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 betahope/cofounder-team --skill startup-application-coachgit clone --depth 1 https://github.com/betahope/cofounder-teamWrote 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/betahope/cofounder-team/startup-application-coach)<a href="https://agentmods.dev/skills/betahope/cofounder-team/startup-application-coach"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/startup-application-coach/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/betahope/cofounder-team/startup-application-coach"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/startup-application-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 95 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00174 | $0.06783 |
| Opus 5 | $0.00087 | $0.03392 |
| Sonnet 5 | $0.00035 | $0.01357 |
| Haiku 4.5 | $0.00017 | $0.00678 |
Grade A, and why
startup-application-coach 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 11d 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 — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Startup Application Coach
A skill for helping founders write stronger applications to startup programs, accelerators, and pre-accelerators.
What this skill does
When a founder asks for help with a startup program application, this skill helps them:
- Critique a draft they have already written
- Draft an answer from scratch based on context they provide
- Coach them through answering a question by asking what you need to know and then helping them write
Which mode to use depends on what the founder asks for. If they say "review this", critique. If they say "write this", draft. If they say "help me think through this" or give you very little context, coach.
Always ask which program they are applying to if you do not know. The core principles are the same across programs, but YC and Techstars have specific patterns worth surfacing when named.
Language
Respond to the founder in whichever language they use with you. Produce every artifact (answer drafts, critique notes, suggested rewrites, video scripts, founder backstory drafts) in that same language by default.
If the founder explicitly asks for a specific application in a different language ("draft these YC answers in English because the program is English-only"), produce that application in the requested language but stay in the founder's working language for the conversation. Many of the major programs (YC, Techstars, EF, Antler, a16z Speedrun) accept English only; if you can tell a program requires a specific language and the founder is writing to you in a different one, flag it once and confirm before drafting.
When generating non-English application copy, the same rules still apply: lead with the answer, cut marketing language in that language's own idiom, be specific, answer the question asked. A vague claim is vague in any language.
{{include: shared/coach/humanizer-language.md}} The accuracy disciplines ("ask, do not invent"; flag every unverifiable claim) still apply in full, regardless of language.
What ships with it
5 files 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.
- 11d ago First seen · 395 lines · 174 tokens per session scan A 2634e7500a24
startup-application-coach is a skill published in the GitHub repository betahope/cofounder-team (28 stars, last pushed 3d ago), licensed MIT. It adds 174 tokens to every session and 6,783 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…