agentleFS
rohithzrrohithzr/claudebase/skills/sync-push/SKILL.md

sync-push

Skill26 starsChanged 8 months agoMITView on GitHub

Use when the user wants to back up, save, or push their current Claude Code config to GitHub. Trigger with /sync-push.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All syncable files from the current project and global config:

    line 26
  2. Distinctive:

    Run the documented script and check its result.

    line 39
  3. Very specific:

    If the script warns about another machine having pushed more recently, advise the user to pull first (/sync-pull) or use --force if they're …

    line 55
  4. Very specific:

    If the script warns about potential secrets, tell the user which files were flagged and suggest reviewing them before using --force.

    line 59
  5. Distinctive:

    Read the README for installation, shared layers, and supported configuration paths.

    line 78
  6. Distinctive:

    Read the privacy policy for backup storage and credential handling.

    line 79
  7. Distinctive:

    Read the changelog for changes affecting installed versions.

    line 80

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Config Sync Push

Overview

Back up the current Claude Code project configuration to a private GitHub repository. Use this skill to save agents, skills, rules, hooks, and memory before moving machines or restoring a profile. Global settings remain opt-in, and local-only configuration is excluded.

Prerequisites

Initialize Claudebase with /sync-setup first. Bash, jq, Git, and an authenticated GitHub CLI with repository access are required. Select the intended project and profile before running the script; use --dry-run to inspect the planned backup.

What gets pushed

All syncable files from the current project and global config:

  • .mcp.json, .claude/settings.json
  • .claude/agents/, .claude/commands/, .claude/skills/
  • .claude/hooks/ (scripts, config, sounds)
  • .claude/rules/, .claude/agent-memory/
  • .auto-memory/ (memory files)
  • ~/.claude/settings.json (global settings, opt-in via --include-global)

Files that are never pushed: CLAUDE.md (version-controlled with project), settings.local.json, hooks-config.local.json, conversations, sessions.

Instructions

  1. Parse the requested arguments and select the appropriate options below.
  2. Run the documented script and check its result.

Parse user arguments and run the push script:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/sync-push.sh [OPTIONS]

Options:

  • --profile NAME — Push to a specific profile (default: active profile)
  • --force — Skip multi-machine safety check and secret warnings
  • --dry-run — Show what would be pushed without actually pushing
  • --include-global — Also push ~/.claude/settings.json (global settings are opt-in)

Multi-machine warning

If the script warns about another machine having pushed more recently, advise the user to pull first (/sync-pull) or use --force if they're sure.

Secret detection

If the script warns about potential secrets, tell the user which files were flagged and suggest reviewing them before using --force.

Output

Report the target profile and whether the script pushed changes, found nothing to update, or only previewed the operation. Include any flagged file names and multi-machine warnings. Verify the script result before describing the remote backup as successful.

Error Handling

Troubleshoot authentication or repository failures before retrying. If secret detection blocks the push, identify the flagged files for review without reproducing secret values. If another machine pushed more recently, recommend pulling and reconciling changes first; use --force only when explicitly requested.

Examples

/sync-push --dry-run
/sync-push --profile work

Resources

  • Read the README for installation, shared layers, and supported configuration paths.
  • Read the privacy policy for backup storage and credential handling.
  • Read the changelog for changes affecting installed versions.

User Arguments

Interpret the following input as arguments for the documented operation:

$ARGUMENTS

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.