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 skills/nweii/agent-stuff/vault-recipesnpx skills add nweii/agent-stuff --skill vault-recipesgit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/vault-recipes)<a href="https://agentmods.dev/skills/nweii/agent-stuff/vault-recipes"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/vault-recipes.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 | $0.00053 | $0.02338 |
| Opus 5 | $0.00026 | $0.01169 |
| Sonnet 5 | $0.00011 | $0.00468 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
vault-recipes 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault recipes
Recipes live in this vault as one note per dish. This skill covers finding, reading, filtering, adapting, combining, and saving them, plus the cooking judgment that reworking them calls for.
Where the recipes live
A settled set of locations — don't relocate or restructure them:
03-Records/Clippings/Recipes/— the recipe notes (one.mdper recipe)98-Spaces/Recipes.md— the hub note (embeds the base; the place to browse)98-Spaces/Engines/Recipes.base— the query engine (seven views, below)99-Admin/Templates/Recipe Template.md— the skeleton for new recipes
Recipe notes carry both [[Clippings]] and [[Recipes]] categories — filed as clippings, but specific enough to live in their own subfolder.
Pick your access tier
Use the first tier available and stop there:
- Obsidian CLI (
obsidian …) — when the desktop app is running and the CLI is on PATH. Richest surface: wikilink resolution, link-safe edits, and direct.basequeries the MCP can't do. Runobsidian helpfor the full command set. Don't reach for the MCP when the CLI is available. - notesmd-cli + file tools — headless/local without the app.
- Brain MCP (
vault_*tools) — MCP-only environments like Claude.ai.
The operations below give both the CLI and the MCP form. Translate to notesmd-cli or plain file reads when that's the tier you're on.
Operations
| Intent | Obsidian CLI (local) | Brain MCP (remote) |
|---|---|---|
| List the collection | obsidian base:query file=Recipes.base view=Gallery format=json, or ls the folder |
vault_read(mode="list", path="03-Records/Clippings/Recipes") |
| Full-text search (ingredient, keyword) | obsidian search query="miso" path="03-Records/Clippings/Recipes" |
vault_search_content(query="miso", folder="03-Records/Clippings/Recipes") |
| Find by title fragment | obsidian read file="Gochujang Buttered Noodles" (resolves by title) |
vault_search_title(title="gochujang") → vault_read |
| Read a recipe | obsidian read file="…" |
vault_read(path="…") |
| Peek without full read | obsidian property:read name=description file="…" |
vault_read_section(heading="Ingredients", path="…") |
| Filter by cuisine / rating / untried | obsidian base:query file=Recipes.base view=Untried format=json |
frontmatter regex (see views below) |
| Save a new recipe | obsidian create name="Title" template="Recipe Template" |
vault_create(path="03-Records/Clippings/Recipes/Title.md", content=…) |
| Adapt an existing recipe | obsidian append/prepend, or edit the file |
vault_edit_section, or vault_update with base_version |
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 · 174 lines · 53 tokens per session scan A 7b586a06c882
vault-recipes is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 17d ago), licensed MIT. It adds 53 tokens to every session and 2,338 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…