Skip to content
Back to skills

Agent Config Sync

ASecurity

Provider-neutral planner for synchronizing MCP configuration, skills and rule files across agent providers and app classes. It discovers evidenced local options and lets the user choose truth, targets, direction and conflicts.

  • 6 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 4, 2026
ai-agentspythongobash

Works with

  • mcp

Security analysis

A100/100

Pro scans all 19 files and shows the line behind each finding

Scanned September 4, 2026

npx -y skills add ellmos-ai/skills --skill agent-config-sync --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Config Sync?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agent Config Sync
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ellmos-ai-agent-config-sync/badge)](https://www.skillsdirectory.com/skills/ellmos-ai-agent-config-sync)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agent-config-sync
version: 0.3.0
type: protocol
author: Lukas Geiger + Claude + Codex
created: 2026-06-20
updated: 2026-07-27
description: Provider-neutral planner for synchronizing MCP configuration, skills and rule files across agent providers and app classes. It discovers evidenced local options and lets the user choose truth, targets, direction and conflicts.

standalone: true
anthropic_compatible: true
bach_compatible: true
bach_origin: false
category: infrastructure
tags: [mcp, skills, rules, sync, provider-neutral, discovery, multi-agent]
language: de
status: active
visibility: public
aliases: [mcp-skill-sync, multi-agent-sync, tool-config-sync, agent-sync]
dependencies: {'tools': ['python'], 'services': [], 'protocols': [], 'python': []}
provenance: {'origin': 'custom', 'origin_path': 'skills/infrastructure/agent-config-sync/', 'origin_version': '0.3.0', 'last_sync_from_origin': None, 'last_sync_to_origin': None, 'local_changes_since_sync': False}
---

<img src="banner.png" width="100%" alt="agent-config-sync banner">

> **Deutsch** — Offizielle Deutsch-Version / Documento Oficial en Deutsch.


# Agent Config Sync (Deutsch)

The skill separates endpoint selection, resources and truth. Run:

```bash
python scripts/sync.py --discover
python scripts/sync.py --offer
```

The user can select an explicit endpoint list, one provider across app classes,
one app class across providers, or all detected endpoints. Detection is
evidence, not authorization.

Truth can be one endpoint, one file, an ordered set of files such as multiple
`AGENTS.md` layers, or a skills directory. No filename or provider is the
implicit hub. Without a selected truth source, plans stay blocked.

Review `--status` and `--plan`; only use `--apply --yes` after approval.
MCP blocks and skill directories are implemented. Rule-file topologies remain
fail-closed until the user selects a merge/redirect adapter.

Files in this skill

  • CACHE.md1.6 KB
  • CONFIG.md4 KB
  • REGISTRY.md1.2 KB
  • SCAFFOLD-REPORT.md2.7 KB
  • SKILL.en.md1.8 KB
  • SKILL.es.md2.3 KB
  • SKILL.fr.md2 KB
  • SKILL.ja.md2.6 KB
  • SKILL.md1.9 KB
  • SKILL.ru.md3.1 KB
  • SKILL.zh.md2 KB
  • cache.example-LOCAL-HOST.json912 B
  • cache.example.json912 B
  • config-LOCAL-HOST.json5.1 KB
  • config.json5.1 KB
  • references/legacy-mcp-config-sync.md1.8 KB
  • registry.example-LOCAL-HOST.json1.7 KB
  • registry.example.json1.7 KB
  • scripts/sync-LOCAL-HOST.py33.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…