landforge CLAUDE.md

landforge CLAUDE.md is an instructions file for coding agents from monthu56/landforge. It costs 812 tokens per session, scanned A, original, MIT.

Repository instructions for landforge, a system that generates and manages static landing pages and their deployment setup. A static landing page contains its readable content directly in the HTML rather than loading it through JavaScript.

In plain words
What is it for?
Use them when building landing pages, running A/B experiments, recording marketing changes, preparing ad materials, or deploying the landing system.
Why use it?
They define the project's key constraint that crawlers must see real page content and describe where its landing-page, experiment, advertising, and deployment workflows live.

Instructions file

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/monthu56/landforge/claude-md
Clone the repo
git clone --depth 1 https://github.com/monthu56/landforge

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 landforge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/monthu56/landforge/claude-md.svg)](https://agentmods.dev/instructions/monthu56/landforge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/monthu56/landforge/claude-md"><img src="https://agentmods.dev/badge/instructions/monthu56/landforge/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 812 This file is loaded in full into every session.
When invoked 812 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.

ModelPer sessionOnce invoked
Fable 5 $0.00812 $0.00812
Opus 5 $0.00406 $0.00406
Sonnet 5 $0.00162 $0.00162
Haiku 4.5 $0.00081 $0.00081

Measured 4d ago against content hash 799a40e66401, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

landforge 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 4d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working on this system (the landing-generation toolkit itself). Human overview: README.md. Decisions: docs/adr/.

What this is

A content-management / generation system for static landing pages, delivered as Claude Code skills + deployment infra. Not a build-tooling project (no bundler, test runner, lint).

Hard invariant: a landing is a static HTML file with content in the markup and zero JS on the critical path (CSS/JS inlined). Crawlers must see real content, not an empty root. Every generator and skill must preserve this.

Skills (.claude/skills/)

  • new-landing — landing from a brief (contract + skeleton + check_landing.py).
  • landing-experiment — A/B on one URL (inline split, no cloaking), variant tracking, card.
  • landing-journal — audit journal: experiments/journal.jsonl + journal.md + git. Log every meaningful action via scripts/log_event.py.
  • landing-ads — UTM, ad copy, keywords, editor exports → ads/<campaign>/ (artifacts only).
  • init-landing-system — deploy this whole system into another project (snapshot + sync + user-level install).

MCP server (mcp/)

The toolbox is also exposed as an MCP server (ADR-0002) — any MCP host can call it, not only Claude Code. Thin wrapper: each tool runs the same .claude/skills/*/scripts/*.py via subprocess (one source of logic). Validators / journal / UTM as tools; contract, brief schema, skeleton and journal as resources; brief interviewer / generation / A/B checklist as prompts. Transport stdio; optional dependency (Python ≥ 3.10, mcp); the static-HTML invariant is untouched. New skill script → add a matching tool (keep CLI↔MCP parity). See mcp/README.md.

Infra & deployment

.github/workflows/deploy.yml routes by branch: main → prod (indexable); dev → staging (noindex); any other → preview (noindex). Server runs Traefik + two nginx containers; only prod is indexed (X-Robots-Tag: noindex on staging via nginx). Infra values are {{PLACEHOLDER}}s (domains/containers/dirs) — substituted by init-landing-system or by hand (.claude/skills/init-landing-system/reference/placeholders.md). Deploy secrets: DEPLOY_HOST, DEPLOY_USER, DEPLOY_SSH_KEY, DEPLOY_KNOWN_HOSTS.

Read the full file on GitHub · 55 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. 4d ago First seen · 55 lines · 812 tokens per session scan A 799a40e66401

Subscribe to this mod's changes

landforge CLAUDE.md is an instructions file published in the GitHub repository monthu56/landforge (10 stars, last pushed 3mo ago), licensed MIT. It adds 812 tokens to every session, about $0.0041 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.