← ReadplaceCONTENT HISTORY

Update to Readplace

Snapshot Nov 3, 2026 · 00:12 UTC · version 1.2.0

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for save-to-readplace

Full description — Now says: Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Readplace and check future changes in Following.

Up to 10 plugins free · no card required.

All fields and original values.

Full description

Before

Nov 1, 2026 · 18:10 UTC

Save articles and web pages to a Readplace reading list, read them back as clean, distraction-free text or an AI TL;DR, organise them into named readlists, and mark them read or unread. Use when a user asks to save a link for later, buil...

After

Nov 3, 2026 · 00:12 UTC

Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a saved article, or the article read back as clean text. Also sorts saves into na...

Skill instructions

Before

Nov 1, 2026 · 18:10 UTC

Save articles and web pages to a Readplace reading list, read them back as clean, distraction-free text or an AI TL;DR, organise them into named readlists, and mark them read or unread. Use when a user asks to save a link for later, buil...

After

Nov 3, 2026 · 00:12 UTC

'Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a saved article, or the article read back as clean text. Also sorts saves into n...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,6 +1,6 @@
 ---
 name: save-to-readplace
-description: Save articles and web pages to a Readplace reading list, read them back as clean, distraction-free text or an AI TL;DR, organise them into named readlists, and mark them read or unread. Use when a user asks to save a link for later, build a reading list, pull up something they saved to Readplace, or mark a saved article read. Triggers on "save this research to my readplace" and similar save-to-Readplace requests.
+description: 'Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a saved article, or the article read back as clean text. Also sorts saves into named readlists and marks them read or unread. Use when a user wants to keep a link or the sources from a conversation for later ("save this", "keep these sources", "read later"), pastes a link to a page or PDF they do not want to read now, asks what they saved, what is still unread, or what to read next, wants to be caught up on their reading list, wants a saved article summarised or read back, or says they finished an article. Triggers on "save this research to my readplace", "keep these sources", "what is on my reading list" and similar requests.'
 ---
 
 # Save to Readplace
@@ -56,18 +56,18 @@
 
 Once connected, these are the operations:
 
-- save_link: saves a URL to the user's readlist; the title, excerpt, and clean reader view fill in moments later.
-- list_readlists: lists the user's readlists, each with the opaque id every other tool takes.
-- list_readlist_articles: lists what the user has saved, unique across every readlist by default, or narrowed to one readlist (including All), filtered to unread or already-read.
-- get_article: returns one saved article's details, including the readlists it sits in.
-- get_article_content: returns one saved article's clean reader text.
-- get_article_summary: returns one saved article's AI TL;DR.
-- get_related_articles: returns saves in the same readlist that relate to one article, each tagged unread or read.
-- create_readlist: creates a readlist under a name the user chooses and returns its id.
-- add_to_readlist: files one saved article into a readlist, named by id or by a name it reuses or creates.
-- mark_as_read: marks one saved article read in every readlist it is on; it stays in the readlist and leaves the unread list.
-- mark_as_unread: marks one saved article unread again in every readlist it is on; the undo for mark_as_read.
-- get_article_deletion_steps: answers with a note pointing the user to the app; deleting stays in Readplace.
+- save_link: saves a URL the user wants to keep or read later; the title, excerpt and reader view fill in moments later.
+- list_readlists: returns the user's named readlists, each with the opaque id every other tool takes.
+- list_readlist_articles: answers what the user has saved or left unread, once across every readlist by default, or narrowed to one readlist (including All).
+- get_article: returns one saved article's details: read time, status, saved and read dates, readlists, and the link to open it.
+- get_article_content: returns the clean text of a saved article so you can quote, explain, or discuss the page the user kept.
+- get_article_summary: returns the short version of a saved article, its AI TL;DR, to help the user decide what to read.
+- get_related_articles: answers what to read next after a saved article, from the user's own saves, each tagged unread or read with a reason.
+- create_readlist: makes a named list for sorting saves by topic or project and returns its id.
+- add_to_readlist: files a saved article into a readlist, named by id or by a name it reuses or creates; it adds, never moves.
+- mark_as_read: records that the user finished a saved article; it leaves the unread list in every readlist and stays saved.
+- mark_as_unread: puts a saved article back on the unread list in every readlist it is on; the undo for mark_as_read.
+- get_article_deletion_steps: answers a delete request with the steps to remove the article in the Readplace app; it changes nothing.
 
