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.
git clone --depth 1 https://github.com/rahilp/second-brain-cloudflareWrote 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/rules/rahilp/second-brain-cloudflare/second-brain-memory)<a href="https://agentmods.dev/rules/rahilp/second-brain-cloudflare/second-brain-memory"><img src="https://agentmods.dev/badge/rules/rahilp/second-brain-cloudflare/second-brain-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/rahilp/second-brain-cloudflare/second-brain-memory"><img src="https://agentmods.dev/badge/rules/rahilp/second-brain-cloudflare/second-brain-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00825 | $0.00825 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
second-brain-memory 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- MCP first — if
remember,recall,get,list_recent,list_teams,append,update,forget,link,unlink,connections,share, orset_statusare in your tool list, use them. - CLI fallback — if MCP tools are missing but
brainis configured (~/.config/second-brain/config.jsonexists), 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> "..."
- 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 teamrecall— semantic search; usehops:1–2when tracing why/how; optionalworkspaceandteamremember— new memory; optionalworkspace,team, andvolatility:durable|state|volatileappend/update— change existing entry (get ID from recall or list_recent first)link/unlink/connections— relationship graphshare— move between personal and company layer (workspace:personal|company; optionalteamid from list_teams)set_status— markcanonical,draft, ordeprecated
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.
- 4d ago First seen · 53 lines · 825 tokens per session scan A 8342d01e7639
second-brain-memory is a cursor rule published in the GitHub repository rahilp/second-brain-cloudflare (757 stars, last pushed yesterday), licensed MIT. It adds 825 tokens to every session, about $0.0041 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 2026-09-07.
Other cursor rules, from other repositories
cursor-rules
You have access to a persistent cross-session memory via the memory MCP server. Knowledge survives between sessions and is shared across agents working on the same project.
type-inference
Derive TypeScript types from Zod schemas - no hand-written interfaces for wire shapes.
cursor-memory
Shokunin memory system: persistent context across sessions.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
turborepo
Turbo query graph primitives and signed remote-cache key provisioning.
workers-cache
Workers Cache - Cache-Control, gateway exports cache off, RPC vs fetch.