lp-scorer

lp-scorer is an agent for Claude Code, Codex from NmadeleiDev/landingforge. It costs 71 tokens per session (2,796 once invoked), scanned A, original, MIT.

An evaluator for landing pages, which are standalone web pages designed around a specific goal such as collecting leads or selling a product.

In plain words
What is it for?
It reads upstream reports for conversion, search visibility, craft, and performance, judges visual distinctiveness, and writes a SCORECARD.md report.
Why use it?
It turns several quality checks and one visual review into a single scorecard, so teams can judge whether a page meets their defined standard.

Agent for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also installed under .codex/. Also seen: mentions subagents; mentions Codex.

Part of the landingforge plugin — 8 skills, 9 agents shipped together

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 agents/nmadeleidev/landingforge/lp-scorer
Clone the repo
git clone --depth 1 https://github.com/NmadeleiDev/landingforge

Made for: Claude Code, Codex.

Or install landingforge, the plugin that ships this one along with the rest of its 8 skills, 9 agents.

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 lp-scorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nmadeleidev/landingforge/lp-scorer.svg)](https://agentmods.dev/agents/nmadeleidev/landingforge/lp-scorer)
Your own site
<a href="https://agentmods.dev/agents/nmadeleidev/landingforge/lp-scorer"><img src="https://agentmods.dev/badge/agents/nmadeleidev/landingforge/lp-scorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,796 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00071 $0.02796
Opus 5 $0.00036 $0.01398
Sonnet 5 $0.00014 $0.00559
Haiku 4.5 $0.00007 $0.00280

Measured 5d ago against content hash 5540a4cfba48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

lp-scorer 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 5d 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.

.codex/agents/lp-scorer.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running an lp-* agent on Codex. Codex has no parallel subagent tool, and this pipeline is sequential and gated anyway. Wherever this file says to spawn or run an agent inline, it means: read .codex/agents/<name>.md and follow its full body verbatim as that phase's operating instructions, one phase at a time. <landingforge-root> is the LandingForge checkout root — the landing-* skill that dispatched you states its absolute path (codex/install.sh stamped it there).

You are the LandingForge scorer (lp-scorer). You own the 10-star scorecard — a 0–100 score rendered as ★ out of 10 across four axes — defined in references/scorecard.md. Read that file first; it is the single source of truth for the rubric, the check list, the aggregation formula, the ship threshold, and the calibration anchors. Do not invent checks or weights — every value you score comes from a row in that file.

You score; you do not re-measure. Three axes are read from upstream reports. One axis (Visual) you judge yourself, calibrated against the embedded anchors.

Human feedback notes

If the prompt includes a human revision note or improvement request, append a short entry to the target project's .landingforge/session-notes.md following references/session-notes.md. Record the human direction, this phase (lp-scorer), and the scorecard or routing changes. Skip this when there is no substantive human feedback; never let notes block SCORECARD.md.

Inputs you consume (do NOT re-measure)

Axis Weight Mode You read
Conversion 35% Deterministic cro-report.md (conversion anti-pattern linter R1–R13 + specificity linter)
Visual distinctiveness 25% LLM-judgment (anchored) design.md + tokens.css + the built page
Discoverability 25% Deterministic seo-report.md + schema/robots/OG values; CWV read from perf-report.md
Craft & performance 15% Deterministic perf-report.md (lp-perf is the sole owner of CWV/a11y measurement)

Read the full file on GitHub · 108 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. 5d ago First seen · 108 lines · 71 tokens per session scan A 5540a4cfba48

Subscribe to this mod's changes

lp-scorer is an agent published in the GitHub repository NmadeleiDev/landingforge (1 stars, last pushed 29d ago), licensed MIT. It adds 71 tokens to every session and 2,796 once invoked, about $0.0004 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 agents, from other repositories

conversion-optimizer

Use when reviewing funnel pages for conversion rate improvements, auditing CTAs, social proof, urgency elements, or diagnosing why a page isn't converting. Returns scored analysis with quick wins and strategic fixes.

ominou5/funnel-architect-plugin · 42 tokens

copy-doctor

Use when writing or rewriting headlines, CTAs, body copy, email sequences, or objection handlers. Applies AIDA, PAS, and StoryBrand frameworks. Always returns a primary version, an A/B variant, and rationale.

ominou5/funnel-architect-plugin · 49 tokens

deploy-assistant

Use when deploying funnel pages to production, setting up hosting, or configuring custom domains and DNS. Supports Netlify, Vercel, Cloudflare Pages, and Firebase Hosting. Runs pre-deploy checks automatically.

ominou5/funnel-architect-plugin · 46 tokens

funnel-builder

Use when building funnel pages, generating HTML/CSS/JS, or executing the full funnel build process. Handles all page generation, applies conversion patterns, and coordinates copy and optimization sub-agents.

ominou5/funnel-architect-plugin · 43 tokens

page-speed-optimizer

Use when pages load slowly, images are unoptimized, or Core Web Vitals need improvement. Audits LCP, FID, CLS, and TTFB, then applies fixes directly to HTML/CSS/JS for sub-3-second load times.

ominou5/funnel-architect-plugin · 57 tokens

neural-explorer

Codebase exploration via neural memory knowledge graph — semantic search and graph traversal. Prefer over generic Explore agents when neural-memory is installed.

Yakoub-ai/neural-memory · 31 tokens