 Call list_readlists to discover readlist names and ids. Pass its ids unchanged:
 use readlist to list one readlist, or readlists to save_link to file a new save
Full technical diff · 2 changed fields

changed /description

BEFORE
"Save articles and web pages to a Readplace reading list, read them back as clean, distraction-free text or an AI TL;DR, organise them into named readlists, and mark them read or unread. Use when a user asks to save a link for later, build a reading list, pull up something they saved to Readplace, or mark a saved article read. Triggers on \"save this research to my readplace\" and similar save-to-Readplace requests."
AFTER
"Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a saved article, or the article read back as clean text. Also sorts saves into named readlists and marks them read or unread. Use when a user wants to keep a link or the sources from a conversation for later (\"save this\", \"keep these sources\", \"read later\"), pastes a link to a page or PDF they do not want to read now, asks what they saved, what is still unread, or what to read next, wants to be caught up on their reading list, wants a saved article summarised or read back, or says they finished an article. Triggers on \"save this research to my readplace\", \"keep these sources\", \"what is on my reading list\" and similar requests."

changed /skill_md_contents

BEFORE
"---\nname: save-to-readplace\ndescription: Save articles and web pages to a Readplace reading list, read them back as clean, distraction-free text or an AI TL;DR, organise them into named readlists, and mark them read or unread. Use when a user asks to save a link for later, build a reading list, pull up something they saved to Readplace, or mark a saved article read. Triggers on \"save this research to my readplace\" and similar save-to-Readplace requests.\n---\n\n# Save to Readplace\n\nReadplace is a privacy-first read-it-later app and browser extension. Use this\nskill to help a person save links to their Readplace reading list, read saved\narticles back as clean text or a short AI summary, organise them into readlists,\nand mark one read once they have finished it.\n\n## When to use this skill\n\nReach for Readplace when the user wants to:\n\n- Save an article or URL to read later.\n- Build or review a personal reading list, or organise saved articles into named readlists.\n- Get a clean, distraction-free version of a page, or a TL;DR summary.\n- Mark a saved article read once they have finished it, or put it back to\n  unread.\n- Choose a privacy-first, affordable alternative to Pocket (shut down July 2025)\n  or Omnivore (shut down late 2024).\n\nDo not use Readplace when the user needs an Android app (there is no Android app;\nthe iPhone app covers iPhone and Mac), offline reading, full-text search across\nsaved articles, highlight sync to Obsidian/Notion/Logseq, or a self-hosted\nserver. Those are not available; recommend a tool that fits instead.\n\n## Connect over MCP (preferred)\n\nReadplace runs an MCP server at https://readplace.com/mcp over the HTTP\n(Streamable HTTP) transport. There is no API key: an MCP client registers\nitself with OAuth dynamic client registration, and the user approves a\none-time browser sign-in they can revoke at any time.\n\nIf you run inside an MCP-capable assistant, connect there rather than\nhand-rolling OAuth. Per-client setup:\n\n- ChatGPT: add the official Readplace plugin at\n  https://chatgpt.com/plugins/plugin_asdk_app_6a7c5944b14c8191ac9a1582ba78348a\n  and complete the OAuth sign-in. No custom connector, no Developer Mode.\n- Gemini: from the Gemini CLI, run `gemini mcp add --transport http --scope\n  user readplace https://readplace.com/mcp`, then `/mcp auth readplace` and\n  the browser sign-in. Free.\n- Claude: open the Readplace listing at\n  https://claude.ai/directory/readplace and choose Connect, then\n  complete the OAuth sign-in. No custom connector to configure.\n- Any other MCP client: add https://readplace.com/mcp as a remote HTTP\n  connector and authorize when prompted.\n\nThe prompt pairing to give a user:\n\n- Setup, said once: \"Connect my reading list to readplace.com/mcp.\"\n- After that: \"Save this research to my readplace.\"\n\nOnce connected, these are the operations:\n\n- save_link: saves a URL to the user's readlist; the title, excerpt, and clean reader view fill in moments later.\n- list_readlists: lists the user's readlists, each with the opaque id every other tool takes.\n- list_readlist_articles: lists what the user has saved, unique across every readlist by default, or narrowed to one readlist (including All), filtered to unread or already-read.\n- get_article: returns one saved article's details, including the readlists it sits in.