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 aliasunder/agent-skills --skill obsidian-vaultgit clone --depth 1 https://github.com/aliasunder/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/aliasunder/agent-skills/obsidian-vault)<a href="https://agentmods.dev/skills/aliasunder/agent-skills/obsidian-vault"><img src="https://agentmods.dev/badge/skills/aliasunder/agent-skills/obsidian-vault.svg" alt="Measured on agentmods" 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 | $0.00252 | $0.07751 |
| Opus 5 | $0.00126 | $0.03875 |
| Sonnet 5 | $0.00050 | $0.01550 |
| Haiku 4.5 | $0.00025 | $0.00775 |
Grade A, and why
obsidian-vault 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 2d 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 — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Vault Skill
You are working inside an Obsidian vault. Your job is to create and edit notes that render correctly, stay plugin-compatible, and follow the vault's established conventions consistently across sessions.
How This Skill Works
This skill contains the core conventions and safe editing rules needed for
every note interaction. For detailed syntax and plugin-specific rules, it
points to reference files in references/ that you load when needed — not
upfront.
Reference files (read on demand — always read BEFORE acting, not after):
Obsidian core syntax
references/syntax.md— Full Obsidian Flavored Markdown syntax: block references, embeds, Mermaid diagrams, inline comments, footnotes, LaTeX math, advanced link patterns. Read before working with any of these constructs.references/properties.md— Full YAML property type reference: reserved keys, type rules, edge cases, common schemas. Read before creating or repairing frontmatter, or when designing a property schema.
Core plugins
references/core-plugins.md— Core Obsidian plugin conventions: Properties (type inference), Daily Notes, Templates, Graph, Backlinks, Slides, Sync. Read before working with any core plugin feature — especially property type consistency or Daily Notes templates.references/bases.md— Bases database views:.basefile YAML format, filter functions (and their gotchas), formulas, property type requirements, Bases vs Dataview comparison. Read before creating or editing.basefiles or writing notes that feed into a Bases view.references/canvas.md— Canvas JSON format: node types, sizing/spacing rules, edge labels, group containment, Enhanced Canvas plugin. Read before creating or editing.canvasfiles.
Community plugins
references/dataview.md— Dataview queries, inline fields, DataviewJS, implicit fields, cross-plugin interactions. Read before writing any Dataview query or inline field.references/tasks.md— Tasks plugin emoji format, custom statuses, dates, priority, recurrence, dependencies, query blocks. Read before writing or editing tasks with emoji metadata.references/kanban.md— Kanban board markdown structure, card syntax, lane management, settings block, safe editing rules. Read before editing any Kanban board file.references/meta-bind.md— Meta Bind INPUT/VIEW/BUTTON syntax, property binding, action types, JavaScript support. Read before writing Meta Bind interactive elements.references/templater.md— Templater syntax, common functions, folder templates, JavaScript in templates, core Templates vs Templater. Read before creating or editing template files.
What ships with it
12 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.
- README.md 4.9 KB
- references/bases.md 5.8 KB
- references/canvas.md 5.4 KB
- references/core-plugins.md 12 KB
- references/dataview.md 14 KB
- references/kanban.md 12 KB
- references/meta-bind.md 10 KB
- references/properties.md 5.5 KB
- references/syntax.md 7.0 KB
- references/tasks.md 13 KB
- references/templater.md 13 KB
- references/vault-tools.md 8.1 KB
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.
- 2d ago Changed aa77b8d86ea5
- 7d ago First seen · 714 lines · 252 tokens per session scan A 677347cc965c
obsidian-vault is a skill published in the GitHub repository aliasunder/agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 252 tokens to every session and 7,751 once invoked, about $0.0013 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
q-claude-setup
Use this skill when the user wants to configure Claude to know them deeply and improve itself over time. Activate when setting up projects, context files, or self-improving instructions, or when the user wants Claude to compound across sessions instead of starting from zero each time.
decision-log
Maintain a lightweight DECISIONS.md log of durable, material decisions in persistent agent workspaces. Use when a decision has actually been made and preserving its rationale would matter to future work, especially when it changes or clarifies prior requirements, structure, workflows, conventions, strategy, or other…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
dep-auditor
A read-only audit of a project’s third-party packages for known security issues, version health, and license facts. It uses the versions actually selected by lockfiles, which record the exact packages installed, rather than relying only on version ranges.