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 ohong/agent-skills --skill save2mdgit clone --depth 1 https://github.com/ohong/agent-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/ohong/agent-skills/save2md)<a href="https://agentmods.dev/skills/ohong/agent-skills/save2md"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/save2md/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/ohong/agent-skills/save2md"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/save2md.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 | $0.00043 | $0.00449 |
| Opus 5.5 | $0.00017 | $0.00180 |
| Sonnet 5.5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
save2md 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 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.
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.
What it actually says
Save to Markdown
Turn one URL into a durable local Markdown archive. Preserve the source URL, use the strongest available source, inspect the result, and return the absolute Markdown path.
Route by URL
- Normalize the URL and identify its host.
- Use exactly one source workflow:
youtube.comoryoutu.be: read references/youtube.md.x.comortwitter.com: read references/x.md.- Any other web or archive URL: read references/web-articles.md.
- Use the user's requested destination. Otherwise use
~/Documents/Saved Articles/with the source subfolderWeb,X, orYouTube. Name the final Markdown file from the extracted title, using a filesystem-safe version of the title, never a generic name such asarticle.md. - Open or inspect the generated Markdown before responding. Reject CAPTCHA pages, paywall prompts without article text, navigation chrome, empty transcripts, broken media, and suspiciously short output.
- Keep the final response short and link the absolute Markdown path. Mention any fallback, incomplete extraction, or podcast-to-YouTube substitution.
Shared rules
- Do not invent text, metadata, authors, dates, media, or archive URLs.
- Prefer structured text or rendered DOM extraction over OCR.
- Preserve useful source metadata and local media when the source provides it.
- Use the extracted title for the final Markdown filename. Preserve readable capitalization and punctuation where the filesystem permits; replace only unsafe filename characters. If no title can be extracted, use the URL-derived title.
- For paywalled articles, try archive.today/archive.ph first, then a readable-text fallback or browser-saved HTML. Clearly label fallbacks.
- Do not ask the user to choose an extraction method. Try the safe routes in order and report a blocker only after they fail.
What ships with it
8 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.
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 · 29 lines · 43 tokens per session scan A 99d5a098b9f8
save2md is a skill published in the GitHub repository ohong/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 449 once invoked, about $0.0002 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.