke the underlying Chrome DevTools MCP server directly when AXI is available.

Keep deterministic project verification in the repository's Playwright-backed scripts. AXI is the interactive inspection interface; npm run verify remains the automated browser gate.

Development Workflow

npm ci
npm test           # Vitest unit and contract tests
npm run lint       # ESLint
npm run build      # TypeScript and production build
npm run verify     # build plus browser-render verification
npm run inspect -- how-to-make-a-presentation

Read the full file on GitHub · 81 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 · 81 lines · 741 tokens per session scan A 8596e0279321

Subscribe to this mod's changes

and-scene AGENTS.md is an instructions file published in the GitHub repository Codagent-AI/and-scene (5 stars, last pushed 3d ago), licensed MIT. It adds 741 tokens to every session, about $0.0037 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.

Browser automation Frontend Productivity

and-scene AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

And Scene

Project Map

Browser Tooling

Development Workflow

What this file has done since we first saw it

Other instructions, from other repositories

Browser4 CLAUDE.md

spring-ai-agentcore AGENTS.md

flyto-core CLAUDE.md

deckforge AGENTS.md

fast-browser CLAUDE.md

agentoscope AGENTS.md