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-discoverabilitygit 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-discoverability)<a href="https://agentmods.dev/skills/nmadeleidev/landingforge/landing-discoverability"><img src="https://agentmods.dev/badge/skills/nmadeleidev/landingforge/landing-discoverability/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-discoverability"><img src="https://agentmods.dev/badge/skills/nmadeleidev/landingforge/landing-discoverability.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 | $0.00142 | $0.04555 |
| Opus 5 | $0.00071 | $0.02278 |
| Sonnet 5 | $0.00028 | $0.00911 |
| Haiku 4.5 | $0.00014 | $0.00456 |
Grade A, and why
landing-discoverability 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 9d 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 — 298 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 Discoverability (Phase 5, standalone)
Run only phase 5 of the LandingForge pipeline: take an already-built page
— a local site/ build or a live URL — and produce the discoverability report
seo-report.md, the SEO + GEO artifact lp-scorer reads for the 25%
Discoverability axis. This is a thin standalone wrapper around the
lp-discoverability agent, which delegates to claude-seo for all real
SEO/GEO validation and scoring. It does not write strategy, copy, design, or build
a page; it audits a built one for discoverability and emits the report.
LandingForge keeps no SEO/GEO knowledge base of its own. claude-seo
(agricidaniel-claude-seo/claude-seo) is the single source of truth for passage
citability, crawler-policy theory, schema property validation, entity/authority
signals, and GEO scoring. This phase's job is to (a) point that engine at the
built page, (b) check the landing-specific build-time knobs LandingForge owns
(SoftwareApplication JSON-LD, citable-passage shape, AI-crawler access), and (c)
record the provenance of how the axis was earned.
Path resolution. All
references/…and.codex/agents/…paths below are relative to the plugin root ({{LANDINGFORGE_ROOT}}, the directory containingplugin.json), not to this skill's own folder. The knowledge base and the agent contracts live at the plugin root on purpose — they are the one shared brain every LandingForge skill and agent reads. If a bare path such asreferences/discoverability.mdor.codex/agents/lp-discoverability.mddoes not resolve from the current directory, prefix it with{{LANDINGFORGE_ROOT}}/.
Same report as the full pipeline. The
seo-report.mdthis skill emits is the exact artifactlanding-buildphase 5 produces. A report committed here is a valid drop-in for phase 8: hand the built page + this report to thelp-scorer(vialanding-critiqueor the wiredlanding-buildloop) and it scores the Discoverability axis (D1–D10) from it. One engine, two entry points.
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.
- 9d ago First seen · 298 lines · 142 tokens per session scan A 59a2a10b5d83
landing-discoverability is a skill published in the GitHub repository NmadeleiDev/landingforge (1 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 4,555 once invoked, about $0.0007 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
funnel-hacking
Reverse-engineer any live public sales funnel and rebuild it — adapted for the user's brand, copy, and offer — without copyright infringement. Handles single pages or entire multi-page funnels. Uses Russell Brunson's Hook/Story/Offer framework to deconstruct what makes a funnel convert, then delegates the build to the…
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.
group-funnel
Builds a 2-page community group growth funnel. Drives free opt-ins to a group (Skool, Whop, Facebook Group, Discord, or any community platform) using a lead magnet. Use when the goal is to grow a free or paid community.
saas-funnel
Builds a 4–6 page SaaS trial/signup funnel. Converts visitors into free trial users or freemium signups, then nurtures to paid. Best for software products with recurring revenue.
analytics-setup
Sets up analytics and tracking for funnel pages. Covers GA4, Meta Pixel, Google Tag Manager, conversion tracking, and UTM parameter handling.
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.