zero

zero is a skill for Claude Code, Codex from miru-zero/zero-brain. It costs 131 tokens per session (2,165 once invoked), scanned A, original, MIT.

A command and skill system for managing Zero, a personal knowledge and memory system. It covers starting the system, checking its health, syncing it, installing it, and troubleshooting it.

In plain words
What is it for?
It helps boot Zero, run health checks, repair or install parts of it, and diagnose problems with its memory vault and tools.
Why use it?
It provides a defined way to check whether Zero is connected and working before changing or using its stored knowledge.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md; mentions Codex.

Good fit It helps boot Zero, run health checks, repair or install parts of it, and diagnose problems with its memory vault and tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/miru-zero/zero-brain/zero
Install

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.

Any agent
npx skills add miru-zero/zero-brain --skill zero
Clone the repo
git clone --depth 1 https://github.com/miru-zero/zero-brain

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for zero

README.md
[![agentmods](https://agentmods.dev/badge/skills/miru-zero/zero-brain/zero/github.svg)](https://agentmods.dev/skills/miru-zero/zero-brain/zero)
Your own site
<a href="https://agentmods.dev/skills/miru-zero/zero-brain/zero"><img src="https://agentmods.dev/badge/skills/miru-zero/zero-brain/zero/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.

agentmods 80×15 button for zero

Your own site · 80×15
<a href="https://agentmods.dev/skills/miru-zero/zero-brain/zero"><img src="https://agentmods.dev/badge/skills/miru-zero/zero-brain/zero.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,165 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00131 $0.02165
Opus 5.5 $0.00052 $0.00866
Sonnet 5.5 $0.00026 $0.00433
Haiku 4.5 $0.00013 $0.00216

Measured 1mo ago against content hash 2442564a19ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zero 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 1mo 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.

skills/zero/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⭕ ZERO — Boot / Health / Install ของระบบ Zero

Overview

คำสั่งเดียวสำหรับ "ตื่น + เช็ค + ซ่อม" ระบบ Zero ของป๊า ทุกอย่างอยู่ใต้โซน ~/.zero/ (Windows: C:\Users\<user>\.zero\) — ห้ามกระจายไปที่อื่น

แผนที่โซน (จำให้ขึ้นใจ)

Path คืออะไร ห้าม
~/.zero/brain/ สมอง (Obsidian vault, 616+ โน้ต, orphan ต้อง = 0) ห้ามแก้ไฟล์ตรงๆ นอก MCP ถ้าไม่ rehash manifest
~/.zero/mcp/zero-brain/ repo miru-zero/zero-brain + MCP server (tools zero_*) ห้าม commit ถ้า smoke ไม่ผ่าน 121/121
~/.zero/share/ ส่วนทำงาน daimon (sessions, skills, runtime) — ไม่ใช่สมอง ห้ามนับเป็นความจำ

Boot Check (รันเมื่อถูกเรียก)

Skills index lifecycle: index สร้างตอน session เริ่ม (และ rebuild ตอน compact) — skill ที่ลงกลาง session จะ ไม่เข้า index ทันที · ถ้าป๊าพิมพ์ /zero แล้วไม่ทริกเกอร์ ให้เช็คว่า session นี้เก่ากว่าตอนติดตั้งไหม → ทางแก้: เปิด session ใหม่ (หรือรอ compact)

  1. เช็ค MCP ด้วยการเรียกจริงเท่านั้น ห้ามเดา — โมเดล list tools ตัวเองไม่ได้ ความรู้สึกว่า "ไม่เห็น tools zero_*" ไม่ใช่หลักฐาน · ให้เรียก zero_health เลย:
    • ตอบ ok:true → MCP ผูกอยู่แล้ว ทำข้อ 2 ต่อทันที — ห้ามพูดว่า "ยังไม่ได้ผูก" และห้ามสั่ง setup/restart ใหม่เด็ดขาด (CLI ผูก auto ทุก boot ผ่าน ~/.miru_zero/mcp.json และ turn จะรอ MCP connect ก่อนคุยอยู่แล้ว)
    • error ชัดเจนว่า tool ไม่มีในระบบ (unknown tool) → ค่อยรัน node ~/.zero/mcp/zero-brain/tools/setup-agents.mjs แล้วบอกป๊า restart client
    • client ไม่มี MCP runtime → ใช้ zero mcp zero_health '{}' ผ่าน CLI แทน (ดูหัวข้อ Client ที่ไม่มี MCP runtime ด้านล่าง) · ห้าม sync/แก้ brain ด้วย file tools แทนเด็ดขาด
  2. ~/.zero/brain/ มี AGENTS.md + manifest.jsonl → อ่าน AGENTS.md ก่อนเสมอ (สัญญามนุษย์-agent)
  3. MCP zero_health ตอบ → notes ครบ / orphans = 0 / dead links = 0 → รายงานตัวเลขให้ป๊า
  4. Obsidian vault = ~/.zero ทั้งโซน โดย non-brain ถูกซ่อนอัตโนมัติ — install รัน tools/setup-obsidian.mjs ซ่อน mcp/share/… 2 ชั้น (userIgnoreFilters ใน graph/search + CSS snippet ใน explorer) ให้เหลือ brain/ ก้อนเดียว · ถ้าเห็น daimon-share/mcp โผล่ใน vault explorer แปลว่าเครื่องนั้นยังไม่ได้รัน → รัน node ~/.zero/mcp/zero-brain/tools/setup-obsidian.mjs แล้ว reload Obsidian (Ctrl+R)
  5. ผิดปกติข้อไหน → รายงาน + เสนอซ่อม ห้ามซ่อมเองถ้าเป็นงานลบ/ย้าย (กฎข้อ 1 ห้องป๊า)

Read the full file on GitHub · 85 lines

Changes

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.

  1. 1mo ago First seen · 85 lines · 131 tokens per session scan A 2442564a19ab

Subscribe to this mod's changes

zero is a skill published in the GitHub repository miru-zero/zero-brain (0 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 2,165 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.

Related

Other skills, from other repositories

Migrate

Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…

danielmiessler/LifeOS · 104 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 tokens

Profile

View, edit, or clear the LifeOS User Model (PRINCIPALIDENTITY.md) — persistent identity context loaded at session startup. Three intents: View, Edit (identity, goals, constraints, preferences), Clear (reset). Read by Algorithm OBSERVE and skills for personalization. USE WHEN profile, show profile, view profile, who am…

danielmiessler/LifeOS · 108 tokens

wiki-dashboard

Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.

Ar9av/obsidian-wiki · 42 tokens

relevance-coarse-filter

Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.

elvisun/newsjack · 57 tokens

session-compact

AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.

codeaholicguy/ai-devkit · 39 tokens