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 ranjeeetvimal/growth-skills --skill founder-contextgit clone --depth 1 https://github.com/ranjeeetvimal/growth-skillsWrote 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/ranjeeetvimal/growth-skills/founder-context)<a href="https://agentmods.dev/skills/ranjeeetvimal/growth-skills/founder-context"><img src="https://agentmods.dev/badge/skills/ranjeeetvimal/growth-skills/founder-context/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/ranjeeetvimal/growth-skills/founder-context"><img src="https://agentmods.dev/badge/skills/ranjeeetvimal/growth-skills/founder-context.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 | $0.00116 | $0.01347 |
| Opus 5 | $0.00058 | $0.00674 |
| Sonnet 5 | $0.00023 | $0.00269 |
| Haiku 4.5 | $0.00012 | $0.00135 |
Grade A, and why
founder-context 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder Context — URL In, Context Out
Collect the founder's context ONCE, and make it feel like magic: they give you a URL, you draft everything you can from it, and they confirm and correct by picking options in the terminal — not by typing paragraphs. You only ask for what a website can't tell you.
How to ask — options in the terminal, not prose (IMPORTANT)
Ask every question as a multiple-choice option prompt using the host's interactive picker (in Claude Code, the terminal option selector). Rules:
- Present concrete, selectable options for every question that has discrete answers.
- Always include an "Other" choice so the founder can type a custom answer.
- Never ask a discrete-answer question as free-text prose. The founder should mostly click, not type.
- Use multi-select when more than one answer can apply (e.g. evidence types).
- If the host has no picker, fall back to a numbered list the founder answers with a number.
- The ONLY things typed freely are genuinely open (the URL, the one-sentence product if there's no site, a custom "Other" value).
Step 1 — Ask for the URL
One ask: "Drop your URL and I'll draft your whole context — you just confirm and correct. No site yet? Describe it in a sentence." (Free text here — a URL or a sentence.)
Step 2 — Auto-draft from the URL
Read the public site (and a quick competitor search if useful). Draft every field you can, each marked (from your site) — solid — or (my guess — confirm) — inferred: Product · Stage · Business model + pricing · ICP ("first 100 will be ___ because ___") · Problem (before/after) · Alternatives (top 3) · Why-you (differentiator).
Step 3 — Confirm the draft as ONE option prompt
Show the draft, then ask a pick-an-option question:
- "Looks good — save it" (accept all)
- "Fix [guessed field]" — one option per inferred field (e.g. "Fix the ICP", "Fix the stage")
- Other — the founder types any correction If they pick a "Fix", re-ask just that field as its own option prompt, then continue.
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 · 111 lines · 116 tokens per session scan A 62fbc5997288
founder-context is a skill published in the GitHub repository ranjeeetvimal/growth-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,347 once invoked, about $0.0006 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
research-seo-demand
A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.
create-seo-page
A Chinese-language workflow for creating and implementing search-focused pages in an existing product repository. SEO means improving a page so it can be found and understood through search engines.
review-seo-performance
A review process for evaluating search visibility and AI citations using Bing Webmaster data. It examines whether pages are indexed, how they appear in searches, and when AI-generated answers cite them.
run-seo-page-loop
Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review. Use when taking an SEO page from opportunity discovery through publication, measurement, iteration, or continuing a…
xiaohongshu-mcp
A browser-based, read-only process for researching posts on Xiaohongshu, a Chinese social platform for user-created lifestyle and product content. It can collect search results, candidate cover images, selected post details, and sanitized evidence.
generate-image
Generate, edit, or batch-create SEO, marketing, social, and document images with Gemini or OpenAI through the repository-owned Growth Lab image client. Use when a page or content loop needs illustrations, diagrams, covers, reference-image edits, multiple candidates, or verified image text and composition. This is the…