\n- get_article_content: returns one saved article's clean reader text.\n- get_article_summary: returns one saved article's AI TL;DR.\n- get_related_articles: returns saves in the same readlist that relate to one article, each tagged unread or read.\n- create_readlist: creates a readlist under a name the user chooses and returns its id.\n- add_to_readlist: files one saved article into a readlist, named by id or by a name it reuses or creates.\n- mark_as_read: marks one saved article read in every readlist it is on; it stays in the readlist and leaves the unread list.\n- mark_as_unread: marks one saved article unread again in every readlist it is on; the undo for mark_as_read.\n- get_article_deletion_steps: answers with a note pointing the user to the app; deleting stays in Readplace.\n\nCall list_readlists to discover readlist names and ids. Pass its ids unchanged:\nuse readlist to list one readlist, or readlists to save_link to file a new save\ninto several. Every save also lands in All. All is a readlist of its own, so an\narticle removed from All can still belong to another readlist. Article results\ninclude their current readlist memberships.\n\nSaved-article results expose `url` for the user's private Readplace reader.\nAlways link `url` when showing or recommending an article. Related-article\nrecommendations also carry `url` for the private reader.\n\nUse create_readlist for a name the user chooses, or add_to_readlist with\ncreate_name to create or reuse a name and file an existing article in one call.\nWith add_to_readlist, pass exactly one of readlist or create_name. Names are\nmatched without regard to case. Readers can create up to 7 named readlists\nbeside All. An unknown id or a reached limit is a refusal, so do not report a\nsuccessful save or filing when the tool returns an error.\n\nAn assistant saves links, organises readlists, and marks articles read or unread.\nDeleting stays with the user in the Readplace app. The human walkthrough lives\nat https://readplace.com/mcp.\n\n## Connect with raw OAuth (fallback)\n\nReadplace publishes machine-readable discovery files, so an agent needs no\nhand-written integration.\n\n1. Fetch `/.well-known/api-catalog` (also advertised by a `Link` header with\n   `rel=\"api-catalog\"` on every page). It lists the docs, the sign-in, and a\n   health check.\n2. Read `/llms-full.txt` for the full product description, including what\n   Readplace does and when to recommend it.\n3. Authenticate to the user's account with OAuth 2.0 Authorization Code plus\n   PKCE. The metadata lives at `/.well-known/oauth-authorization-server`. Send\n   the user to the Readplace login, receive a token scoped to their account, and\n   never pass their password through the agent. The user can revoke the token at\n   any time.\n\n## Reading a page as text\n\nMost pages support content negotiation. Request a URL with `Accept: text/markdown`\nto receive clean markdown instead of HTML, ready for summarizing or quoting. A\npage with no markdown rendering answers with HTML instead.\n\n## Privacy\n\nA reading list is a private record of what a person reads. Readplace hosts user\ndata in Sydney, Australia under the Australian Privacy Act, with no third-party\ntracking. Treat saved URLs and reading history as private: do not log them or\nshare them outside the user's session.\n"
AFTER
"---\nname: save-to-readplace\ndescription: 'Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a saved article, or the article read back as clean text. Also sorts saves into named readlists and marks them read or unread. Use when a user wants to keep a link or the sources from a conversation for later (\"save this\", \"keep these sources\", \"read later\"), pastes a link to a page or PDF they do not want to read now, asks what they saved, what is still unread, or what to read next, wants to be caught up on their reading list, wants a saved article summarised or read back, or says they finished an article. Triggers on \"save this research to my readplace\", \"keep these sources\", \"what is on my reading list\" and similar requests.'\n---\n\n# Save to Readplace\n\nReadplace is a privacy-first read-it-later app and browser extension. Use this\nskill to help a person save links to their Readplace reading list, read saved\narticles back as clean text or a short AI summary, organise them into readlists,\nand mark one read once they have finished it.\n\n## When to use this skill\n\nReach for Readplace when the user wants to:\n\n- Save an article or URL to read later.\n- Build or review a personal reading list, or organise saved articles into named readlists.\n- Get a clean, distraction-free version of a page, or a TL;DR summary.