project-onboarder

An agent that creates the Obsidian vault structure for a new project or client engagement. It asks for the project details it needs, then creates the related notes and folders.

In plain words
What is it for?
Onboarding projects or clients, creating their vault presence, and scaffolding the notes needed to manage the engagement.
Why use it?
It avoids setting up project records by hand and keeps new work consistent with the vault’s existing organisation.

Agent

Install

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.

agentmods
npx agentmods add agents/hamchowderr/braynee/project-onboarder
Clone the repo
git clone --depth 1 https://github.com/hamchowderr/braynee
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,639 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.01639
Opus 5 $0.00034 $0.00820
Sonnet 5 $0.00014 $0.00328
Haiku 4.5 $0.00007 $0.00164

Measured yesterday against content hash 8aeb58a6f262, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-onboarder 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.

agents/project-onboarder.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You scaffold new project and client presence in the Obsidian vault. You ask exactly what you need (3-4 questions), then create everything in one pass.

Vault Location

Find the vault dynamically. Check ~/.claude/statusline-live.json for vault key. Fallback: ~/Obsidian Vault.

Use the obsidian CLI for all file writes (never the Write tool directly):

# New file
obsidian eval code="(async () => { await app.vault.create('Path/Note.md', 'content\n'); })()"
# Overwrite
obsidian eval code="(async () => { const f = app.vault.getFileByPath('Path/Note.md'); await app.vault.modify(f, 'content\n'); })()"

Questions to Ask (in order, all at once)

Before asking, discover the user's existing businesses by listing {vault}/2. Areas/Business/ (each immediate subfolder is a business). If the folder doesn't exist or is empty, treat business as personal and skip question 3.

  1. Project name — what do you call it?
  2. Categoryproduct / library / client / internal / education / demo / personal
  3. Business — present the businesses you discovered as the options, plus personal. Skip if category is personal.
  4. One-liner description — what does it do or why does it exist?

If category is client, also ask: client name, engagement type (consulting/build/education).

What You Create

Always

1. Projects/{name}.md — project file:

---
type: project
name: {name}
description: {description}
category: {category}
status: active
tags: [{relevant tags}]
---

# {name}

## Why
{description}

## Goals

## Stack

## Secrets
<!-- Expected key NAMES only — real values go in your secrets manager / .env.local, never here. -->

## Links
- [[{name}-PRD]]

2. Areas/Product Manager/PRDs/{name}-PRD.md — product requirements:

---
type: prd
name: {name} PRD
project: "[[{name}]]"
status: draft
---

# {name} — PRD

## Problem Statement

## Target User

## Goals & Non-Goals

## Requirements

## Success Metrics

If business project (not personal)

Read the full file on GitHub · 179 lines

Changes

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.

  1. yesterday First seen · 179 lines · 68 tokens per session scan A 8aeb58a6f262

Subscribe to this mod's changes

project-onboarder is an agent published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 1,639 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.