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.
npx skills add NmadeleiDev/landingforge --skill landing-critiquegit clone --depth 1 https://github.com/NmadeleiDev/landingforgeWrote 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.
[](https://agentmods.dev/skills/nmadeleidev/landingforge/landing-critique)<a href="https://agentmods.dev/skills/nmadeleidev/landingforge/landing-critique"><img src="https://agentmods.dev/badge/skills/nmadeleidev/landingforge/landing-critique/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.
<a href="https://agentmods.dev/skills/nmadeleidev/landingforge/landing-critique"><img src="https://agentmods.dev/badge/skills/nmadeleidev/landingforge/landing-critique.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00107 | $0.05695 |
| Opus 5 | $0.00053 | $0.02848 |
| Sonnet 5 | $0.00021 | $0.01139 |
| Haiku 4.5 | $0.00011 | $0.00570 |
Grade A, and why
landing-critique 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 236 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>.mdand follow its full body verbatim as that phase's operating instructions, one phase at a time.
Landing Page Critique (10-Star Audit)
Audit any existing landing page — a live URL or a local file path — and score it 0–100 rendered as ★ out of 10 across the four LandingForge axes (Conversion 35% · Visual distinctiveness 25% · Discoverability 25% · Craft & performance 15%).
This is a read-only orchestrator that mirrors the claude-seo seo-audit delegation pattern: it inspects the page, delegates the Discoverability axis to claude-seo's specialist agents when present (inline fallback otherwise), and hands the gathered evidence to the lp-scorer contract. It does not generate or modify a page.
Path resolution. All
references/…and.codex/agents/…paths below are relative to the plugin root ({{LANDINGFORGE_ROOT}}, the dir withplugin.json), not this skill's folder — the knowledge base is the shared brain at the plugin root. If a bare path does not resolve, prefix it with{{LANDINGFORGE_ROOT}}/.
Same rubric as the generator. This skill scores against
references/scorecard.md— the exact rubriclanding-buildphase 8 targets. A critique score is therefore directly comparable to alanding-buildscore: a page audited at ★ 7.4 here and a page generated to ★ 7.4 there cleared (or missed) the identical checks. There is one engine, two entry points.
Prerequisites
- Use the bundled browser at
{{LANDINGFORGE_ROOT}}/scripts/browse(it starts itself on first use — there is no connect step). The supported inspection tool is that CLI — not WebFetch. WebFetch sees pre-render HTML and no computed styles, so it cannot judge fonts, colors, motion, or JS-injected schema. Do NOT use WebFetch in this skill. - One page at a time. The browser drives a single page; audit one URL/path per invocation. For a multi-page sweep, invoke the skill once per page.
- claude-seo is optional but preferred. When installed, the Discoverability axis is earned via full validation/scoring; when absent, a labeled-degraded inline fallback runs (see step 4). Note:
claude-seois typically not installed on Codex — expect the inline fallback branch.
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.
- 10d ago First seen · 236 lines · 107 tokens per session scan A cd39013e9ad3
landing-critique is a skill published in the GitHub repository NmadeleiDev/landingforge (1 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 5,695 once invoked, about $0.0005 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.
Other skills, from other repositories
design-system
Design system and visual language for sales funnels. Provides color palettes, typography, spacing, component styles, and theming guidelines for a polished, premium look.
conversion-ux
Conversion-focused UX patterns for sales funnel pages. Apply these patterns to every page to maximize conversion rates. Covers layout, CTA placement, social proof, urgency, and friction reduction.
mobile-responsive
Mobile-first responsive design patterns for sales funnels. Ensures every page works flawlessly on all screen sizes with proper touch targets, readable typography, and fast load times.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…