mindpalace

Files (14)

• .gitignore
• LICENSE
• README.md
• SKILL.md
• social-preview.png · assets/
• social-preview.source.html · assets/
• walkthrough.md · examples/
• system_prompt.md · openai/
• init-vault.sh · scripts/
• account.md · templates/
• infra.md · templates/
• project.md · templates/
• runbook.md · templates/
• vault-README.md · templates/

SKILL.md (first lines)

# mindpalace — resource-first knowledge vault

A layout and a set of rules that let an AI agent build a durable second brain instead of
re-learning your world every session.

The core idea: **shared resources live in dedicated files that many projects reference —
never duplicated.** One server, one file. One client account, one file. Projects are thin
pointers that link to them. A credential exists in exactly one place, so rotating it is a
one-file edit, not a grep-and-pray.

This file is the whole skill. It is host-agnostic — see `README.md` for how to load it into
Claude Code, Claude.ai, the OpenAI Agents SDK, Cursor, or any harness that can read a
markdown instruction file.

---

## Location

Resolve the vault root in this order:

1. `$MINDPALACE_VAULT`, if set
2. `~/.mindpalace/vault/` — the default, and the same path the full mindpalace tool uses
3. A `vault/` or `mindpalace/` directory in the current project

If none exists, offer to create one (see **Bootstrapping** below). Never guess a path and
never scatter files outside the resolved root.

---

## Mental model

```
infra/<resource>.md     ← one file per server, hosting plan, DNS zone, CI runner
accounts/<owner>.md     ← one file per party — a client, or yourself
projects/<slug>.md      ← THIN pointer; frontmatter links to infra + accounts
runbooks/<verb>-<x>.md  ← repeatable procedures
docs/<type>/            ← dated artifacts: PDFs, diagrams, exports, notes
README.md               ← indexes of every resource, account and project
LOG.md                  ← append-only timeline, curated regularly
```

Two rules generate most of the value:

- **A fact lives in exactly one file.** Everything else links to it.
- **Projects never hold infrastructure detail.** They hold a *relation* to it.

---

## Always-read entry points

Before answering anything from the vault, read:

- `README.md` — the indexes. Tells you what exists without globbing.
- `ME.md` — the user's own context, if present.

Projects are flat files at `projects/<slug>.md`. There is no `projects/<slug>/INDEX.md`.

---

## File catalog — where to look

| User mentions | Read this |
|---|---|
| API key, password, secret, env var | `infra/<resource>.md` **or** `accounts/<owner>.md` — never `projects/` |
| URL, port, endpoint, prod, staging | `projects/<slug>.md` → Environments table → `infra/<server>.md` |
| Cloud root account, GitHub handle, billing | `accounts/<owner>.md` |
| server, VPS, EC2, droplet, DNS, CI | `infra/<resource>.md` |
| "why did we choose X" | `projects/<slug>.md` → Decisions |
| deploy, restore, rotate, onboard | `runbooks/<verb>-<target>.md` |
| meeting notes, PDFs, diagrams | `docs/<type>/YYYY-MM-DD_<slug>.<ext>` |
| "what changed recently" | `LOG.md` |

---

## Frontmatter contract

Every file carries typed frontmatter. This is what makes the vault queryable with nothing
more than `grep`.

**`infra/<resource>.md`**
```yaml
---
type: infra
name: hetzner-vps-01        # matches the filename
provider: hetzner
owner: me                   # → accounts/me.md
status: active              # active | dead | planned
sensitive: true
---
```

**`accounts/<owner>.md`**
```yaml
---
type: account
name: acme-corp
owner: acme-corp            # "me" for your own
sensitive: true
---
```

**`projects/<slug>.md`**
```yaml
---
type: project
name: storefront
client: acme-corp           # → accounts/acme-corp.md
status: prod                # idea | dev | staging | prod | archived
hosts_on: [hetzner-vps-01]  # → infra/*.md — the relation that replaces duplication
accounts: [acme-corp]       # → accounts/*.md
stack: [django, nuxt, postgres]
---
```

**`runbooks/<verb>-<target>.md`**
```yaml
---
applies_to: [hetzner-vps-01, any-django]
risk: low                   # low | med | high

From aashutosh396/mindpalace-skill, MIT.