# boot

Adopt this skill: https://proskills.md/skills/other/saksham10arora-dotcom-everything-claude-codex-skills-boot

Page: https://proskills.md/skills/other/saksham10arora-dotcom-everything-claude-codex-skills-boot
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: skills/boot/SKILL.md
size: 1155
sha: 3c01dbb0d980905cc073e0c47eeb0f5c3b6b61b5
upstream: https://github.com/saksham10arora-dotcom/everything-claude-codex/blob/main/skills/boot/SKILL.md

```text
---
name: boot
description: Use when the user says "/boot", "start session", "boot up", "what's the situation", or starts a session wanting a full briefing
---

# /boot: the 30-second session briefing

Read in parallel, then stop reading once you have what you need:
1. `.remember/hot.md`: deadlines, active projects, tracks, hard rules
2. `daily/<today>.md` if it exists

Only open a tracker (`*_tracker.md`) if hot.md lacks the detail. Never read big trackers by default.

## Output (exactly this, no intro)

**BOOT: <date>**

### Kill list (hard deadlines in the next 7 days)
Date | What | Status. If none: "None this week".

### Active projects
One line each: name, status, what's left.

### Tracks
One line per track from hot.md: where you are, what's next.

### Today
Daily note headline, or "No daily note. Create one?"

**What are we doing?**

## Rules
- Load the "Hard rules" section of hot.md into working memory and never break them.
- Never invent a status or deadline. If it isn't in the files, say "unknown, check <file>".
- If hot.md was last updated more than 2 days ago, say so.
- At the end of the session, remind the user to run /tldr.
```

## File: README.md
upstream: https://github.com/saksham10arora-dotcom/everything-claude-codex/blob/main/README.md

````text
<p align="center">
  <img src="assets/hero.png" alt="ECX: everything claude codex. Claude Code and Codex working as one team, with one memory." width="100%" />
</p>

<p align="center">
  <a href="https://github.com/saksham10arora-dotcom/everything-claude-codex/stargazers"><img src="https://img.shields.io/github/stars/saksham10arora-dotcom/everything-claude-codex?style=flat&color=c2a4ff" alt="Stars" /></a>
  <a href="https://github.com/saksham10arora-dotcom/everything-claude-codex/actions/workflows/test.yml"><img src="https://github.com/saksham10arora-dotcom/everything-claude-codex/actions/workflows/test.yml/badge.svg" alt="Tests" /></a>
  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT" /></a>
  <img src="https://img.shields.io/badge/Claude%20Code-supported-e8835f" alt="Claude Code" />
  <img src="https://img.shields.io/badge/Codex-supported-8f73e6" alt="Codex" />
  <img src="https://img.shields.io/badge/python-3.9%2B-3776AB?logo=python&logoColor=white" alt="Python 3.9+" />
</p>

# ECX: everything claude codex

![Tell Codex a codeword by voice, ask Claude a minute later without reading any file, and it knows](assets/demo-agent-sync.png)

<sub><b>Real, unedited.</b> A codeword told to Codex by voice. A minute later Claude knows it, without reading a single file.</sub>

**Claude Code and Codex, working as one team.** Two agents from two different labs share one memory and see each other's latest messages, so you can start a task in one and finish it in the other without explaining anything twice. Around that team: every session starts already knowing you, your notes are searchable by meaning, the setup checks its own tools before they break, and it keeps working from your phone with your laptop shut.

Not a skills pack. It runs alongside packs like Superpowers instead of replacing them.

Built and battle-tested every day for 6 months by [@nerfsaksham](https://x.com/nerfsaksham), 3x hackathon winner. It's the setup behind 37 shipped projects. Install it in 30 seconds.

```text
you talk to either agent  ->  both remember  ->  your notes answer  ->  your phone keeps going
```

| Included | Count | What it gives you |
|---|---:|---|
| Skills | **18** | `/boot`, `/daily`, `/weekly`, `/catchup`, `/opps`, `/outreach`, `/content`, `/ship`, `/video-notes`, `/wiki` and more |
| Hooks | **21** | Memory loading, tests before "done", a health check at every session start, a working danger guard, MCP health checks, AI-tell guard |
| Search engines | **3** | By meaning (ChromaDB), by relationship (LightRAG graph), by image (CLIP over your slides and screenshots) |
| Agents, one memory | **2** | Claude Code and Codex read the same memory and see each other's latest messages |
| Phone access | **1 repo** | Your private GitHub repo is the bridge. No server, no new app |
| Health checks | **16+** | `doctor` checks every part at the start of every session and tells you the exact fix |
| Tests | **27** | Hooks, installer and doctor tested against the real Claude Code payload, on macOS and Linux |

## Install in 30 seconds

```bash
git clone https://github.com/saksham10arora-dotcom/everything-claude-codex ~/ecx
cd ~/ecx && ./install.sh
```

It asks two questions (where your notes live, your first name) and wires everything in. It's safe to re-run, never overwrites your files, and backs up every settings file it touches.

Want the full stack?

