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 wyattowalsh/agents --skill trafilaturagit clone --depth 1 https://github.com/wyattowalsh/agentsWrote 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/wyattowalsh/agents/trafilatura)<a href="https://agentmods.dev/skills/wyattowalsh/agents/trafilatura"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/trafilatura/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/wyattowalsh/agents/trafilatura"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/trafilatura.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 | $0.00057 | $0.02700 |
| Opus 5.5 | $0.00023 | $0.01080 |
| Sonnet 5.5 | $0.00011 | $0.00540 |
| Haiku 4.5 | $0.00006 | $0.00270 |
Grade A, and why
trafilatura scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. If download blocked: `wget -qO- 'URL' | trafilatura` or `curl -sL 'URL' | trafilatura`. How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trafilatura
CLI skill for trafilatura: extract main article text and metadata from URLs, piped HTML, or local files. Follow the stdout-first protocol before any batch writes.
Scope: Single-page extraction, metadata JSON, piped/local HTML, bounded URL discovery (--list), and user-approved batch processing. NOT for: multi-source research (research), PDF/tables (docling), raw page fetch (fetch/fetcher), video hosts (yt-dlp), or paywall bypass.
Canonical Vocabulary
| Term | Meaning | NOT |
|---|---|---|
| extract | Single URL → clean text via CLI | full crawl harvest |
| metadata | JSON output with with_metadata |
bare URL probe only |
| pipe | Stdin or local .html file as input |
download from URL |
| discover | --feed / --sitemap / --crawl / --probe with --list |
bulk download |
| batch | -i link list → output directory |
silent mass scrape |
| local | --input-dir reprocess saved HTML |
live fetch |
| archived | --archived Internet Archive fallback |
paywall bypass |
| precision | --precision — less noise |
default when content missing |
| recall | --recall — more text |
default when noise high |
| doctor | Preflight JSON for binary and version | live URL smoke |
Dispatch
$ARGUMENTS |
Mode | Action |
|---|---|---|
doctor / preflight |
Doctor | Run scripts/doctor.py --format json |
extract <url> / bare https://… |
Extract | Stdout-first via extract_url.py |
metadata <url> |
Metadata | extract_url.py with --with-metadata --format json |
pipe <file> / stdin HTML |
Pipe | trafilatura on file or stdin |
discover feed <url> |
Discover | list_urls.py --mode feed (--list only) |
discover sitemap <url> |
Discover | list_urls.py --mode sitemap |
discover crawl <url> |
Discover | list_urls.py --mode crawl |
discover probe <url> |
Discover | list_urls.py --mode probe |
batch <listfile> |
Batch | Approval gate → -i + -o under user dir |
local <input-dir> |
Local | Approval gate → --input-dir + -o |
archived <url> |
Archived | extract_url.py --archived after normal fetch fails |
| Natural language: "main text", "clean article", "extract from URL" | Auto | Map to extract (stdout-first) |
| (empty) | Help | Gallery + protocol + references |
What ships with it
11 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 7.4 KB
- references/discovery.md 1.1 KB
- references/mcp-fallback.md 805 B
- references/output-formats.md 1.1 KB
- references/politeness-and-ethics.md 945 B
- references/troubleshooting.md 1.1 KB
- scripts/asset_toolkit/validate_hooks.py 13 KB runs code
- scripts/check.py 2.6 KB runs code
- scripts/doctor.py 3.4 KB runs code
- scripts/extract_url.py 5.3 KB runs code
- scripts/list_urls.py 3.4 KB runs code
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.
- 1mo ago First seen · 266 lines · 57 tokens per session scan A c6c3edc5f1b5
trafilatura is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,700 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…