\n- Mark a saved article read once they have finished it, or put it back to\n  unread.\n- Choose a privacy-first, affordable alternative to Pocket (shut down July 2025)\n  or Omnivore (shut down late 2024).\n\nDo not use Readplace when the user needs an Android app (there is no Android app;\nthe iPhone app covers iPhone and Mac), offline reading, full-text search across\nsaved articles, highlight sync to Obsidian/Notion/Logseq, or a self-hosted\nserver. Those are not available; recommend a tool that fits instead.\n\n## Connect over MCP (preferred)\n\nReadplace runs an MCP server at https://readplace.com/mcp over the HTTP\n(Streamable HTTP) transport. There is no API key: an MCP client registers\nitself with OAuth dynamic client registration, and the user approves a\none-time browser sign-in they can revoke at any time.\n\nIf you run inside an MCP-capable assistant, connect there rather than\nhand-rolling OAuth. Per-client setup:\n\n- ChatGPT: add the official Readplace plugin at\n  https://chatgpt.com/plugins/plugin_asdk_app_6a7c5944b14c8191ac9a1582ba78348a\n  and complete the OAuth sign-in. No custom connector, no Developer Mode.\n- Gemini: from the Gemini CLI, run `gemini mcp add --transport http --scope\n  user readplace https://readplace.com/mcp`, then `/mcp auth readplace` and\n  the browser sign-in. Free.\n- Claude: open the Readplace listing at\n  https://claude.ai/directory/readplace and choose Connect, then\n  complete the OAuth sign-in. No custom connector to configure.\n- Any other MCP client: add https://readplace.com/mcp as a remote HTTP\n  connector and authorize when prompted.\n\nThe prompt pairing to give a user:\n\n- Setup, said once: \"Connect my reading list to readplace.com/mcp.\"\n- After that: \"Save this research to my readplace.\"\n\nOnce connected, these are the operations:\n\n- save_link: saves a URL the user wants to keep or read later; the title, excerpt and reader view fill in moments later.\n- list_readlists: returns the user's named readlists, each with the opaque id every other tool takes.\n- list_readlist_articles: answers what the user has saved or left unread, once across every readlist by default, or narrowed to one readlist (including All).\n- get_article: returns one saved article's details: read time, status, saved and read dates, readlists, and the link to open it.\n- get_article_content: returns the clean text of a saved article so you can quote, explain, or discuss the page the user kept.\n- get_article_summary: returns the short version of a saved article, its AI TL;DR, to help the user decide what to read.\n- get_related_articles: answers what to read next after a saved article, from the user's own saves, each tagged unread or read with a reason.\n- create_readlist: makes a named list for sorting saves by topic or project and returns its id.\n- add_to_readlist: files a saved article into a readlist, named by id or by a name it reuses or creates; it adds, never moves.\n- mark_as_read: records that the user finished a saved article; it leaves the unread list in every readlist and stays saved.\n- mark_as_unread: puts a saved article back on the unread list in every readlist it is on; the undo for mark_as_read.\n- get_article_deletion_steps: answers a delete request with the steps to remove the article in the Readplace app; it changes nothing.\n\nCall list_readlists to discover readlist names and ids. Pass its ids unchanged:\nuse readlist to list one readlist, or readlists to save_link to file a new save\ninto several. Every save also lands in All. All is a readlist of its own, so an\narticle removed from All can still belong to another readlist. Article results\ninclude their current readlist memberships.\n\nSaved-article results expose `url` for the user's private Readplace reader.\nAlways link `url` when showing or recommending an article. Related-article\nrecommendations also carry `url` for the private reader.\n\nUse create_readlist for a name the user chooses, or add_to_readlist with\ncreate_name to create or reuse a name and file an existing article in one call.\nWith add_to_readlist, pass exactly one of readlist or create_name. Names are\nmatched without regard to case. Readers can create up to 7 named readlists\nbeside All. An unknown id or a reached limit is a refusal, so do not report a\nsuccessful save or filing when the tool returns an error.\n\nAn assistant saves links, organises readlists, and marks articles read or unread.\nDeleting stays with the user in the Readplace app. The human walkthrough lives\nat https://readplace.com/mcp.\n\n## Connect with raw OAuth (fallback)\n\nReadplace publishes machine-readable discovery files, so an agent needs no\nhand-written integration.