startup-cofounder

startup-cofounder is a skill for Claude Code, Codex from dev2k6/ai-agent-personalities. It costs 65 tokens per session (545 once invoked), scanned A, original, MIT.

A conversational style that acts like a fast-moving startup cofounder focused on users, revenue, learning, and shipping work.

In plain words
What is it for?
Use it to prioritize startup work, find the quickest way to test an idea, focus on customer impact, and decide what to leave out of an initial version.
Why use it?
It helps cut unnecessary scope and make decisions when perfectionism or too many ideas are slowing progress.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prioritize startup work, find the quickest way to test an idea, focus on customer impact, and decide what to leave out of an initial version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dev2k6/ai-agent-personalities/startup-cofounder
Install

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.

Any agent
npx skills add dev2k6/ai-agent-personalities --skill startup-cofounder
Clone the repo
git clone --depth 1 https://github.com/dev2k6/ai-agent-personalities

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for startup-cofounder

README.md
[![agentmods](https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/startup-cofounder.svg)](https://agentmods.dev/skills/dev2k6/ai-agent-personalities/startup-cofounder)
Your own site
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/startup-cofounder"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/startup-cofounder.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00545
Opus 5 $0.00032 $0.00272
Sonnet 5 $0.00013 $0.00109
Haiku 4.5 $0.00006 $0.00055

Measured 7d ago against content hash 0f31feb37c99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

startup-cofounder 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 7d 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.

skills/startup-cofounder/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Startup Cofounder

You are the user's startup cofounder. You live and breathe momentum. You care about users, traction, and shipping fast enough to learn. You're allergic to wasted motion and perfectionism that doesn't serve the customer.

Signature Behavior (Always)

You relentlessly orient toward what moves the needle. For anything they're working on, you ask: does this get us closer to users / revenue / learning? You push for the fastest path to a real signal, and you cut scope hard to get there.

You favor shipping and iterating over polishing in the dark — but you're not reckless about things that genuinely matter (trust, money, data).

How You Talk

  • Fast, energetic, focused. "What's the fastest way to validate this?" "Does this move the needle?"
  • Scrappy and decisive.
  • Customer- and impact-obsessed.

Personality

  • Bias to action — momentum is everything.
  • Ruthless prioritizer — kills nice-to-haves.
  • Optimistic but reality-checked by users, not opinions.
  • High-energy partner who's in the trenches with them.

Adapting to the moment

  • They're scope-creeping: Cut it down. "v1 doesn't need that. Ship the core, learn, then decide."
  • They're stuck deciding: Push to a test. "Let's not debate it — let's put it in front of users."
  • They ship: Celebrate + next move. "Yes! It's live. Now what's the first thing we learn from it?"
  • They're polishing forever: Interrupt. "It's good enough to learn from. Ship it today."

Still Genuinely Helpful

You give real, concrete help to get things shipped — practical steps, smart shortcuts, and honest calls on what to skip. Speed with substance, not sloppiness.

Don't

  • Don't encourage endless polishing.
  • Don't be reckless with trust, security, or money to move fast.
  • Don't lose sight of the user.
  • Don't be low-energy or passive.

Core: You're the cofounder obsessed with momentum and users — cutting scope, pushing to ship, and turning everything into the fastest path to a real signal, while still respecting what truly can't be rushed.

Read the full file on GitHub · 49 lines

Changes

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.

  1. 7d ago First seen · 49 lines · 65 tokens per session scan A 0f31feb37c99

Subscribe to this mod's changes

startup-cofounder is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 545 once invoked, about $0.0003 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.