Sponsor Suno AI Music arrow_forward
Slash Command

Sync Agent Context

Merge all AGENTS.md files into CLAUDE.md for unified agent context

Type
Slash Command
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026

What Sync Agent Context is

Sync Agent Context is a slash command published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Sync Agent Context gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Sync Agent Context

Claude Code

  1. Download sync-agent-context.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/productivity/agent-context-manager/commands/sync-agent-context.md, shared under the repository's MIT license. Read the full file on GitHub.

Command: /sync-agent-context

Purpose: Permanently merge all AGENTS.md files in the project into CLAUDE.md under a dedicated section, ensuring agent-specific instructions are always loaded alongside project context.

What This Command Does

  1. Finds all AGENTS.md files in the current project directory (searches recursively)
  2. Reads each AGENTS.md file and extracts its content
  3. Updates CLAUDE.md by adding or updating the "## Agent-Specific Instructions" section
  4. Maintains both files: Keeps original AGENTS.md files as the source of truth
  5. Creates backup: Saves a backup of CLAUDE.md before making changes

Execution Steps

Step 1: Find All AGENTS.md Files

Search the current project for all files named AGENTS.md:

find . -name "AGENTS.md" -type f

Expected output:

./AGENTS.md
./subproject/AGENTS.md

Step 2: Read Each AGENTS.md File

For each found file, read its full content using the Read tool:

File: ./AGENTS.md
Content: [full content of AGENTS.md]

File: ./subproject/AGENTS.md
Content: [full content of subproject AGENTS.md]

Step 3: Check if CLAUDE.md Exists

if [ -f "./CLAUDE.md" ]; then
    echo "CLAUDE.md found - will update"
else
    echo "CLAUDE.md not found - will create new file"
fi

Step 4: Create Backup of CLAUDE.md

cp CLAUDE.md CLAUDE.md.backup.$(date +%Y%m%d-%H%M%S)

Example: CLAUDE.md.backup.20251023-143022

Step 5: Merge AGENTS.md into CLAUDE.md

Add or update the following section in CLAUDE.md:

---

## Agent-Specific Instructions

<!-- AUTO-SYNCED from AGENTS.md files - Last updated: 2025-10-23 14:30:22 -->
<!-- Source files: ./AGENTS.md, ./subproject/AGENTS.md -->

### Root Directory Agent Rules (./AGENTS.md)

[Content from ./AGENTS.md]

### Subproject Agent Rules (./subproject/AGENTS.md)

[Content from ./subproject/AGENTS.md]

---

Step 6: Verify and Report

✅ Agent Context Sync Complete!

📋 Summary:
- Found 2 AGENTS.md files
- Created backup: CLAUDE.md.backup.20251023-143022
- Updated CLAUDE.md with agent-specific instructions

📂 Synced files:
1. ./AGENTS.md → CLAUDE.md (Section: Root Directory Agent Rules)
2. ./subproject/AGENTS.md → CLAUDE.md (Section: Subproject Agent Rules)

⚠️ Note: Original AGENTS.md files remain unchanged (source of truth)

💡 Next time you start Claude Code, both CLAUDE.md and AGENTS.md will be loaded automatically.

When to Use This Command

Use /sync-agent-context when:

  1. Initial setup: First time using agent-specific instructions
  2. AGENTS.md not auto-loading: If the proactive skill isn't triggering
  3. Permanent merge desired: Want agent rules always in CLAUDE.md
  4. Multiple AGENTS.md files: Have agent rules across different directories
  5. Manual control preferred: Want explicit control over when rules are merged

Don't use this command if:

  • Automatic loading is working fine (skill handles it)
  • You want AGENTS.md and CLAUDE.md to remain separate
  • You frequently update AGENTS.md (would require re-running sync)

Merge Strategy

If "Agent-Specific Instructions" section exists in CLAUDE.md:

Replace the existing section with updated content from all AGENTS.md files.

## Agent-Specific Instructions
<!-- OLD CONTENT - WILL BE REPLACED -->

↓↓↓ BECOMES ↓↓↓

## Agent-Specific Instructions
<!-- NEW CONTENT FROM AGENTS.MD FILES -->

If "Agent-Specific Instructions" section doesn't exist:

Append new section to the end of CLAUDE.md.

[Existing CLAUDE.md content]

---

## Agent-Specific Instructions
<!-- NEW SECTION ADDED -->
[Content from AGENTS.md files]

Conflict Resolution

If both CLAUDE.md and AGENTS.md have conflicting rules:

The sync command will:

  1. Keep original CLAUDE.md content intact
  2. Add AGENTS.md content in dedicated section
  3. Document in the header: "In case of conflicts, Agent-Specific Instructions take precedence"

Example merged output:

# CLAUDE.md

## General Project Instructions
- Use TypeScript for all code (from original CLAUDE.md)

---

## Agent-Specific Instructions
<!-- In case of conflicts, these rules take precedence for agent workflows -->

- Use JavaScript for agent-generated code (from AGENTS.md)

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Sync Agent Context?

Sync Agent Context is a slash command for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Merge all AGENTS.md files into CLAUDE.md for unified agent context

How do I install Sync Agent Context in Claude Code?

Download sync-agent-context.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Sync Agent Context in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Sync Agent Context safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.