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/thoreinstein/obsidian-rag/claude-mdgit clone --depth 1 https://github.com/thoreinstein/obsidian-ragWrote 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/thoreinstein/obsidian-rag/claude-md)<a href="https://agentmods.dev/instructions/thoreinstein/obsidian-rag/claude-md"><img src="https://agentmods.dev/badge/instructions/thoreinstein/obsidian-rag/claude-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 | $0.00677 | $0.00677 |
| Opus 5 | $0.00338 | $0.00338 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
obsidian-rag CLAUDE.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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
obsidian-rag
Claude Code plugin providing Obsidian vault integration with local RAG (Retrieval Augmented Generation).
Architecture
- MCP Server (
src/index.ts): Exposes 16 tools via the Model Context Protocol over stdio. Also supports one-shot CLI mode for hook scripts. - Embedder (
src/rag/embedder.ts): Local embedding via@xenova/transformers(all-MiniLM-L6-v2). Singleton pattern. - Vector Store (
src/rag/store.ts): LanceDB-backed vector store with incremental indexing and md5-based change detection.
Build
npm install
npm run build
The build uses esbuild to bundle into dist/index.js (committed to the repo). Native dependencies (@lancedb/lancedb, onnxruntime-node, sharp) are externalized.
Key Constraints
- onnxruntime-node pinned to 1.14.0: Required by
@xenova/transformers 2.17.x. Do not upgrade. - Native deps externalized: The esbuild bundle excludes
@lancedb/lancedb,onnxruntime-node, andsharp— they load fromnode_modulesat runtime. - sharp is required: Transitive runtime dependency of
@xenova/transformers(imported at top-level inutils/image.js). Must stay independenciessince esbuild externalizes it. - Dependency placement is intentional: Bundled deps (MCP SDK, transformers, glob, gray-matter, md5) are in
devDependenciesbecause esbuild bakes them intodist/index.js. Externalized native deps are independenciesbecause they load fromnode_modulesat runtime. - dist/ is committed: The built artifact is checked in so the plugin works without a build step after clone +
npm install.
Data Paths
When running as an installed plugin, all state is stored in ${CLAUDE_PLUGIN_DATA}/ (persistent across plugin updates). Falls back to ~/ for development/CLI usage.
- Config:
.obsidian-rag.config.json - LanceDB:
.obsidian-rag-lancedb/ - File hashes:
.obsidian-rag-file-hashes.json
Environment Variables
OBSIDIAN_VAULT_PATH: Default vault path (overrides config file)OBSIDIAN_RAG_MIN_CHUNK_CHARS: Minimum chunk size (default 40)OBSIDIAN_RAG_MAX_CHUNK_CHARS: Maximum chunk size (default 1800)OBSIDIAN_RAG_TARGET_CHUNK_CHARS: Target chunk size for merging (default 700)OBSIDIAN_RAG_EMBED_BATCH_SIZE: Embedding batch size (default 48)
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.
- 4d ago First seen · 52 lines · 677 tokens per session scan A dbd382929f91
obsidian-rag CLAUDE.md is an instructions file published in the GitHub repository thoreinstein/obsidian-rag (2 stars, last pushed 1mo ago), licensed MIT. It adds 677 tokens to every session, about $0.0034 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
claude-sessions CLAUDE.md
Instructions for gapmiss/claude-sessions, covering claude sessions — obsidian plugin, development, file structure, code exploration (cymbal) and conventions.
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
obsidian-vfs AGENTS.md
Instructions for otaviof/obsidian-vfs, covering agents.md, project, architecture, build & verification and conventions.
pluginhub CLAUDE.md
Instructions for qxbyte/pluginhub, covering claude.md, what this repo is, multi-host adaptation, commands and non-negotiable conventions.
qa-orchestra CLAUDE.md
Claude Code instructions for Anasss/qa-orchestra, covering qa orchestra — claude code instructions, what this project is, quick start, 1. clone into your workspace and 2. fill in your project context.
claude-sdlc CLAUDE.md
Claude Code instructions for lantisprime/claude-sdlc, covering claude.md, what this repo is, design intent — read this before "improving" anything, eat your own dog food and hook strictness philosophy.