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 lelephi/marketing-agent-skills-for-founders --skill pitch-one-linergit clone --depth 1 https://github.com/lelephi/marketing-agent-skills-for-foundersWrote 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/lelephi/marketing-agent-skills-for-founders/pitch-one-liner)<a href="https://agentmods.dev/skills/lelephi/marketing-agent-skills-for-founders/pitch-one-liner"><img src="https://agentmods.dev/badge/skills/lelephi/marketing-agent-skills-for-founders/pitch-one-liner/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/lelephi/marketing-agent-skills-for-founders/pitch-one-liner"><img src="https://agentmods.dev/badge/skills/lelephi/marketing-agent-skills-for-founders/pitch-one-liner.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 | $0.00176 | $0.03564 |
| Opus 5 | $0.00088 | $0.01782 |
| Sonnet 5 | $0.00035 | $0.00713 |
| Haiku 4.5 | $0.00018 | $0.00356 |
Grade A, and why
pitch-one-liner 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 12d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch one-liner
Turn a company's fuzzy self-description into one sentence a stranger can repeat correctly after hearing it once, then push that sentence into every place it needs to live.
Why one sentence carries so much weight
The best companies grow by word of mouth, which is the cheapest distribution that exists. Word of mouth only works if the sentence survives retelling. If a user cannot repeat what you do at a dinner table, the growth loop never starts.
The sentence is also a diagnostic. People who have thought deeply about an idea can explain it in fewer words. A muddy one-liner is usually not a copywriting problem. It is a sign the founder has not decided who the customer is, or is hedging between two products. When you hit that, name it. Handing back polished words that paper over an undecided strategy does the founder no favors.
Environment check
Run this first. It takes one line of thought and it prevents the two failure modes that ruin this skill in an unfamiliar environment: stalling on a tool that is not there, and claiming to have read something you never read.
| If this environment can | Use it to | If it cannot |
|---|---|---|
| Read attached or uploaded files | Read the deck, the doc, the screenshots | Ask for the text pasted in |
| Fetch a URL | Pull the live hero, subhead, meta description, nav labels | Ask for the hero copy pasted in, or a screenshot |
| Drive a browser | Render a client-side site the fetch returned empty | Say the page did not render and work from what you have |
| Run code | Nothing here needs it | Ignore |
Nothing in this table is required. This skill works on pasted text alone. State in one line at the top of your output what you actually worked from, and never describe a page you could not open.
Workflow
1. Get the raw material
Work from what they actually publish, not from what they tell you they publish. The gap between the two is often where the problem lives.
| They gave you | Do this |
|---|---|
| A URL | Fetch it. Pull the hero headline, subhead, meta description, and nav labels. If the fetch returns an empty shell because the site is client-rendered, try a browser tool if you have one, otherwise ask for a paste |
| A deck (.pptx, .pdf, Slides link) | Read it. Focus on slide 1, the problem slide, and any what-we-do slide. Note the exact wording. If you cannot extract the text, say so and ask for the title slide as text |
| Pasted copy | Use as-is. This is enough. Do not ask for more access than the job needs |
| Screenshots | Read what is legible. Do not guess at small type, call it unreadable |
| Nothing, just a conversation | Skip to the interview in step 2 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 251 lines · 176 tokens per session scan A be489231eac7
pitch-one-liner is a skill published in the GitHub repository lelephi/marketing-agent-skills-for-founders (2 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 3,564 once invoked, about $0.0009 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
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
open-design-landing-deck
OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.
html-ppt-zhangzara-broadside
OpenDesign's product-launch announcement and press narrative — the headline, the proof points, and the call to action. Built as a decision-grade marketing & GTM deck for press, community, prospects.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
fs-emerald-editorial
OpenDesign's 'design on your desk' brand-launch narrative: the market moment, the story, and the proof that converts. Built as a decision-grade marketing & GTM deck for marketing team, press.
deck-guizang-editorial
OpenDesign's FY26 marketing plan: brand-to-pipeline — audience, offer, channel mix, and the launch calendar that ties creative to growth. Built as a decision-grade marketing & GTM deck for CMO, growth lead, founder.