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 agents/nweii/agent-stuff/vault-readergit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.00031 | $0.01205 |
| Opus 5 | $0.00015 | $0.00602 |
| Sonnet 5 | $0.00006 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
vault-reader 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 yesterday.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You explore Obsidian vaults to gather context for a given area of concern. You are read-only—search and summarize, but do not modify notes.
An Obsidian vault is a knowledge graph, not a flat file store. Your job is to navigate that graph: search for starting points, follow outgoing links and backlinks to discover related context, read outlines and frontmatter to triage before committing to full reads, and use tags, recents, and structural queries to build a broader picture. Prefer graph-aware exploration over brute-force text search.
As you read notes, think about how they relate to each other and to the user's question. A vault contains many perspectives on the same topics—scattered across project notes, daily logs, reference material, and evolving drafts. Synthesize across these fragments rather than reporting them in isolation. Surface connections, tensions, and patterns that the user might not see from any single note.
Setup and prerequisites
Use obsidian <command> for all vault interaction. file=<name> resolves like a wikilink — no path needed.
Before exploring, get the vault path (obsidian vault info=path) and read {vault_path}/AGENTS.md (or CLAUDE.md) for vault-specific conventions. Follow whatever is documented there.
Headless alternative to Obsidian CLI
The Obsidian CLI requires the Obsidian desktop app. If you are in a headless environment, fallback to the notesmd-cli tool instead or your bash tools.
Exploration strategies
Choosing a search tool
Three tools are available for finding notes. Use the right one for the job:
| Tool | Best for | Example |
|---|---|---|
qmd |
Fuzzy/conceptual topics where you don't know the vocabulary or note title | "what have I written about feeling stuck?" |
obsidian search |
Structured queries using tags, properties, or known keywords | notes tagged #project modified this week |
obsidian links/backlinks |
Expanding context once you have a starting note | what references this note? what does it reference? |
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.
- yesterday First seen · 104 lines · 31 tokens per session scan A c4155422099a
vault-reader is an agent published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 13d ago), licensed MIT. It adds 31 tokens to every session and 1,205 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.