A workflow for writing landing-page text from a page strategy, brand information, approved claims, evidence, and customer objections. It keeps the product's actual explanation and proof at the center of the copy.

Writing page sections, explaining how an offer works, using available proof, addressing objections, shaping calls to action, and checking claims for accuracy.

It reduces vague sales language and prevents unsupported promises from being presented as facts.

page-copy — Skill for Claude Code and Codex by TheMattBerman

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.

Any agent

npx skills add TheMattBerman/landing-page-factory --skill page-copy

Clone the repo

git clone --depth 1 https://github.com/TheMattBerman/landing-page-factory

Made for: Claude Code, Codex.

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/skills/themattberman/landing-page-factory/page-copy/github.svg)](https://agentmods.dev/skills/themattberman/landing-page-factory/page-copy)

Your own site

<a href="https://agentmods.dev/skills/themattberman/landing-page-factory/page-copy"><img src="https://agentmods.dev/badge/skills/themattberman/landing-page-factory/page-copy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/themattberman/landing-page-factory/page-copy"><img src="https://agentmods.dev/badge/skills/themattberman/landing-page-factory/page-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,006 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.01006
Opus 5	$0.00017	$0.00503
Sonnet 5	$0.00007	$0.00201
Haiku 4.5	$0.00003	$0.00101

Measured 12d ago against content hash fb87cc8bf889, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

page-copy 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 12d 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.

skills/page-copy/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Page Copy

Good landing page copy is not generic persuasion sludge. It is a controlled translation of the mechanism, offer, proof, and objection map into page sections.

If strategy is missing, stop.

Required inputs

workspace/pages/[page-name]/strategy.json
workspace/brand/profile.md
workspace/brand/extract.md

Pre-write control block

Before drafting, print and honor:

Offer
Unique mechanism
Allowed claims
Forbidden claims
Available proof
Priority objections
CTA action
CTA destination

If any are missing, downgrade or stop.

Copy rules

Mechanism first. A good-looking page that weakens the mechanism is bad copy.
Use extracted language where it is strongest.
Every section has one job.
Do not use unearned certainty.
Do not upgrade missing proof into verified proof.
Ban empty phrases unless directly quoted from source.

Hard ban list

Cut these unless there is direct source evidence and a damn good reason:

elevate
seamless
unlock
next-gen
cutting-edge
revolutionize
transform your business
premium solution
game-changer
innovative platform

Required section order

The exact layout can vary, but the copy artifact must include:

strategy snapshot
hero
problem / failed alternative
mechanism / solution
proof
objections
CTA close
metadata
sharpness audit

Required output format

# [Page Name] — Copy
Brand:
Generated:
Page type:
Awareness stage:
CTA:

## STRATEGY SNAPSHOT
- Offer:
- Unique mechanism:
- Allowed claims:
- Forbidden claims:
- Proof available:
- Priority objections:

## HERO
### Headline options
1. 
2. 
3. 
Recommended:
Reason:

### Subheadline

### CTA

### Above-fold trust cue

## PROBLEM / FAILED ALTERNATIVE

## MECHANISM / SOLUTION
- explain why this works
- tie benefits directly to failed alternatives

## PROOF
| Element | Copy | Provenance | Shippable? |
|---|---|---|---|

## OBJECTIONS
Q:
A:

## FINAL CTA

## PAGE METADATA
- SEO title
- Meta description
- OG title
- OG description

## SHARPNESS AUDIT
| Dimension | Score /10 | Pass threshold | Notes |
|---|---:|---:|---|
| mechanism clarity | | 8 | |
| specificity | | 8 | |
| proof density | | 7 | |
| objection coverage | | 7 | |
| phrase originality | | 7 | |
| section discipline | | 8 | |
| CTA clarity | | 8 | |

Overall: pass / fail
Required cuts:
-

Read the full file on GitHub · 203 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.

12d ago First seen · 203 lines · 35 tokens per session scan A fb87cc8bf889

Subscribe to this mod's changes

page-copy is a skill published in the GitHub repository TheMattBerman/landing-page-factory (40 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,006 once invoked, about $0.0002 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 2026-08-30.

Marketing and SEO Writing and docs ai-agents conversion-rate-optimization landing-pages openclaw

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

HKUDS/nanobot · 22 tokens

officecli-word-form

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…

iOfficeAI/OfficeCLI · 224 tokens

page-copy