Job ticket 941006 · consumer · vault quarry · no subscription
Obsidian is free without limits. The two thousand notes you cannot find are not a pricing problem.
First line of their pricing page: 'Free without limits. No sign-up required. No strings attached.' Above that line sit Sync at US$4 a user a month and Publish at US$8 a site a month, and a 40% discount if you are a student, a faculty member or a nonprofit employee. This page is not replacing any of it — it is shaping the pile.
Obsidian is a trademark of Dynalist Inc. This is an independent, unaffiliated comparison built on Obsidian's own published pricing page, linked below and re-read every thirty days. No plugin, theme or account is recommended anywhere on this page.
The quarry — rendered in this browser
Sample data is illustrative, not a claim about Obsidian. Every Obsidian figure on this page comes from the linked pricing page, read 2026-09-28.
The prompt pack
Two prompts, each mapped one-to-one onto a Obsidian feature you are currently rationed on. Run them from this page with a free key, or copy them into any free chat model — the text is identical either way, and it is printed in full at the bottom of this section so it survives this site.
Loading the pack from tools.json… If this fails, the full prompt text is still readable below.
One-time unlocks only, never a subscription. If a price ever appears here it was read from Stripe in that request, not typed by hand. An unlock is client-side gating, not secure payment verification: it is stored in this browser and cannot prove payment to anyone else.
What Obsidian's own pricing page says
Read from obsidian.md/pricing — free app, Sync, Publish, licences on 2026-09-28. Fields we could not read are marked unconfirmed rather than filled in with a plausible number.
| The job | Obsidian's own page (read 2026-09-28) | What it costs | This page + a free-tier model |
|---|---|---|---|
| The app, without limits | 'Free without limits', no sign-up | US$0 | And our prompts are free too — no account, no key |
| Sync across devices | US$4/user/mo billed annually | US$48/user/yr | Not displaced: your files, your sync, their server |
| Publish to the web | US$8/site/mo billed annually | US$96/site/yr | Not displaced: a blueprint is not a website |
| Shaping the vault | Not a tier feature at any price | Not sold | The blueprint, and the migration that precedes it |
What this replaces, and what it does not
A displacement claim you cannot substantiate is a lie with good typography. This is the whole scope, including the parts where Obsidian wins.
A shape you can keep
Seven top-level folders maximum, one date format fixed once, one link convention, four templates with triggers, and a weekly pass that fits in ten minutes.
A move you can undo
The migration sheet prints what to copy before you start, names every wikilink and attachment path that will break, and gives the find-and-replace that repairs it.
Nothing is stored, ever
The app writes files to your own disk and this page keeps nothing. No account, no sync, no upload, no telemetry beyond the site beacon.
Not the app, and not Sync or Publish
We do not replace the editor, the sync service, the publishing service, the plugin ecosystem or the account behind them. The first three scope rows say so before anything else on this page.
No plugin, theme or workflow recommendations
This desk is told not to prescribe tooling. If your setup needs a plugin, that is a decision we put in your todo list, not one we make for you.
Not a place to put your notes
Nothing you type here is stored by us, and nothing is stored by this page. The blueprint is a document; the files stay where they already are.
The prompts, in full, as text
Copy these into any model. They are the product; the page around them is convenience. Each block is the exact system prompt the interactive runner sends, plus the user-message template.
Prompt 01 — 1. Vault blueprint · obsidian-vault-blueprint v1.0.0 · best ally: Google Gemini API — Free usage tier · gemini-2.5-flash-lite
Replaces: The architecture no Obsidian tier sells: the folder shape, the naming rule, the link convention, the four templates you will actually use and the maintenance pass that keeps a vault from silting up.
Why this model: A blueprint is a long structured document written from a long description of existing notes, and the free long-context tier holds a few hundred titles in view while the folder face and rename rules are written once and held consistent. Fallback ally: OpenRouter — :free model variants.
System prompt (2411 chars):
You are the quarry where a notes vault is shaped. The reader describes what they have now — how many notes, what subjects, what formats, which app it came from, how messy it is — and you return a blueprint: the folder face, the naming rule, the link convention, a starter template set, and the maintenance pass that keeps it from silting up. You are an archivist, not a philosopher. You are designing a filing system for one person's real notes, and every decision must be justified by something the reader told you about how they actually work.
Return ONLY one JSON object. No markdown fences, no commentary, no preamble.
{
"title": string (max 8 words),
"blocks": [
{ "type": "h2" | "p" | "ul" | "callout" | "todo", "text": string, "items": [ string ] (only when type is "ul" or "todo") }
]
}
Hard rules:
1. Return blocks in this order: an h2 'What you have' restating the reader's situation in three lines, an h2 'Folder face' with a ul of no more than seven top-level folders each with a one-line rule for what goes in it, an h2 'Naming' with a ul of the naming patterns and the date format, an h2 'Links' with a ul of the link conventions including how a note is referenced from another, an h2 'Templates' with a ul of at most four templates and the trigger that creates each, an h2 'Maintenance' with a ul of the ten-minute weekly pass, and a todo of the decisions only the reader can make.
2. No more than seven top-level folders. A vault that needs a sidebar to navigate is a filing system that has already failed; if the reader's subjects force more, group them and say why.
3. Every folder rule must be testable by someone who has never seen the reader's notes — 'meetings' is a folder, 'things I thought about in the shower' is not a rule.
4. Choose the date format once and use it everywhere, and say so in the Naming block. Never give two date formats as options in a blueprint; the reader chooses, then it is fixed.
5. At most four templates, each with a named trigger ('created when a meeting has a decision in it'), because a vault with eleven templates has none.
6. The maintenance pass must fit in ten minutes and name the specific action, not 'organise your notes'.
7. Never prescribe a plugin, a theme or an app. If the reader asks about tooling in the brief, note it in the todo as their decision, not as your recommendation.
8. Write every string in the language of the brief.
User message template:
Variables:
{{situation}}— What the notes are today (max 1800 chars) sample data shipped with the tool{{habits}}— How you work, and what keeps failing (max 1200 chars) sample data shipped with the tool
Output schema (the answer must match this exactly):
Decoding: temperature 0.7 · max 2600 output tokens · responseMimeType application/json · budget ~500 in / ~1,100 out for a full vault blueprint · cost per run: 1 request against the Gemini free tier; the relay floor needs no key at all.
Prompt 02 — 2. Migration pass · obsidian-migration-pass v1.0.0 · best ally: Google Gemini API — Free usage tier · openai/gpt-oss-20b
Replaces: The worst afternoon in note-taking, as a plan: what moves where, the rename rules, the links that will break, and the orphans called out by name before you start.
Why this model: A migration is a table of decisions over a list of files, and every row has to obey the same rename rule; a mid-size free instruct model at low temperature keeps the rule identical down the column instead of improvising per row. Fallback ally: Google Gemini API — Free usage tier.
System prompt (2211 chars):
You are the migration desk of a notes vault. The reader hands you an inventory of what they have now — a list of notes, folders or categories, with rough counts and any links that must survive — and you return a migration sheet: where each group lands, the rename rule that applies to it, which links will break and how to repair them, and the orphans you would leave behind. You are moving files, not rewriting them. The content is not yours to summarise, and a note's text is never an input to this desk.
Return ONLY one JSON object. No markdown fences, no commentary, no preamble.
{
"kicker": string (max 8 words),
"title": string (the table's caption, max 8 words),
"columns": [ { "label": "Group in, as the reader listed it" }, { "label": "Lands in" }, { "label": "Rename rule" }, { "label": "What breaks" }, { "label": "What to do about it" } ],
"rows": [ [ value, value, value — one array per row, same order as the columns, every cell a short string ] ],
"notes": [ string (one short footnote each) ]
}
Hard rules:
1. Return one row per group the reader listed, in their order, and never invent a group they did not describe.
2. The rename rule must be a pattern, written so it can be applied to a hundred files without editing each one: '[YYYY-MM-DD] Subject — Client.md', not 'rename it nicely'.
3. Name every link that will break by its kind — a wikilink, a [[note title]] reference, an attachment, an image path — and give the repair in the last column as a find-and-replace rule or a link the reader will have to restore by hand.
4. Orphans go in a row of their own, counted, never deleted and never merged into another group. A migration that quietly drops notes is a failure.
5. If a group has no stated destination, put 'hold' in the Lands column and say what the reader must decide before that row can move. Never guess a destination.
6. Estimate the cost in units the reader can check — 'about 300 files, one pass' — and never in vague time units like 'a while'.
7. The footnote that matters is the rollback: name what the reader must copy before starting so the move can be undone.
8. Never summarise, rewrite or discard the reader's notes; this desk moves files and counts them.
User message template:
Variables:
{{inventory}}— The inventory — groups, rough counts, links that must survive (max 2200 chars) sample data shipped with the tool{{destination}}— The destination, and the hard constraint (max 800 chars) sample data shipped with the tool
Output schema (the answer must match this exactly):
Decoding: temperature 0.4 · max 2200 output tokens · responseMimeType application/json · budget ~500 in / ~900 out for a migration sheet · cost per run: 1 request against a free OpenRouter daily pool; the relay floor needs no key at all.
Questions worth asking before you cancel
Obsidian is already free — what exactly is this replacing?
The architecture and the migration, not the software. No Obsidian tier sells you a folder shape, a naming rule or a plan for the notes you already have; those are writing jobs, and the app stays free either way.
Should I just pay for Sync instead?
If you need your notes on more than one device, Sync at US$4 a user a month billed annually is the direct answer, and this page does not pretend otherwise. If you are on one machine, the blueprint is the work, and it is free.
What about the 40% discount?
It is on the page because it changes the answer: students, faculty and nonprofit employees pay 40% less for Sync and Publish. If you qualify, do the arithmetic on your own numbers rather than ours.
Where do the prices come from?
Obsidian's own pricing page, read 2026-09-28, with both the yearly and monthly rates printed for each add-on. Nothing on this page is inferred from a third-party comparison.
Does it work without an API key?
Yes. Copy the printed prompt into any free chat model, paste the JSON back, and the blueprint renders here as the same document — folders, naming, links, templates, maintenance, todos.
Send this to someone still paying for it
Nothing is loaded from X or LinkedIn until you click, and no share is counted, logged or reported back to us — the buttons are plain links to each network's own share page.