agentrigs
+ submit rig
~ / rigs / Vifert / second-brain-template

Vifert/second-brain-template

A token-efficient second brain: an Obsidian vault run by any coding agent, where answers cost 30–50× less than loading your notes and nothing is summarised away.

↗ GitHub ★ 6 MIT updated 11d ago project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~6.7k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Vifert/second-brain-template/.claude ./rig-second-brain-template  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit Vifert/second-brain-template/.agents/skills/vault-audit .claude/skills/vault-audit
$ npx degit Vifert/second-brain-template/.agents/skills/vault-compile .claude/skills/vault-compile
$ npx degit Vifert/second-brain-template/.agents/skills/vault-deep-audit .claude/skills/vault-deep-audit
$ npx degit Vifert/second-brain-template/.agents/skills/vault-excalidraw .claude/skills/vault-excalidraw
$ npx degit Vifert/second-brain-template/.agents/skills/vault-handoff .claude/skills/vault-handoff
$ npx degit Vifert/second-brain-template/.agents/skills/vault-tailor .claude/skills/vault-tailor
$ curl -fsSL --create-dirs -o .claude/agents/vault-fidelity-verifier.md https://raw.githubusercontent.com/Vifert/second-brain-template/main/.claude/agents/vault-fidelity-verifier.md
$ curl -fsSL --create-dirs -o .claude/agents/vault-gap-auditor.md https://raw.githubusercontent.com/Vifert/second-brain-template/main/.claude/agents/vault-gap-auditor.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "node"
          }
        ]
      }
    ]
  }
}

Skills (6)

vault-auditvault-compilevault-deep-auditvault-excalidrawvault-handoffvault-tailor

Subagents (2)

vault-fidelity-verifier
model: sonnet
Independent fidelity check for a /vault-compile — compares compiled wiki nodes against their raw source and reports every wrong, overstated, unsupported or missing claim. Read-only.
vault-gap-auditor
model: sonnet
Asks questions in the vault owner's own words and tries to answer each from the vault's index alone, reporting every miss. Used by /vault-deep-audit. Read-only.

Hooks (3)

eventmatcherruns
Stop*node
PostToolUseWrite|Edit|MultiEditnode
PreToolUseBashnode

Similar rigs

tarangdeep-goel-by/claude-harness
Dev-focused Claude Code harness — workflow-engine skills, in-repo memory, session continuity (/recall ↔ /vault-push), local telemetry, + a ready-to-fill vault scaffold. clone + ./install.sh and go.
★ 0 setup Claude CodeCodex 22 skills 1 agents 2mo ago
Skill Collector 8.0k tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 155k project CodexCursorCopilot 6 skills 4d ago
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
★ 141k project Claude CodeCodex 1 mcp 3 skills 9d ago
Pragmatist 4.2k tok ·
copied ✓