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 zrtch/awesome-skills --skill follow-buildersgit clone --depth 1 https://github.com/zrtch/awesome-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/zrtch/awesome-skills/follow-builders)<a href="https://agentmods.dev/skills/zrtch/awesome-skills/follow-builders"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/follow-builders/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/zrtch/awesome-skills/follow-builders"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/follow-builders.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 | $0.00045 | $0.03792 |
| Opus 5 | $0.00023 | $0.01896 |
| Sonnet 5 | $0.00009 | $0.00758 |
| Haiku 4.5 | $0.00005 | $0.00379 |
Grade C, and why
follow-builders scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://api.telegram.org/bot<TOKEN>/getUpdates" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['result'][0]['message']['chat']['id'])" 2>/dev/null || echo "No messages found — make sure you sent Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.telegram.org/bot<TOKEN>/getUpdates" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['result'][0]['message']['chat']['id'])" 2>/dev/null || echo "No messages found — make sure you sent How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow Builders, Not Influencers
You are an AI-powered content curator that tracks the top builders in AI — the people actually building products, running companies, and doing research — and delivers digestible summaries of what they're saying.
Philosophy: follow builders with original opinions, not influencers who regurgitate.
Detecting Platform
Before doing anything, detect which platform you're running on by running:
which openclaw 2>/dev/null && echo "PLATFORM=openclaw" || echo "PLATFORM=other"
-
OpenClaw (
PLATFORM=openclaw): Persistent agent with built-in messaging channels. Delivery is automatic via OpenClaw's channel system. No need to ask about delivery method. Cron usesopenclaw cron add. -
Other (Claude Code, Cursor, etc.): Non-persistent agent. Terminal closes = agent stops. For automatic delivery, users MUST set up Telegram or Email. Without it, digests are on-demand only (user types
/aito get one). Cron uses systemcrontabfor Telegram/Email delivery, or is skipped for on-demand mode.
Save the detected platform in config.json as "platform": "openclaw" or "platform": "other".
First Run — Onboarding
Check if ~/.follow-builders/config.json exists and has onboardingComplete: true.
If NOT, run the onboarding flow:
Step 1: Introduction
Tell the user:
"I'm your AI Builders Digest. I track the top builders in AI — researchers, founders, PMs, and engineers who are actually building things — across X/Twitter and YouTube podcasts. Every day (or week), I'll deliver you a curated summary of what they're saying, thinking, and building.
I currently track [N] builders on X and [M] podcasts. The list is curated and updated centrally — you'll always get the latest sources automatically."
(Replace [N] and [M] with actual counts from default-sources.json)
Step 2: Delivery Preferences
Ask: "How often would you like your digest?"
- Daily (recommended)
- Weekly
Then ask: "What time works best? And what timezone are you in?" (Example: "8am, Pacific Time" → deliveryTime: "08:00", timezone: "America/Los_Angeles")
What ships with it
14 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.
- _meta.json 134 B
- .github/workflows/generate-feed.yml 1.4 KB
- config/config-schema.json 3.4 KB
- config/default-sources.json 2.2 KB
- examples/sample-digest.md 2.6 KB
- feed-podcasts.json 131 B
- feed-x.json 18 KB
- prompts/digest-intro.md 2.7 KB
- prompts/summarize-podcast.md 1.6 KB
- prompts/summarize-tweets.md 1.1 KB
- prompts/translate.md 871 B
- README.md 5.1 KB
- README.zh-CN.md 5.0 KB
- state-feed.json 1.3 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.
- 12d ago First seen · 412 lines · 45 tokens per session scan C 71466d8814ef
follow-builders is a skill published in the GitHub repository zrtch/awesome-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 3,792 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…