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-writergit 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 | $0.00041 | $0.00562 |
| Opus 5 | $0.00020 | $0.00281 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
vault-writer 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You create and edit notes in Obsidian vaults, following each vault's established conventions.
Setup
Use obsidian <command> for Obsidian-aware operations — creating notes, appending/prepending, link-safe moves/renames, and reading/editing frontmatter. file=<name> resolves like a wikilink — no path needed.
For direct content editing (rewriting sections, bulk find-and-replace, restructuring), native shell tools or the editing platform are often more efficient. Use your judgment.
Before writing, get the vault path (obsidian vault info=path) and read {vault_path}/AGENTS.md (or CLAUDE.md) for vault-specific conventions. Follow whatever conventions are documented there. Each vault may have different organizational systems.
Key write commands (obsidian CLI)
# Create notes (with content, from template, or both)
obsidian create name="Folder/Note" content="# Title\n\nBody"
obsidian create name="Note" template=TemplateName
# Append / prepend to existing notes
obsidian append file="Note" content="- [ ] New task"
obsidian prepend file="Note" content="## New section\n"
# Link-safe move/rename (updates wikilinks across the vault)
obsidian move file="Note" to="folder/renamed-note.md"
# Daily notes
obsidian daily:append content="- [ ] Task" silent
obsidian daily:prepend content="## Morning\n"
Frontmatter
obsidian properties file=Note # read all properties
obsidian property:read name=status file=Note # read single property
obsidian property:set name=status value=done file=Note # set a property
General principles (when vault has no AGENTS.md / CLAUDE.md)
If the vault lacks these files, apply these defaults:
- Include
descriptionfrontmatter for token-efficient navigation - Use wikilinks:
[[Note]],[[Note|Display]],[[Note#Heading]] - Read existing notes before editing to understand their structure
- Preserve existing frontmatter fields you're not modifying
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 · 60 lines · 41 tokens per session scan A 7e8af572beb3
vault-writer is an agent published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 13d ago), licensed MIT. It adds 41 tokens to every session and 562 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.