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 NovadaLabs/Novada-mcp --skill novada-scrapegit clone --depth 1 https://github.com/NovadaLabs/Novada-mcpWrote 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/novadalabs/novada-mcp/novada-scrape)<a href="https://agentmods.dev/skills/novadalabs/novada-mcp/novada-scrape"><img src="https://agentmods.dev/badge/skills/novadalabs/novada-mcp/novada-scrape/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/novadalabs/novada-mcp/novada-scrape"><img src="https://agentmods.dev/badge/skills/novadalabs/novada-mcp/novada-scrape.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 | $0.00000 | $0.01492 |
| Opus 5.5 | $0.00000 | $0.00597 |
| Sonnet 5.5 | $0.00000 | $0.00298 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade C, and why
novada-scrape scanned grade C with 1 finding 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 17d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
**When to use:** You need structured records from a known platform (Amazon, TikTok, LinkedIn, GitHub, etc.) — not raw HTML, but clean tabular data. 16 platforms are in the catalog: Amazon, Walmart, SHEIN, Google (incl. S How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
novada_scrape — Platform Scraper Skill
When to use: You need structured records from a known platform (Amazon, TikTok, LinkedIn, GitHub, etc.) — not raw HTML, but clean tabular data. 16 platforms are in the catalog: Amazon, Walmart, SHEIN, Google (incl. Shopping), Bing, DuckDuckGo, Yandex, X/Twitter, TikTok, Instagram, Facebook, YouTube, LinkedIn, GitHub, ChatGPT, Perplexity. 14 of those 16 have a dedicated novada_scrape_<platform> tool (see below) — ChatGPT doesn't (both of its catalog operations are backend-dead), and as of 2026-10-13 SHEIN no longer does either (all 5 of its catalog operations are backend_broken — live-verified — so its tool was removed rather than left with zero working operations). Note: 11 operations across the catalog are currently backend-broken (forwarded with a warning via generic novada_scrape — backend may fix any day); the other 76 are verified working (as of 2026-07-13, except where a later date is noted against a specific op).
Prefer the dedicated novada_scrape_<platform> tool over generic novada_scrape
For these 14 platforms, call the dedicated tool instead of generic novada_scrape — its operation parameter is a closed, typed enum scoped to exactly that platform's verified-working operations. This removes the two failure modes generic novada_scrape is prone to: error 11008 (wrong/misspelled platform name) and picking an operation ID that belongs to a different platform. Same params shape otherwise (params, limit, format), same output rendering.
| Tool | Platform | Verified ops |
|---|---|---|
novada_scrape_amazon |
amazon.com | 10 |
novada_scrape_google |
google.com | 13 |
novada_scrape_bing |
bing.com | 4 |
novada_scrape_duckduckgo |
duckduckgo.com | 1 |
novada_scrape_yandex |
yandex.com | 1 |
novada_scrape_youtube |
youtube.com | 12 |
novada_scrape_instagram |
instagram.com | 7 |
novada_scrape_facebook |
facebook.com | 6 |
novada_scrape_tiktok |
tiktok.com | 5 |
novada_scrape_x |
x.com / twitter.com | 3 |
novada_scrape_walmart |
walmart.com | 5 |
novada_scrape_linkedin |
linkedin.com | 4 |
novada_scrape_github |
github.com | 3 |
novada_scrape_perplexity |
perplexity.ai | 2 |
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.
- 17d ago Changed scan A → C 6ab50925df04
- 22d ago Changed · -1 lines f79047daa4ff
- 2mo ago First seen · 100 lines · 0 tokens per session scan A 6cf69d5f95dd
novada-scrape is a skill published in the GitHub repository NovadaLabs/Novada-mcp (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,492 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
novada-scrape compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| novada-scrapeNovadaLabs/Novada-mcp | Skill | 3 | today | MIT | C | 0 | Claude Code, Codex |
| web-readingellmos-ai/skills | Skill | 9 | 4d ago | MIT | A | 56 | Claude Code, Codex |
| crawl4ai-skilllancelin111/crawl4ai-skill | Skill | 17 | 8mo ago | MIT | A | 63 | Claude Code, Codex |
| x402browser-use/browser-use | Skill | 120k | yesterday | MIT | A | 175 | Claude Code |
| browser-usebrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 57 | Claude Code, Codex |
| blocked-page-recoveryNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 25 | Claude Code, Codex |
| playwrightopenai/openai-agents-python | Skill | 31k | yesterday | MIT | A | 19 | Claude Code, Codex |