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 instructions/ddmanyes/second-brain-mcp/claude-mdgit clone --depth 1 https://github.com/ddmanyes/second-brain-mcpWrote 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/instructions/ddmanyes/second-brain-mcp/claude-md)<a href="https://agentmods.dev/instructions/ddmanyes/second-brain-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ddmanyes/second-brain-mcp/claude-md.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 | $0.01164 | $0.01164 |
| Opus 5 | $0.00582 | $0.00582 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
second-brain-mcp CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Brain MCP Server
本地 Claude Code：操作 SOP 見 AGENTS.md，vault 目錄結構與工具清單在同一文件。 遠端 MCP 連入：呼叫
get_agent_instructions()工具可取得 AGENTS.md 完整內容。 CLAUDE.md 位置：second-brain/CLAUDE.md（由 Claude Code 在此目錄啟動時自動載入）。
執行（開發）
uv run --with "mcp[cli]" --with "markitdown[all]" python -m mcp_second_brain
部署（改完碼要做的事）
⚠️ 線上服務跑的是「安裝好的 wheel」，不是這個 checkout（lcdda-start-remote.sh 明寫
"The live service imports the installed wheel"）。只改 repo + 重啟服務不會生效：
~/.venvs/second-brain/bin/pip install --force-reinstall --no-deps ~/git-repos/second-brain
launchctl kickstart -k gui/501/com.user.second-brain-remote
launchctl kickstart -k gui/501/com.user.lcdda-remote
- 三個 server（sb
:9100/ lcdda:9104/ lcdda-harvest:9106）共用同一個 venv， 一次pip install全部改到——要嘛全部重啟，要嘛新舊碼並存。 AGENTS.md也是 wheel 的一部分（pyproject.toml的force-include），所以改手冊 同樣要重新打包才會送到遠端 agent。tests/test_wheel_packaging.py會驗產物內容。- 這個落差曾讓
get_agent_instructions()靜默回傳 placeholder 數個月都沒被發現， 見 CHANGELOG「wheel never packaged AGENTS.md」。
架構（中央活腦）
- Index backend 可插拔：
store/，由SB_DB_BACKEND選postgres（中央，pgvector+pg_trgm，多機並發）或duckdb（預設/離線 fallback）。markdown 是正本，index 可由sync_all重建。 - 正式拓樸：單一中央 HTTP server（launchd
com.user.second-brain-remote，streamable-http綁 Tailscale IP:9100，SB_DB_BACKEND=postgres）+ Docker Postgres（sb-pg，僅127.0.0.1:5432）。 - 連線：client 走
http://<tailscale-ip>:9100/mcp，帶 headerX-API-Key（server 設SB_API_KEY/SB_API_KEYS時強制）。Postgres 永不對外，只 server 同機 localhost 連。 - 排程：
second-brain-pg-sync（StartCalendarInterval每逢:00、:30incremental，防脫節）、second-brain-pg-backup（每日 pg_dump）。 - 寫入紀律：所有寫入經中央 server（單一寫者）；client 端 Obsidian 唯讀，避免 Drive 衝突副本。
- 測試：Postgres 測試對
sb_test（fixture 會DELETE全表，絕不可指向sb_personal/sb_lab，test_postgres_store.py有硬 guard）。 - 詳見 MIGRATION_PLAN_POSTGRES.md 與 AGENTS.md 的 Connection Topology 段。
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.
- yesterday Changed · +18 lines · +326 tokens per session 94d22d3ded61
- 5d ago First seen · 32 lines · 838 tokens per session scan A b7f11ca3695c
second-brain-mcp CLAUDE.md is an instructions file published in the GitHub repository ddmanyes/second-brain-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 1,164 tokens to every session, about $0.0058 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 instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.