```bash
./install.sh --vault ~/vault --name Ada --with-search --with-cron --with-phone
```

Then open Claude Code in your vault and type `/boot`.

## Things your setup can't do yet

| | Most setups | ECX |
|---|---|---|
| Tell Codex something by voice, then ask Claude | Claude has no idea | Claude already knows. Every message, both directions, under 0.1 s |
| Ask your notes a question from your phone, laptop shut | Not possible | Works. Captures you dictate land in your vault |
| "Find the slide with the gradient descent diagram" | Grep for words | Search images by describing them, and jump to the note they're in |
| Continue a chat from another Claude window | Start over | `/catchup` reads the other session in full |
| A tool your agent depends on silently dies | Wasted turns, empty answers | Blocked before the call, with the exact fix |
| Your nightly index stops updating | You find out months later | Your next session opens with a warning and when it last updated |
| The agent says "done" but the tests fail | You find out later | It can't stop until your tests pass. Claude Code and Codex both get sent back with the failing output |
| `rm -rf ~` | Most guards read a variable Claude Code never sets, so they block nothing | Blocked. Tested against the real hook payload |

## Without a system vs. with ECX

| Without | With ECX |
|---|---|
| Every session starts from zero | `hot.md` + memory load before your first message |
| Claude and Codex are strangers | They share memory and message each other directly |
| Your knowledge is scattered across notes, PDFs, slides | One vault, three search engines, every night re-indexed |
| You find out a tool broke when it's too late | Health checks before every call, `doctor` for everything |
| Your AI writes like an AI | The AI-tell guard flags it before you publish |
| Ideas from your phone get lost | One voice note, one file in `inbox/`, filed on your laptop automatically |

## What's inside

```text
everything-claude-codex/
|-- agent-sync/      Claude <-> Codex: each sees the other's newest messages, plus agent-to-agent mail
|-- skills/          18 skills: boot, daily, weekly, catchup, opps, outreach, email, content, brand, resume,
|                    money, project, summary, ship, tldr, wiki, wiki-health, video-notes
|-- hooks/           tests before done, guard, MCP health, session memory, inbox, archive, AI-tell guard, usage
|-- vault-search/    3 MCP servers (meaning, graph, router) + image search + nightly indexers
|-- phone-vault/     after-every-reply GitHub sync, phone capture auto-merge, cloud boot rules
|-- memory/          keeps hot.md current after every /compact
|-- watch-notes/     video -> key frames + transcript, for /video-notes
|-- statusline/      context bar + unread mail from Codex
|-- templates/       CLAUDE.md, AGENTS.md (Codex boots knowing what Claude knows), hot.md
|-- scripts/         install.py, doctor.py
`-- tests/           27 tests, macOS + Linux, Python 3.9 to 3.12
```

## How it fits together

```mermaid
flowchart LR
  you((You)) -- types --> CC[Claude Code]
  you -- talks --> CX[Codex + voice]
  CC <-- agent-sync: newest messages + mail --> CX
  CC & CX -- boot from --> M[(hot.md + memory)]
  CC & CX -- MCP --> S[Vault search: meaning, graph, images]
  M & V[(Your vault)] -- sync after every reply --> GH[(Private GitHub repo)]
  phone((Phone, laptop shut)) -- Claude app / ChatGPT app --> GH
```

## The pieces

### 1. Memory that knows you
`hot.md` holds what's true right now: deadlines, projects, hard rules. A hook loads it, plus your last sessions, before your first message. After every `/compact`, it's refreshed automatically. Codex reads the exact same files through `AGENTS.md`, so it knows what Claude knows.

### 2. agent-sync: two agents, one conversation
Before every message, a hook hands each agent the newest lines of the other's chats, Codex voice transcripts included. Local, one Python file, stdlib only. They can also mail each other directly (`sync.py send`), and you get a readable log in `agents/AGENT_CHAT.md`.

### 3. Vault search, three ways
- **By meaning:** "notes about latency" finds them even if the word never appears.
- **By relationship:** "how does my engine relate to my competition strategy" walks a knowledge graph.
- **By image:** "the slide with the architecture diagram" searches your slides, screenshots and PDF pages, and tells you which note each one lives in.

A router picks the right one. All of it re-indexes every night.

### 4. Phone vault: laptop shut, still works
After every reply, your not
````