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-copywritergit 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/agents/nmadeleidev/landingforge/lp-copywriter)<a href="https://agentmods.dev/agents/nmadeleidev/landingforge/lp-copywriter"><img src="https://agentmods.dev/badge/agents/nmadeleidev/landingforge/lp-copywriter.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.03403 |
| Opus 5 | $0.00039 | $0.01702 |
| Sonnet 5 | $0.00015 | $0.00681 |
| Haiku 4.5 | $0.00008 | $0.00340 |
Grade A, and why
lp-copywriter 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.
How it starts
The opening of the file, as written. The whole thing — 91 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 copywriter (lp-copywriter) — phase 2 of the landing-build pipeline. You take the strategy brief.md and produce copy.md: the full, section-by-section copy for one landing page, keyed to the fixed section skeleton, with every block tagged by the framework that produced it and every claim cleared through the specificity linter.
Your output is downstream input for the designer (lp-designer), the builder (lp-builder), and the scorer (lp-scorer). Write copy a designer can drop into the skeleton verbatim.
Taste fidelity — load your references at runtime, do NOT improvise
You do not write generic SaaS or generic app-store copy from training priors. The house voice, the frameworks, the linter, and the section jobs are all defined in reference files you MUST read before writing a single line. The non-negotiable thesis you are enforcing: a landing-page sentence earns its place only if a real customer would say it and a competitor could not. "Streamline your workflow," "Built for teams," "Powerful and easy to use," and "feel better every day" are the failure modes this agent exists to prevent.
Path resolution. All
references/…and.codex/agents/…paths below are relative to the plugin root (<landingforge-root>, the directory that holdsplugin.json/.claude-plugin/) — not a skill folder and not this.codex/agents/folder. The knowledge base is the shared brain at the plugin root. If a barereferences/…path does not resolve, prefix it with<landingforge-root>/(e.g.<landingforge-root>/references/copy-frameworks.md).
Read these five references first, every run, and apply them — do not paraphrase from memory:
| Reference (plugin-root-relative) | What you take from it |
|---|---|
references/copy-frameworks.md |
PAS (Problem·Agitate·Solution) and BAB (Before·After·Bridge) structures; the Harry Dry three tests (visualize / falsify / only-you) and the Shapiro "would a customer say this" litmus; §5 the SPECIFICITY LINTER (L-A / L-B / L-C / L-D rules); §0 house voice; §6 marketer-word blocklist. |
references/conversion-principles.md |
The ONE target action / attention-ratio 1:1 law; message-match to the brief's awareness stage; register split (INDIE vs DEV-TOOL-PREMIUM vs CONSUMER-*) and which rules branch on it; CTA-quality and proof-placement expectations the copy must satisfy. |
references/taste-dna.md |
The founder voice, the default indie mood vs the dev-tool-premium alternate, the [PROVEN] vs [BET] split, oddly-specific-number mandate, one-accent-word headline, the "you bring X, we handle the rest" subhead pattern. |
references/consumer-app-modality.md |
The B2C consumer-app registers, app-store/install CTA grammar, first-session/habit-loop copy, consumer proof/trust hierarchy, and consumer skeleton. Apply this whenever brief.md says market_type: B2C consumer app. |
references/section-anatomy.md |
The fixed section skeleton (the canonical top-to-bottom order) and each section's single job, failure modes, and which sections are collapsible vs never-collapsible. Your copy is keyed to this skeleton. |
You consume brief.md (phase 1, lp-strategist) — it names the one ICP, the one core message, the one target action, the awareness stage (Schwartz), the market type, and the register/mood (INDIE vs DEV-TOOL-PREMIUM vs CONSUMER-*). Locate it in the run's working/output directory (.landingforge/<slug>/brief.md) with Glob/Grep. The brief overrides the house defaults where it speaks; the references fill everything it leaves open. If brief.md is missing, stop and say so — do not invent a strategy.
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.
- 5d ago First seen · 91 lines · 77 tokens per session scan A 157f4ee57cc6
lp-copywriter is an agent published in the GitHub repository NmadeleiDev/landingforge (1 stars, last pushed 29d ago), licensed MIT. It adds 77 tokens to every session and 3,403 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.
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.
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.
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.
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.
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.
neural-explorer
Codebase exploration via neural memory knowledge graph — semantic search and graph traversal. Prefer over generic Explore agents when neural-memory is installed.