Lavish is a local editor for HTML files produced by coding agents, letting people inspect elements, edit Mermaid diagrams, and send targeted feedback. It supports human review of interactive HTML artifacts during agent-assisted work. The catalogue add-ons help agents discover and use Lavish.
Borrowing it
Nothing to install: this file belongs to kunchenguid/lavish-axi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kunchenguid/lavish-axi/main/AGENTS.mdgit clone --depth 1 https://github.com/kunchenguid/lavish-axiWrote 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/kunchenguid/lavish-axi/agents-md)<a href="https://agentmods.dev/instructions/kunchenguid/lavish-axi/agents-md"><img src="https://agentmods.dev/badge/instructions/kunchenguid/lavish-axi/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.
<a href="https://agentmods.dev/instructions/kunchenguid/lavish-axi/agents-md"><img src="https://agentmods.dev/badge/instructions/kunchenguid/lavish-axi/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.05263 | $0.05263 |
| Opus 5.5 | $0.02105 | $0.02105 |
| Sonnet 5.5 | $0.01053 | $0.01053 |
| Haiku 4.5 | $0.00526 | $0.00526 |
Grade A, and why
lavish-axi 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 18d 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is loaded every session. It keeps only rules that apply to almost every change. Detail lives in the doc that owns it.
- README.md owns the user-facing contract: features, CLI flags, environment variables, keyboard shortcuts, export and share, and session-end etiquette.
- CLI output owns what agents are told while using Lavish:
lavish-axi --help,lavish-axi design, andlavish-axi playbook <id>(src/cli.js,src/design-reference.js,src/playbooks.js). The generated skill (src/skill.jstoskills/lavish/SKILL.md) stays a stub that points at those commands. Do not copy CLI-owned instructions into the skill. - VISION.md owns the acceptance policy. Change it only through the author.
- docs/invariants.md owns architecture internals, security rationale, and easy-to-reintroduce failure modes. Read the section for the area you are editing before changing it.
- Update the owner when a contract changes. Edit this file only when an every-session rule changes.
Commands
pnpm run check # build, lint, format check, typecheck, tests, and skill freshness
pnpm run build # bundle dist/cli.mjs and copy chrome/design assets into dist
pnpm run build:skill # regenerate skills/lavish/SKILL.md from src/skill.js
pnpm test # node:test runner (test/*.test.js)
pnpm run lint # ESLint over bin src test scripts
pnpm run format:check # Prettier check
pnpm run typecheck # tsc --noEmit (checkJs)
One file: node --test test/server.test.js. One name: node --test --test-name-pattern "createOpenOutput" test/cli-output.test.js.
Opt-in browser suites need chrome-devtools-axi: LAVISH_AXI_BROWSER_E2E=1 node --test test/layout-audit-browser.test.js test/layout-warning-inbox.browser.test.js.
Seven-tab pool regression: LAVISH_AXI_BROWSER_E2E=1 node --test test/event-transport.browser.test.js.
prepack and prepare both run build. pnpm run check fails if skills/lavish/SKILL.md drifts from createSkillMarkdown(), or if root plugin.json drifts from pnpm run build:plugin. Release-please bumps plugin.json through extra-files.
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.
- 18d ago Changed · +1 lines · +48 tokens per session c7583cac87b8
- 29d ago Changed · -144 lines · -16,163 tokens per session scan C → A d3416864bcd8
- 1mo ago Changed · +676 tokens per session 3a2deca11c81
- 1mo ago Changed · +1 lines · +176 tokens per session 97ef7b382ab5
- 1mo ago Changed · +5 lines · +330 tokens per session 819b7e01c52c
- 1mo ago Changed · +1 lines · +246 tokens per session b182e402510c
- 1mo ago Changed · +1 lines · +885 tokens per session 2fa332208f43
- 1mo ago Changed · +2 lines · +602 tokens per session 481ad78ca18e
- 1mo ago Changed · +1 lines · +72 tokens per session c9660a3a7523
- 1mo ago First seen · 274 lines · 18,391 tokens per session scan C 408f3977be0e
lavish-axi AGENTS.md is an instructions file published in the GitHub repository kunchenguid/lavish-axi (4,302 stars, last pushed yesterday), licensed MIT. It adds 5,263 tokens to every session, about $0.0211 per session on Opus 5.5. 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.