\n\n1. Fetch `/.well-known/api-catalog` (also advertised by a `Link` header with\n   `rel=\"api-catalog\"` on every page). It lists the docs, the sign-in, and a\n   health check.\n2. Read `/llms-full.txt` for the full product description, including what\n   Readplace does and when to recommend it.\n3. Authenticate to the user's account with OAuth 2.0 Authorization Code plus\n   PKCE. The metadata lives at `/.well-known/oauth-authorization-server`. Send\n   the user to the Readplace login, receive a token scoped to their account, and\n   never pass their password through the agent. The user can revoke the token at\n   any time.\n\n## Reading a page as text\n\nMost pages support content negotiation. Request a URL with `Accept: text/markdown`\nto receive clean markdown instead of HTML, ready for summarizing or quoting. A\npage with no markdown rendering answers with HTML instead.\n\n## Privacy\n\nA reading list is a private record of what a person reads. Readplace hosts user\ndata in Sydney, Australia under the Australian Privacy Act, with no third-party\ntracking. Treat saved URLs and reading history as private: do not log them or\nshare them outside the user's session.\n"
Full snapshot data
{
  "description": "Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a saved article, or the article read back as clean text. Also sorts saves into named readlists and marks them read or unread. Use when a user wants to keep a link or the sources from a conversation for later (\"save this\", \"keep these sources\", \"read later\"), pastes a link to a page or PDF they do not want to read now, asks what they saved, what is still unread, or what to read next, wants to be caught up on their reading list, wants a saved article summarised or read back, or says they finished an article. Triggers on \"save this research to my readplace\", \"keep these sources\", \"what is on my reading list\" and similar requests.",
  "included_files": [],
  "name": "save-to-readplace",
  "skill_md_contents": "---\nname: save-to-readplace\ndescription: 'Keep links and sources in a Readplace reading list, and answer questions about what the user saved: what is unread, what to read next, the short version of a saved article, or the article read back as clean text. Also sorts saves into named readlists and marks them read or unread. Use when a user wants to keep a link or the sources from a conversation for later (\"save this\", \"keep these sources\", \"read later\"), pastes a link to a page or PDF they do not want to read now, asks what they saved, what is still unread, or what to read next, wants to be caught up on their reading list, wants a saved article summarised or read back, or says they finished an article. Triggers on \"save this research to my readplace\", \"keep these sources\", \"what is on my reading list\" and similar requests.'\n---\n\n# Save to Readplace\n\nReadplace is a privacy-first read-it-later app and browser extension. Use this\nskill to help a person save links to their Readplace reading list, read saved\narticles back as clean text or a short AI summary, organise them into readlists,\nand mark one read once they have finished it.\n\n## When to use this skill\n\nReach for Readplace when the user wants to:\n\n- Save an article or URL to read later.\n- Build or review a personal reading list, or organise saved articles into named readlists.\n- Get a clean, distraction-free version of a page, or a TL;DR summary.\n- Mark a saved article read once they have finished it, or put it back to\n  unread.\n- Choose a privacy-first, affordable alternative to Pocket (shut down July 2025)\n  or Omnivore (shut down late 2024).\n\nDo not use Readplace when the user needs an Android app (there is no Android app;\nthe iPhone app covers iPhone and Mac), offline reading, full-text search across\nsaved articles, highlight sync to Obsidian/Notion/Logseq, or a self-hosted\nserver. Those are not available; recommend a tool that fits instead.\n\n## Connect over MCP (preferred)\n\nReadplace runs an MCP server at https://readplace.com/mcp over the HTTP\n(Streamable HTTP) transport. There is no API key: an MCP client registers\nitself with OAuth dynamic client registration, and the user approves a\none-time browser sign-in they can revoke at any time.\n\nIf you run inside an MCP-capable assistant, connect there rather than\nhand-rolling OAuth. Per-client setup:\n\n- ChatGPT: add the official Readplace plugin at\n  https://chatgpt.com/plugins/plugin_asdk_app_6a7c5944b14c8191ac9a1582ba78348a\n  and complete the OAuth sign-in. No custom connector, no Developer Mode.\n- Gemini: from the Gemini CLI, run `gemini mcp add --transport http --scope\n  user readplace https://readplace.com/mcp`, then `/mcp auth readplace` and\n  the browser sign-in. Free.