init-agent-sync
Skill3 starsChanged 26 days agoMITView on GitHub
Initializes the AGENT_SYNC.md hub for AI agent coordination and task tracking.
In this repository4 other files it gives its agents.
- create-roadmapSkill
- project-scaffoldSkill
- team-summarySkill
- wrap-phaseSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Create an AGENT_SYNC.md file in the root of the project if one doesn't exist.
- Distinctive: line 19
Use this when starting a new project, or when you want to introduce the AI agent synchronization system to an existing repository.
- Distinctive: line 23
When invoked, execute the following steps:
- Very specific: line 24
Check for existing file: Check if AGENT_SYNC.md already exists in the project root.
- Very specific: line 25
Create the file: Use the Write tool to create AGENT_SYNC.md with the following template:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
What I do
- Create an
AGENT_SYNC.mdfile in the root of the project if one doesn't exist. - Populate it with standard AI agent instructions, context tracking, a session task board, and a handoff log.
- Set up the foundation for multi-agent workflows so AI assistants can cleanly hand off tasks to one another.
When to use me
Use this when starting a new project, or when you want to introduce the AI agent synchronization system to an existing repository.
Execution Steps
When invoked, execute the following steps:
- Check for existing file: Check if
AGENT_SYNC.mdalready exists in the project root. If it does, inform the user and ask if they want to overwrite it. - Create the file: Use the Write tool to create
AGENT_SYNC.mdwith the following template:
# 🤖 Agent Synchronization & Handoff Hub
**⚠️ INSTRUCTIONS FOR ALL AI AGENTS ⚠️**
1. **Read this file first** upon waking up or starting a new session.
2. **Check the Handoff Log** for context, recent changes, and messages directed at you.
3. **Master Trackers:** Always consult `progress.md` (or equivalent) for the *master project roadmap*. This file (`AGENT_SYNC.md`) is specifically for inter-agent communication, technical handoffs, and session-level tasks.
4. **Task Management:** When you start a task, update the Short-Term Tasks section (mark as `[~] In Progress`). When finished, mark as `[x] Completed`.
5. **Session Wrap-up:** Before ending your session or asking the user to switch agents, **append a brief summary** of what you accomplished and any blockers to the **Handoff Log**.
---
## 🎯 Current Context & Technical State
- **Active Branch:** `main`
- **Current Phase:** Initial Setup
- **Master Reference:** `progress.md`
---
## 📋 Session Task Board (Granular / Short-Term)
*Note: High-level goals live in master trackers. Use this for immediate, technical sub-tasks.*
- [ ] Define initial tasks here
---
## 💬 Handoff & Discussion Log
*Format: `**[YYYY-MM-DD] - [User/Agent Name]:** Message @Mention`*
**[Current Date] - Setup Agent:**
### Session Summary: Hub Initialization
**Objectives Accomplished:**
1. Initialized the AGENT_SYNC.md coordination hub.- Commit: Automatically run
git add AGENT_SYNC.md && git commit -m "chore: initialize AGENT_SYNC.md for AI coordination"if inside a git repository.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

