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 lexbritvin/obsidian-skills-pack --skill obsidian-dataviewgit clone --depth 1 https://github.com/lexbritvin/obsidian-skills-packWrote 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/lexbritvin/obsidian-skills-pack/obsidian-dataview)<a href="https://agentmods.dev/skills/lexbritvin/obsidian-skills-pack/obsidian-dataview"><img src="https://agentmods.dev/badge/skills/lexbritvin/obsidian-skills-pack/obsidian-dataview/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/lexbritvin/obsidian-skills-pack/obsidian-dataview"><img src="https://agentmods.dev/badge/skills/lexbritvin/obsidian-skills-pack/obsidian-dataview.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 | $0.00297 | $0.03081 |
| Opus 5 | $0.00148 | $0.01541 |
| Sonnet 5 | $0.00059 | $0.00616 |
| Haiku 4.5 | $0.00030 | $0.00308 |
Grade A, and why
obsidian-dataview 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 5d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dataview
Reference for authoring queries and scripts against the Obsidian Dataview plugin. Dataview indexes vault metadata (frontmatter, inline fields, tasks, links) and exposes it through four codeblock surfaces.
This file is the index. For deep coverage, consult the reference files (loaded only when relevant).
What Dataview is
A read-only metadata index. It scans the vault, builds a typed in-memory database from frontmatter + inline fields + tasks + the Obsidian link graph, and renders results back into notes through codeblocks. It does not modify files (the one exception: clicking a checkbox in a rendered TASK block toggles the underlying source, but DataviewJS code itself cannot write).
The four codeblock surfaces
| Surface | Fence | Use it for |
|---|---|---|
| DQL query | ```dataview |
Static, declarative views. Safer, faster to render, no JS required. |
| DataviewJS | ```dataviewjs |
Anything DQL can't express: control flow, multi-step computation, custom DOM, awaiting dv.io/dv.query, custom views via dv.view. |
| Inline DQL | `= expr` (default prefix =) |
Single-value expression rendered inline mid-paragraph. |
| Inline JS DQL | `$= expr` (default prefix $=) |
Same idea, full dv API available. |
JS surfaces are gated by the plugin's "Enable JavaScript Queries" toggle. Treat third-party DataviewJS as untrusted code — it has full vault read access.
Decision tree — DQL vs DataviewJS
Pick DQL unless one of these is true:
- The output needs
await(dv.query,dv.io.csv,dv.io.load,dv.view). - You want loops, mutable state, conditionals over the rendered output (e.g. one header per group, then a per-group table).
- You want to render a custom DOM structure or multiple sub-views in one block.
- The transformation needs intermediate variables that DQL can't express.
- You need to import a
dv.view("Scripts/foo", input)helper.
Otherwise DQL wins on conciseness, performance, and reactivity.
What ships with it
5 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.
- 5d ago Changed · +297 tokens per session 3dff02388bc5
- 11d ago First seen · 160 lines · 0 tokens per session scan A c673a8db1463
obsidian-dataview is a skill published in the GitHub repository lexbritvin/obsidian-skills-pack (2 stars, last pushed 6d ago), licensed MIT. It adds 297 tokens to every session and 3,081 once invoked, about $0.0015 per session on Opus 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
obsidian
Obsidian vault management — create notes, backlinks, tags, and Dataview queries via file operations.
obsidian
Operational skill for Claude to automate Obsidian vaults via URI schemes, Templater/Dataview patterns, Markdown structure, and local plugin workflows.
gtd-evening
A guided evening routine for a GTD task system, where GTD means sorting work into clear next actions, waiting items, and projects. It reviews the day, records results, and tidies unfinished work.
gtd-alignment
A monthly goal-checking and coaching routine based on the user's stated strategy, values, and personal patterns. It compares time spent and actions taken with the goals the user says matter most.
gtd-inbox
A guided process for emptying a GTD inbox, where an inbox is a temporary holding place for uncategorized tasks and ideas. It examines each item and helps decide whether it belongs in actions, projects, waiting items, someday items, areas, or reference notes.
gtd-review
A guided weekly review for a GTD system, where GTD is a method for keeping tasks, projects, waiting items, and reference material organized. It prepares a review note from recent work, journal entries, and, when available, calendar events.