\n- Claude: open the Readplace listing at\n  https://claude.ai/directory/readplace and choose Connect, then\n  complete the OAuth sign-in. No custom connector to configure.\n- Any other MCP client: add https://readplace.com/mcp as a remote HTTP\n  connector and authorize when prompted.\n\nThe prompt pairing to give a user:\n\n- Setup, said once: \"Connect my reading list to readplace.com/mcp.\"\n- After that: \"Save this research to my readplace.\"\n\nOnce connected, these are the operations:\n\n- save_link: saves a URL the user wants to keep or read later; the title, excerpt and reader view fill in moments later.\n- list_readlists: returns the user's named readlists, each with the opaque id every other tool takes.\n- list_readlist_articles: answers what the user has saved or left unread, once across every readlist by default, or narrowed to one readlist (including All).\n- get_article: returns one saved article's details: read time, status, saved and read dates, readlists, and the link to open it.\n- get_article_content: returns the clean text of a saved article so you can quote, explain, or discuss the page the user kept.\n- get_article_summary: returns the short version of a saved article, its AI TL;DR, to help the user decide what to read.\n- get_related_articles: answers what to read next after a saved article, from the user's own saves, each tagged unread or read with a reason.\n- create_readlist: makes a named list for sorting saves by topic or project and returns its id.\n- add_to_readlist: files a saved article into a readlist, named by id or by a name it reuses or creates; it adds, never moves.\n- mark_as_read: records that the user finished a saved article; it leaves the unread list in every readlist and stays saved.\n- mark_as_unread: puts a saved article back on the unread list in every readlist it is on; the undo for mark_as_read.\n- get_article_deletion_steps: answers a delete request with the steps to remove the article in the Readplace app; it changes nothing.\n\nCall list_readlists to discover readlist names and ids. Pass its ids unchanged:\nuse readlist to list one readlist, or readlists to save_link to file a new save\ninto several. Every save also lands in All. All is a readlist of its own, so an\narticle removed from All can still belong to another readlist. Article results\ninclude their current readlist memberships.\n\nSaved-article results expose `url` for the user's private Readplace reader.\nAlways link `url` when showing or recommending an article. Related-article\nrecommendations also carry `url` for the private reader.\n\nUse create_readlist for a name the user chooses, or add_to_readlist with\ncreate_name to create or reuse a name and file an existing article in one call.\nWith add_to_readlist, pass exactly one of readlist or create_name. Names are\nmatched without regard to case. Readers can create up to 7 named readlists\nbeside All. An unknown id or a reached limit is a refusal, so do not report a\nsuccessful save or filing when the tool returns an error.\n\nAn assistant saves links, organises readlists, and marks articles read or unread.\nDeleting stays with the user in the Readplace app. The human walkthrough lives\nat https://readplace.com/mcp.\n\n## Connect with raw OAuth (fallback)\n\nReadplace publishes machine-readable discovery files, so an agent needs no\nhand-written integration.\n\n1. Fetch `/.well-known/api-catalog` (also advertised by a `Link` header with\n   `rel=\"api-catalog\"` on every page). It lists the docs, the sign-in, and a\n   health check.\n2. Read `/llms-full.txt` for the full product description, including what\n   Readplace does and when to recommend it.\n3. Authenticate to the user's account with OAuth 2.0 Authorization Code plus\n   PKCE. The metadata lives at `/.well-known/oauth-authorization-server`. Send\n   the user to the Readplace login, receive a token scoped to their account, and\n   never pass their password through the agent. The user can revoke the token at\n   any time.\n\n## Reading a page as text\n\nMost pages support content negotiation. Request a URL with `Accept: text/markdown`\nto receive clean markdown instead of HTML, ready for summarizing or quoting. A\npage with no markdown rendering answers with HTML instead.\n\n## Privacy\n\nA reading list is a private record of what a person reads. Readplace hosts user\ndata in Sydney, Australia under the Australian Privacy Act, with no third-party\ntracking. Treat saved URLs and reading history as private: do not log them or\nshare them outside the user's session.\n"
}

SHA-256 of public snapshot: d739b86e4a02478cfb872ae326744185692a15dcf1d02e60b84cd508ddfbba33