What is lavish-axi AGENTS.md?

Repository instructions for Lavish Axi, a JavaScript and TypeScript project with a command-line tool, browser assets, tests, and a generated skill file.

Use them to build, lint, format-check, type-check, test, or run the project's optional real-browser tests while following its packaging conventions.

They define the supported commands and checks, helping agents avoid stale generated files and incomplete validation.

How kunchenguid/lavish-axi configures Claude Code and Codex

About the project

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.

kunchenguid/lavish-axi · 3,329 stars · on GitHub

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/kunchenguid/lavish-axi/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/kunchenguid/lavish-axi

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kunchenguid/lavish-axi/agents-md.svg)](https://agentmods.dev/instructions/kunchenguid/lavish-axi/agents-md)

Your own site

<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="Measured on agentmods" height="20"></a>

Per session 18,391 This file is loaded in full into every session.

When invoked 18,391 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.18391	$0.18391
Opus 5	$0.09196	$0.09196
Sonnet 5	$0.03678	$0.03678
Haiku 4.5	$0.01839	$0.01839

Measured yesterday against content hash 408f3977be0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

lavish-axi AGENTS.md scanned grade C with 1 finding 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 yesterday.

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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

The transform makes **no outbound requests** (no fetching, no SSRF); its only security surface is local file reading, which is confined to the artifact directory both lexically (`confineDir`) and by **real-path/symlink r

AGENTS.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents when working with code in this repository.

Commands

pnpm run check          # Run build, lint, format check, typecheck, tests, and skill freshness check
pnpm run build          # Bundle dist/cli.mjs and copy chrome/design assets into dist
pnpm run build:skill    # Regenerate the minimal skills/lavish/SKILL.md stub 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 mode)

Run a single test file: node --test test/server.test.js. Filter by test name: node --test --test-name-pattern "createOpenOutput" test/cli-output.test.js. Run the opt-in real-browser suites: LAVISH_AXI_BROWSER_E2E=1 node --test test/layout-audit-browser.test.js test/layout-warning-inbox.browser.test.js (requires chrome-devtools-axi). Run the seven-tab connection-pool regression: LAVISH_AXI_BROWSER_E2E=1 node --test test/event-transport.browser.test.js.

The prepack and prepare scripts both run build automatically, so publishing always ships a fresh bundle and git-based installs (which run prepare) get a built dist/. The committed skills/lavish/SKILL.md is generated by pnpm run build:skill; pnpm run check fails if it drifts from createSkillMarkdown(). The committed root plugin.json is generated by pnpm run build:plugin from package.json; pnpm run check fails if it drifts, and release-please bumps its version through extra-files.

Project Conventions

Node 22+, ESM-only JavaScript ("type": "module"). No TypeScript source - .js files validated via TS checkJs.
Use TDD for bug fixes and new features (see test-driven-development skill).
Run pnpm run check before pushing.
Treat repo-provided .agents/ skill content as vendored; Prettier intentionally ignores it.
Do not hand-edit CHANGELOG.md or .release-please-manifest.json - release-please owns them.
Human-authored PRs to main must go through no-mistakes (>= 1.46.0); the Require no-mistakes gate enforces both the deterministic signature and the no-mistakes-pipeline-attestation:v1 comment, requiring review/test/document to be completed and the attested head_sha to equal the PR's current head. .github/workflows/no-mistakes-required.yml is a thin caller of the shared kunchenguid/no-mistakes/.github/actions/require-no-mistakes composite action, pinned to an immutable commit SHA and never @main. Enforcement logic and its tests live upstream in the no-mistakes repository - change enforcement there rather than copying it back here, and bump this repo's pin in a deliberate separate PR. This repo still owns its on:, paths-ignore, concurrency, permissions, job name, and author-exemption if:. A PR whose body no-mistakes did not rewrite for the current head going red is the attestation contract, not a flake. See CONTRIBUTING.md.

Read the full file on GitHub · 274 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.

yesterday Changed · +1 lines · +79 tokens per session 408f3977be0e
7d ago First seen · 273 lines · 18,312 tokens per session scan C 5499c485168a

Subscribe to this mod's changes

lavish-axi AGENTS.md is an instructions file published in the GitHub repository kunchenguid/lavish-axi (3,329 stars, last pushed yesterday), licensed MIT. It adds 18,391 tokens to every session, about $0.0920 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 5,182 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

lavish-axi: Instructions file for Claude Code