landingforge: Instructions file for Claude Code

CLAUDE.md

landingforge CLAUDE.md is an instructions file for Claude Code from NmadeleiDev/landingforge. It costs 896 tokens per session, scanned A, original, MIT.

A project guide for LandingForge, a Claude Code plugin that creates and scores landing pages for software and consumer products. It also defines how agents must use browser automation when inspecting real web pages.

In plain words
What is it for?
Use it when building, reviewing, scoring, or visually checking landing pages, including their conversion, search, AI-search, and visual quality.
Why use it?
It gives agents the project’s rules, workflow, and required tools so their landing-page work follows the repository’s conventions.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code; mentions Codex.

This is NmadeleiDev/landingforge's own configuration. It tells Claude Code how to work on landingforge 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 landingforge configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to NmadeleiDev/landingforge. 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/NmadeleiDev/landingforge/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/NmadeleiDev/landingforge

Made for: Claude Code.

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 landingforge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nmadeleidev/landingforge/claude-md.svg)](https://agentmods.dev/instructions/nmadeleidev/landingforge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nmadeleidev/landingforge/claude-md"><img src="https://agentmods.dev/badge/instructions/nmadeleidev/landingforge/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 896 This file is loaded in full into every session.
When invoked 896 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 $0.00896 $0.00896
Opus 5 $0.00448 $0.00448
Sonnet 5 $0.00179 $0.00179
Haiku 4.5 $0.00090 $0.00090

Measured 6d ago against content hash a27746119c80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

landingforge CLAUDE.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 6d 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.

CLAUDE.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LandingForge — project guide for agents

LandingForge is a Claude Code plugin that manufactures and scores SaaS, dev-tool, and B2C consumer-app landing pages across four axes (conversion, organic SEO, AI-search/GEO, visual craft). See README.md for the architecture and references/ for the knowledge base.

Browser automation (REQUIRED for workflows and agents)

When any task needs to load, render, screenshot, or inspect a real web page — landing-page teardowns, scoring the calibration anchors, /landing-critique, build/visual QA — use the browser bundled with this plugin at scripts/browse. Do not use WebFetch for these, and do not reach for an externally-installed browser tool.

How:

B="${CLAUDE_PLUGIN_ROOT}/scripts/browse"
"$B" goto <url>                 # navigate (starts a browser on first use — there is no connect step)
"$B" js "<expr>"                # computed CSS / DOM facts (font-size, weight, letter-spacing, colors, JSON-LD, counts)
"$B" text                       # rendered copy
"$B" screenshot <path> --viewport   # above-the-fold; then Read the PNG
"$B" inspect <selector>         # computed style + box + aboveTheFold for one element
"$B" perf                       # navigation timings + LCP/CLS observed for this load
"$B" resize 390 844             # mobile fold checks
"$B" close                      # shut the session down when finished

It runs on the playwright already declared in scripts/package.jsoncd scripts && npm install once (the postinstall fetches Chromium). Nothing global to install, nothing to connect to.

Why not WebFetch: it can't see rendered CSS or computed styles and gets bot-blocked on JS-heavy marketing sites — useless for visual teardowns and scoring.

Operating rules:

  • The session persists across invocations. goto once, then probe that one page load as many times as you need. Re-goto only to change page — never to re-read the same one.
  • Sessions are named. Concurrent work on different pages must pass distinct --session <name> values. Agents sharing a name share a tab and will clobber each other.
  • For SPAs that poll, use "$B" wait --load (not --networkidle, which times out). A timeout is reported as reached: false, not raised — the run continues.
  • Use --viewport for hero/above-the-fold screenshots (a full-page shot of a tall lazy-loaded page can capture a near-blank PNG).
  • perf reports transferBytesKnown as a floor: cross-origin resources without Timing-Allow-Origin report zero bytes and are counted in opaqueCount. Never quote it as total page weight. Lighthouse (scripts/score.ts) owns the real CWV numbers.
  • Close sessions you opened so a stray Chromium does not outlive the run.

Read the full file on GitHub · 62 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. 6d ago First seen · 62 lines · 896 tokens per session scan A a27746119c80

Subscribe to this mod's changes

landingforge CLAUDE.md is an instructions file published in the GitHub repository NmadeleiDev/landingforge (1 stars, last pushed 1mo ago), licensed MIT. It adds 896 tokens to every session, about $0.0045 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.

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 · 5,182 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

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