agentleFS
egregore-labsegregore-labs/egregore/.claude/skills/sync-repos/SKILL.md

sync-repos

Skill293 starsChanged 11 days agoMITView on GitHub

Smart sync of all Egregore repos (memory + managed repos + current repo) — fetches first, only pulls if behind. Use for /sync-repos or 'sync all repos'.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the printed revisions as {local_sha} and {remote_sha}.

    line 48
  2. Very specific:

    Use the printed count as {behind} for the output.

    line 57
  3. Very specific:

    Use the printed value as {branch}.

    line 67
  4. Very specific:

    If the rebase fails, run git rebase --abort, then git merge develop -m 'Sync with develop'.

    line 73
  5. Distinctive:

    Use absolute paths with git -C to avoid permission prompts.

    line 87
  6. Very specific:

    Use git -C /absolute/path — no cd commands

    line 102

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Smart sync of all Egregore repos. Fetches first, only pulls if behind.

When to invoke

User says: "/sync-repos", "sync all repos", "sync everything", "get every repo up to date"

Execution boundary

This is deterministic multi-repository sync. Run it inline with bounded parallel fetches; do not spend a Loom/model-routing call or delegate it to another agent.

Repos to sync

  • ../{memory_dir} — shared knowledge (derived from memory_repo in egregore.json)
  • Any repos listed in the repos array in egregore.json (as sibling directories ../{repo})
  • Current repo (egregore-core)

Read egregore.json first to get the dynamic list:

# Memory repo directory
bash bin/config-get.sh memory_dir

# Managed repos
bash bin/config-get.sh repos

Use the first command’s printed value as {memory_dir} and each line from the second as a managed {repo} name; for each value, quote it in single quotes when you use it in a command, and write any single quote inside the value as '\''. If a command prints nothing, it contributes no repo to sync.

Execution

For each repo, run these commands:

# 1. Fetch (always)
git -C /path/to/repo fetch origin --quiet

# 2. Compare local vs remote
git -C /path/to/repo rev-parse HEAD
git -C /path/to/repo rev-parse origin/main

Use the printed revisions as {local_sha} and {remote_sha}. If they differ, pull and then count commits behind:

# 3. Only pull if different
git -C /path/to/repo pull origin main --quiet
# Count commits behind
git -C /path/to/repo rev-list HEAD..origin/main --count

Use the printed count as {behind} for the output. If the revisions match, report the repo as up to date and skip the pull and count.

For the current repo (egregore-core): sync the develop branch instead of main:

# Update local develop ref without switching branches (safe for concurrent sessions)
git fetch origin develop:develop --quiet
# If on dev/* branch, rebase onto develop
git branch --show-current

Use the printed value as {branch}. If it starts with dev/, rebase onto develop:

git rebase develop --quiet

If the rebase fails, run git rebase --abort, then git merge develop -m 'Sync with develop'. Continue to the merge only if the abort succeeds:

git rebase --abort
git merge develop -m 'Sync with develop'

For any other branch, skip the rebase and merge.

Use absolute paths with git -C to avoid permission prompts.

Output format

Syncing Egregore repos...

  {memory-dir}       ↓ 3 commits → pulled
  {repo-1}           ✓ up to date
  {repo-2}           ✓ up to date
  egregore-core      ↓ 1 commit → pulled

Rules

  • Use git -C /absolute/path — no cd commands
  • Fetch ALL repos first (parallel if possible), then compare/pull
  • Show commit count when pulling
  • Skip repos that don't exist (no error)

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.