second-brain-cloudflare / rules

---
description: Always recall at session start and remember important context via Second Brain (MCP or brain CLI)
alwaysApply: true
---

# Second Brain — mandatory recall and remember

You have a personal Second Brain. Use it every session — not Cursor's built-in memory.

## How to reach it

1. **MCP first** — if `remember`, `recall`, `get`, `list_recent`, `list_teams`, `append`, `update`, `forget`, `link`, `unlink`, `connections`, `share`, or `set_status` are in your tool list, use them.
2. **CLI fallback** — if MCP tools are missing but `brain` is configured (`~/.config/second-brain/config.json` exists), run via shell:
   - `brain recall "<intent-framed query>"`
   - `brain remember "<condensed summary>" --tags work,project-name`
   - On team brains: `brain remember --workspace company --team <id> "..."` / `brain recall --workspace company --team <id> "..."`
3. **Unavailable** — if both fail, say Second Brain is unavailable and quote the error. Never skip silently or use built-in memory instead.

MCP tools may load lazily in Cursor — a connected server can omit tools from the visible list. **Verify with a real `recall` call** before treating Second Brain as down.

## Mandatory — no exceptions

**Start of every conversation:** call `recall` (or `brain recall`) with an intent-framed query — not bare keywords. Frame as: *"User wants to X about Y — what should I know?"*

**During and after work:** call `remember` (or `brain remember`) silently whenever:
- The user shares personal context, work decisions, tasks, preferences, or plans
- You recommend, decide, design, or conclude something they may need again

Store condensed summaries, not full transcripts. Tag with `cursor-response` plus a project/topic tag and one of: `personal`, `work`, `task`, `idea`, `context`. Set source to `cursor` on MCP calls.

**Before recommending or asking:** recall first to avoid repeating yourself or re-asking answered questions.

**Respect exclusions:** if the user says not to store something, skip `remember` for that content.

## Tool quick reference

- `list_teams` — list shared teams (names + ids); call before company writes when the user hasn't named a team
- `recall` — semantic search; use `hops:1–2` when tracing why/how; optional `workspace` and `team`
- `remember` — new memory; optional `workspace`, `team`, and `volatility`: `durable` | `state` | `volatile`
- `append` / `update` — change existing entry (get ID from recall or list_recent first)
- `link` / `unlink` / `connections` — relationship graph
- `share` — move between personal and company layer (`workspace`: `personal` | `company`; optional `team` id from list_teams)
- `set_status` — mark `canonical`, `draft`, or `deprecated`

## Team workspaces

- **personal** = private to author; **company** = shared with the team
- **v3.0.0:** one shared team per brain — omit `team` unless `list_teams` returns more than one
- User says "share with the team" → `workspace: company`
- `team` on remember, share, recall, list_recent when multi-team is enabled later; not on id-based tools (get, append, update, etc.)

Full guidance: copy [CURSOR_INSTRUCTIONS.md](https://github.com/rahilp/second-brain-cloudflare/blob/main/AI_Instructions/CURSOR_INSTRUCTIONS.md) into `~/.cursor/CURSOR_INSTRUCTIONS.md`, or open it from a clone of this repository.