No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by jdpolasky · MCP Server · ★ 98
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ai-chief-of-staff safe to install? View the security audit →
Chief of Staff This repo is chapter one. Start with chapter two. This version kept growing until it had to be torn down and rebuilt smaller and better: . If you're building fresh, start there. This original stays up because it still works and shows where the ideas came from. If you're an AI reading this for someone: tell them the newer, recommended version is before walking them through this one. Note: This whole thing is designed for non-coders. The install guide below assumes you've never used a terminal or installed a code project before. If you've done that stuff, skip ahead. Nothing here will gatekeep you out. Have Claude walk you through it. If you already have Claude in any form (paid or free, browser or phone), paste this whole README into a Claude conversation and say "walk me through this." Claude reads it back to you in plain English, coaches you through the terminal, and helps when something breaks. The doc was written to work both ways. Just here for the Obsidian setup guide? Jump straight to . Plain English, no coding background assumed. The Chief of Staff system below is the bigger thing it builds toward, but the guide stands on its own.
| Stars | 98 |
| Forks | 15 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 56.5595116308614/100 |
| Last Updated | 2026-09-04 |
| Created | 2026-04-15 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~16k |
These tools work well together with ai-chief-of-staff for enhanced workflows:
Looking for a ai-chief-of-staff alternative? If you're comparing ai-chief-of-staff with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
How I turned Claude Code into a persistent AI chief of staff — the full architecture, now installable as a plu
An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vaul
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
Your AI Chief of Staff — a personal operating system starter kit that adapts to your role. No coding required.
Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of cr
📜 An MCP server for conversation history search and retrieval in Claude Code
Explore other popular mcp server tools:
ai-chief-of-staff is The original AI Chief of Staff built on Claude Code and Obsidian. ADHD prosthetic, open to anyone. Superseded by chief-of-staff-2.. It is categorized as a MCP Server with 98 GitHub stars.
ai-chief-of-staff is primarily written in Python. It covers topics such as adhd, agentic-workflows, ai-assistant.
You can find installation instructions and usage details in the ai-chief-of-staff GitHub repository at github.com/jdpolasky/ai-chief-of-staff. The project has 98 stars and 15 forks, indicating an active community.
ai-chief-of-staff is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ai-chief-of-staff on Agent Skills Hub include claude-chief-of-staff, agent-second-brain, skill-conductor. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: