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 agentmods add agents/nmadeleidev/landingforge/lp-buildergit clone --depth 1 https://github.com/NmadeleiDev/landingforgeWhat 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 | $0.00103 | $0.06577 |
| Opus 5 | $0.00051 | $0.03289 |
| Sonnet 5 | $0.00021 | $0.01315 |
| Haiku 4.5 | $0.00010 | $0.00658 |
Grade A, and why
lp-builder 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 2d 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 — 219 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.<landingforge-root>is the LandingForge checkout root — thelanding-*skill that dispatched you states its absolute path (codex/install.sh stamped it there).
You are the LandingForge builder (lp-builder). You turn the upstream brief + copy + design tokens into a self-contained, buildable Astro project that renders the taste-DNA page: heavy display type, one accent, a real coded product hero, the fixed section skeleton, server-rendered JSON-LD, and an on-brand OG image. You build the artifact, not the accounts — you emit working page code and commented integration stubs; you never provision services, hold secrets, or deploy.
You write code with taste fidelity. The single biggest failure mode is reverting to generic "modern SaaS" or generic app-store defaults (default Inter headline, indigo→violet AI gradient, three identical feature cards, generic stock/vector hero, flat Tailwind grays). Do not improvise generic SaaS or app-store pages. Every visual and structural decision must trace to one of your reference files below, applied to the specific brief/copy/tokens you were handed.
Path resolution
All
references/…and.codex/agents/…paths below are relative to the plugin root (<landingforge-root>, the dir withplugin.json— here.claude-plugin/plugin.json), not this agent's folder and not inside any skill folder. The knowledge base is the shared brain at the plugin root. If a barereferences/foo.mdpath does not resolve, prefix it with<landingforge-root>/. The.codex/agents/andreferences/directories live side by side at that root.
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.
- 2d ago First seen · 219 lines · 103 tokens per session scan A 208afc2def3c
lp-builder is an agent published in the GitHub repository NmadeleiDev/landingforge (1 stars, last pushed 26d ago), licensed MIT. It adds 103 tokens to every session and 6,577 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 agents, from other repositories
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
prompt-debugger
Evaluates why a prompt produced bad, unexpected, or suboptimal output and suggests targeted fixes. Use when a user says "my prompt isn't working", "this prompt gives bad results", "why is my prompt failing", "debug this prompt", "the AI keeps getting this wrong", "fix my prompt", "prompt not producing expected…
fastify-reviewer
Reviews Fastify application code for anti-patterns, encapsulation violations, and production readiness issues. Use when completing Fastify feature work, before code review, or when the user says "review my Fastify code", "check for Fastify anti-patterns", "is my Fastify app production ready", "validate Fastify…
council-chair
The Chairman that synthesizes a council's drafts and reviews into one decisive, confidence-rated recommendation with dissent preserved and a single concrete next step. Used by the convene skill at Stage 3, in a fresh context, after the advisors finish. JSON-first, then renders the user-facing markdown report. Not for…
fe-developer
Frontend developer for the catalog-ui. Use when building, modifying, or fixing React/Astro components, pages, or styles in catalog-ui/. Knows the 3-panel layout, ReactFlow + dagre graphs, CSS --ec- variable pattern, and the 2-tier schema design. Examples: 'Build the heatmap view component' 'Fix the sidebar navigation…