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 agentmods add instructions/otaviof/obsidian-vfs/agents-mdgit clone --depth 1 https://github.com/otaviof/obsidian-vfsWrote 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/instructions/otaviof/obsidian-vfs/agents-md)<a href="https://agentmods.dev/instructions/otaviof/obsidian-vfs/agents-md"><img src="https://agentmods.dev/badge/instructions/otaviof/obsidian-vfs/agents-md.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 | $0.00854 | $0.00854 |
| Opus 5 | $0.00427 | $0.00427 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
obsidian-vfs AGENTS.md 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project
Virtual file-system sharing Obsidian notes with VSCode and Claude Code.
Architecture
No cross-dependencies between vscode, claude-plugin, cli. Shared logic goes in core. Entry points: CONTRIBUTING.md#architecture.
Hook handler: self-contained bundle at bundle/hook-handler.mjs (tracked in git). Details: CONTRIBUTING.md#hook-handler-bundle.
Build & Verification
Do NOT run bare pnpm ci -- that is pnpm's clean-install and wipes node_modules. Use pnpm run ci.
Always run pnpm format:check before reporting work as done. This is not covered by pnpm run ci and will catch Prettier violations. Fix with pnpm format if needed.
Toolchain, scripts, workflows: CONTRIBUTING.md#toolchain, CONTRIBUTING.md#scripts.
Conventions
Style, file layout, patterns: CONTRIBUTING.md#conventions.
Versioning (bump checklist)
- VSCode:
packages/vscode/package.json - Claude plugin:
.claude-plugin/marketplace.json,packages/claude-plugin/package.json,.claude-plugin/plugin.json(all three must match) - npm packages:
packages/core/package.json+packages/cli/package.json(must match)
VSCode: Workspace Folder Architecture
- Single
file://workspace folder at the vault root for Quick Open (Cmd+P) andCtrl+Shift+Fsearch. VSCode's file discovery and ripgrep indexer only operate onfile://workspace folders —obs://workspace folders provide zero discoverability (confirmed by spike, 2026-05-15). files.excludepatterns hide non-autoMount vault content to match the Explorer tree view's visibility. Two-tier split: dotfiles +blocked→ConfigurationTarget.WorkspaceFolder(<vault>/.vscode/settings.json); non-autoMount dirs + file extension globs →ConfigurationTarget.Workspace. Tracked incontext.workspaceState, cleaned up on change or disable. All defaults come frompackage.json(single source of truth).- Vault-side exclusion toggles —
vault.excludeDotfiles,vault.excludeDotfilePattern,vault.excludeBlocked,vault.gitIgnore. Each independently toggleable at runtime. Settings reference: README.md § Vault. - Sub-path exclusion — computed via mount tree (
packages/core/src/mount-tree.ts). Controlled byworkspace.excludeUnmountedFolders. - File-level exclusion — regex on basenames generates
{prefix}/*{ext}globs in the folder-scopedfiles.excludetier. Gated byworkspace.excludeUnmountedFilestoggle. - Vault write protection —
vault.modecontrolsobs://writes ("ro"→isReadonly: true;"partial"→ autoMount-scoped enforcement). Thefile://workspace folder bypasses the provider. Limitations: README.md § Workspace Folder. obs://FileSystemProvider — registered for tree view, wikilinks, drag-and-drop, watch events; does not back a workspace folder.FileSearchProvider/TextSearchProvider— proposed (unstable) as of@types/[email protected]. Do not use while proposed. Details: README.md § Workspace Folder.
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 First seen · 45 lines · 854 tokens per session scan A ed66a1745d88
obsidian-vfs AGENTS.md is an instructions file published in the GitHub repository otaviof/obsidian-vfs (3 stars, last pushed 26d ago), licensed Apache-2.0. It adds 854 tokens to every session, about $0.0043 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 instructions, from other repositories
obsidian-cli-skill CLAUDE.md
Instructions for cwaits6/obsidian-cli-skill, covering claude.md, project overview, repository structure, versioning and releases and working with reference files.
super-token-saver CLAUDE.md
Claude Code instructions for ww-w-ai/super-token-saver, covering claude.md, what this is, architecture, two transcript sources, one pipeline and one repo, two hosts.
pluginhub CLAUDE.md
Instructions for qxbyte/pluginhub, covering claude.md, what this repo is, multi-host adaptation, commands and non-negotiable conventions.
universal-remote-control CLAUDE.md
Claude Code instructions for sidkandan/universal-remote-control, covering urc — rc bridge + cli-to-cli communication, quick start, development rules, architecture (v3) and communication strategy.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).