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 agustinkassis/claude-skills --skill nostr-waitlistgit clone --depth 1 https://github.com/agustinkassis/claude-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/agustinkassis/claude-skills/nostr-waitlist)<a href="https://agentmods.dev/skills/agustinkassis/claude-skills/nostr-waitlist"><img src="https://agentmods.dev/badge/skills/agustinkassis/claude-skills/nostr-waitlist/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/agustinkassis/claude-skills/nostr-waitlist"><img src="https://agentmods.dev/badge/skills/agustinkassis/claude-skills/nostr-waitlist.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 | $0.00144 | $0.02954 |
| Opus 5 | $0.00072 | $0.01477 |
| Sonnet 5 | $0.00029 | $0.00591 |
| Haiku 4.5 | $0.00014 | $0.00295 |
Grade B, and why
nostr-waitlist scanned grade B 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- if yes: `pnpm dev` background, wait 4s, `curl -X POST localhost:3000/api/waitlist/check -H 'Content-Type: application/json' -d '{"contact":"[email protected]"}'` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- "want me to start the dev server and curl `/api/waitlist/check`? (y/n)" How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nostr Waitlist Skill
Scaffolds a polished email + Nostr "early access" flow into the host Next.js
project. The output is opinionated about UX (Radix dialog, three-state form
based on email vs npub vs NIP-05, confetti on success) and unopinionated
about destinations — the user picks any combination of bundled adapters
(Resend Audiences, webhook, Postgres, Supabase, SQLite) or writes their own
satisfying the small Destination interface.
References
references/nostr-keys.md— how to generate annsec, what to put in envreferences/destination-adapters.md— theDestinationinterface + a worked example of a custom adapterreferences/db-schema.sql— canonicalwaitlisttable for Postgres + SQLitereferences/nip-cheatsheet.md— quick recap of NIP-04 / NIP-05 / NIP-44
Phase 1 — Detect stack
Before asking the user anything, gather facts about the host project.
# Run from the project root the user is currently in
cat package.json | grep -E '"(next|react)"' || echo "NOT_NEXT"
ls app/ 2>/dev/null && echo "HAS_APP"
ls pages/api/ 2>/dev/null && echo "HAS_PAGES_API"
ls tsconfig.json 2>/dev/null && echo "HAS_TS"
ls tailwind.config.ts tailwind.config.js tailwind.config.mjs 2>/dev/null && echo "HAS_TAILWIND"
ls pnpm-lock.yaml yarn.lock package-lock.json bun.lockb 2>/dev/null
ls components/ui/dialog.tsx components/ui/button.tsx components/ui/input.tsx 2>/dev/null
Decide:
- NOT_NEXT → stop. Tell the user "this skill targets Next.js. Detected: ." and exit.
- HAS_APP present → use App Router templates (
templates/api/app-router/). - Only HAS_PAGES_API → use Pages Router templates.
- Both present → ask the user which to target (Modal vs section can also live in either; route handler placement is what matters).
- Package manager: pnpm-lock →
pnpm, yarn.lock →yarn, package-lock.json →npm, bun.lockb →bun. Defaultnpmif none found. - shadcn primitives detected → set
EMIT_UI = false. OtherwiseEMIT_UI = true.
What ships with it
30 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.
- references/db-schema.sql 1.4 KB
- references/destination-adapters.md 3.3 KB
- references/nip-cheatsheet.md 2.0 KB
- references/nostr-keys.md 1.6 KB
- scripts/detect-stack.sh 1.3 KB runs code
- scripts/install-deps.sh 1.4 KB runs code
- scripts/smoke-test.sh 1.1 KB runs code
- templates/api/app-router/check.route.ts.tpl 780 B
- templates/api/app-router/subscribe.route.ts.tpl 4.7 KB
- templates/api/pages-router/check.api.ts.tpl 912 B
- templates/api/pages-router/subscribe.api.ts.tpl 4.5 KB
- templates/components/ui/button.tsx.tpl 2.0 KB
- templates/components/ui/dialog.tsx.tpl 3.7 KB
- templates/components/ui/input.tsx.tpl 796 B
- templates/components/waitlist-modal.tsx.tpl 10 KB
- templates/components/waitlist-section.tsx.tpl 5.6 KB
- templates/components/waitlist-trigger.tsx.tpl 917 B
- templates/email/waitlist-welcome.html.tpl 4.5 KB
- templates/env/.env.example.tpl 1.3 KB
- templates/lib/nostr.ts.tpl 5.0 KB
- templates/lib/resend.ts.tpl 1.1 KB
- templates/lib/waitlist/adapters/postgres.ts.tpl 1.2 KB
- templates/lib/waitlist/adapters/resend-audience.ts.tpl 1.2 KB
- templates/lib/waitlist/adapters/sqlite.ts.tpl 1.3 KB
- templates/lib/waitlist/adapters/supabase.ts.tpl 1.2 KB
- templates/lib/waitlist/adapters/webhook.ts.tpl 1.0 KB
- templates/lib/waitlist/destinations.ts.tpl 851 B
- templates/lib/waitlist/run.ts.tpl 643 B
- templates/lib/waitlist/types.ts.tpl 768 B
- templates/nostr/nostr-welcome.txt.tpl 176 B
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 · 257 lines · 144 tokens per session scan B ca8ad22ef36c
nostr-waitlist is a skill published in the GitHub repository agustinkassis/claude-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 144 tokens to every session and 2,954 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…