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 marcos-sponton/frameworks-as-skills --skill cold-start-problemgit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/cold-start-problem)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/cold-start-problem"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/cold-start-problem/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/marcos-sponton/frameworks-as-skills/cold-start-problem"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/cold-start-problem.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 | $0.00387 | $0.03400 |
| Opus 5 | $0.00193 | $0.01700 |
| Sonnet 5 | $0.00077 | $0.00680 |
| Haiku 4.5 | $0.00039 | $0.00340 |
Grade A, and why
cold-start-problem 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Cold Start Problem
Andrew Chen's Cold Start Problem — the operational playbook for launching and scaling network products (marketplaces, social networks, dating apps, collaboration tools, communities, creator platforms) through the 5 stages of network effects: Cold Start → Tipping Point → Escape Velocity → Hitting the Ceiling → The Moat. Distilled from Chen's book The Cold Start Problem: How to Start and Scale Network Effects (Harper Business, 2021), his ongoing essays on andrewchen.com and andrewchen.substack.com, his a16z portfolio commentary, and podcast appearances including Lenny Rachitsky's, Noah Kagan Presents, Intercom, and the a16z podcast. Chen draws heavily on first-person Uber tenure (head of Rider Growth, 15M→100M users) and a16z portfolio visibility that summarizers can't reproduce.
This skill helps your agent think like the operator behind Uber's city launches — narrow, dense, self-sustaining atomic networks; hard-side users solved first; anti-network effects respected on both the launch curve and the ceiling curve. It's opinionated because Chen is opinionated: atomic networks are smaller and more specific than founders think, the hard side is where the leverage is, viral loops are not network effects, and network defensibility is a live discipline, not a static moat.
When this skill activates
Use this skill when the user is:
- Launching a networked product (marketplace, social, chat, dating, community, creator platform, multiplayer, dev tools) and stuck on the chicken-and-egg problem.
- Trying to figure out the beachhead — which city, which campus, which team, which niche — to start from.
- Debating supply-side vs demand-side prioritization on a two-sided marketplace.
- Watching a marketplace with signups but no engagement — empty rooms.
- Diagnosing why a previously growing network has stalled, decayed, been spammed, or drifted into "eternal September".
- Considering a come-for-the-tool-stay-for-the-network launch (single-player value first, network second).
- Being asked "how defensible is our network effect?" in a fundraise or board conversation.
- Deciding whether to launch city-by-city or in one big push.
- Working on a creator / UGC platform and trying to identify who the hard-side users are.
- Post-launch, at scale, wondering whether the ceiling problems are fixable or structural.
- Cloning a competitor's network product and trying to attack their moat (cherry-picking argument).
What ships with it
12 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.
- evals/evals.json 8.9 KB
- examples/.gitkeep 0 B
- README.md 6.6 KB
- references/applications.md 10 KB
- references/author-live-sources.md 8.8 KB
- references/examples.md 16 KB
- references/heuristics.md 19 KB
- references/method.md 17 KB
- references/post-book.md 13 KB
- references/prompts.md 9.8 KB
- references/sources.md 8.1 KB
- references/voice-and-tone.md 13 KB
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.
- 9d ago First seen · 109 lines · 387 tokens per session scan A 5261b09998a1
cold-start-problem is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 387 tokens to every session and 3,400 once invoked, about $0.0019 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
acquire-skills
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
endpoint-discovery
Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.
param-miner
Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.