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 mysleekdesigns/crawlforge-mcp --skill crawlforge-structured-extractiongit clone --depth 1 https://github.com/mysleekdesigns/crawlforge-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/mysleekdesigns/crawlforge-mcp/crawlforge-structured-extraction)<a href="https://agentmods.dev/skills/mysleekdesigns/crawlforge-mcp/crawlforge-structured-extraction"><img src="https://agentmods.dev/badge/skills/mysleekdesigns/crawlforge-mcp/crawlforge-structured-extraction/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/mysleekdesigns/crawlforge-mcp/crawlforge-structured-extraction"><img src="https://agentmods.dev/badge/skills/mysleekdesigns/crawlforge-mcp/crawlforge-structured-extraction.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 | $0.00172 | $0.02178 |
| Opus 5.5 | $0.00069 | $0.00871 |
| Sonnet 5.5 | $0.00034 | $0.00436 |
| Haiku 4.5 | $0.00017 | $0.00218 |
Grade A, and why
crawlforge-structured-extraction 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 8d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrawlForge Structured Extraction & Analysis
Turn pages and documents into structured data, and run NLP analysis. Pick the extraction method by how predictable the page is and whether an LLM is needed.
Tool selection
| You have / want | Tool | Cost |
|---|---|---|
| A well-known site (Amazon, GitHub, LinkedIn...) | scrape_template |
1 |
| Exact CSS selectors for the fields | scrape_structured |
2 |
| The data is in the page's JS state, not its HTML | extract_embedded_state |
2 |
| A JSON schema to fill (LLM, CSS fallback) | extract_structured |
3 |
| A natural-language extraction instruction | extract_with_llm |
3 |
| A PDF / DOCX / TXT to parse | process_document |
2 |
| A summary of long text | summarize_content |
4 |
| Sentiment / entities / keywords / readability | analyze_content |
3 |
| To list local LLMs available for extraction | list_ollama_models |
1 |
Cheapest-first rule: try scrape_template → scrape_structured /
extract_embedded_state (all deterministic) before reaching for the LLM tools.
On a React/Next/Nuxt page the values are usually sitting in the embedded state
already, exact and typed — that beats asking a model to read them off the render.
extract_embedded_state — the page's own JS state (cost: 2)
{ "tool": "extract_embedded_state", "params": { "url": "https://www.ticketmaster.com/discover/concerts", "path": "next_data.props.pageProps" } }
Finds __NEXT_DATA__, self.__next_f (React Server Component payloads, with
$<id> references between rows resolved and a data_rows index of the rows
carrying data), window.__NUXT__ and Nuxt 3's __NUXT_DATA__ (decoded as
nuxt_data; raw: true also keeps the undecoded array), SvelteKit kit.start
data, __APOLLO_STATE__, __INITIAL_STATE__, __PRELOADED_STATE__,
ytInitialData, ytInitialPlayerResponse, Inertia data-page, Shopify meta and
product JSON, JSON data-* attributes and <script type="application/json">
blocks, keyed by source name. No LLM in the path, so values are exact rather
than inferred.
What ships with it
1 file 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.
- 8d ago Changed 7719bf0748a0
- 14d ago Changed 4a821dec1f81
- 15d ago Changed 83f3851c99f2
- 17d ago Changed 7209aed8a8f5
- 26d ago Changed 0c6ee3f7d7dd
- 1mo ago Changed · +9 lines 79e85ae3e603
- 1mo ago Changed · +10 lines 07661b26bac1
- 2mo ago Changed 945406557925
- 2mo ago First seen · 145 lines · 172 tokens per session scan A 12958dfa7524
crawlforge-structured-extraction is a skill published in the GitHub repository mysleekdesigns/crawlforge-mcp (6 stars, last pushed 5d ago), licensed MIT. It adds 172 tokens to every session and 2,178 once invoked, about $0.0007 per session on Opus 5.5. 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.
crawlforge-structured-extraction compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crawlforge-structured-extractionmysleekdesigns/crawlforge-mcp | Skill | 6 | 5d ago | MIT | A | 172 | Claude Code, Codex |
| skillnoteluna-prompts/skillnote | Skill | 68 | 5d ago | MIT | A | 54 | Claude Code, Codex |
| healthcare-providers-enrichNimbleway/agent-skills | Skill | 61 | 8d ago | MIT | A | 194 | Claude Code |
| healthcare-providers-extractNimbleway/agent-skills | Skill | 61 | 8d ago | MIT | A | 206 | Claude Code |
| talent-sourcingNimbleway/agent-skills | Skill | 61 | 8d ago | MIT | A | 210 | Claude Code |
| chatcrystal-debug-recallZengLiangYi/ChatCrystal | Skill | 60 | 5d ago | Apache-2.0 | A | 54 | Codex |
| verifyyha9806/academic-writing-toolkit | Skill | 54 | 9d ago | MIT | A | 26 | Claude Code |