agentleFS
SebastianWiercinskiSebastianWiercinski/vibe-session-sync/skills/sync-start/SKILL.md

sync-start

Skill0 starsChanged 7 months agoMITView on GitHub

Show changes from other parallel sessions since this session last checked in, triggered ONLY by the explicit `/sync-start` slash command. Never auto-trigger on natural-language phrases like "sync check", "catch up on other sessions", "was haben die anderen gemacht", or similar — this skill should remain user-initiated. Reads `.sync/_shared.md` and all other per-session status files, highlights items tagged at the current session.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    If remembered from earlier /sync-init in this conversation → use that

    line 13
  2. Very specific:

    If .sync/ doesn't exist → tell user to run /sync-init <name> first and exit.

    line 15
  3. Very specific:

    Read file's mtime (stat -f %m .sync/_shared.md on macOS.

    line 20
  4. Very specific:

    If mtime > last_seen_shared → read file, show "Shared Context updates since last check" section

    line 21
  5. Very specific:

    If mtime > last_seen_sessions[<name>] (or never seen) → flag as "new/updated"

    line 25
  6. Distinctive:

    If no other sessions exist, say: "Du bist die einzige registrierte Session.

    line 56

≈ “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

Sync Start

Show what has changed in other sessions and in _shared.md since this session last checked in.

Steps

  1. Determine current session name:
    • If remembered from earlier /sync-init in this conversation → use that
    • Else: read .sync/_active.json, list all session names, ask user which one is "this session"
    • If .sync/ doesn't exist → tell user to run /sync-init <name> first and exit.
  2. Read _active.json — get current session's last_seen_shared and last_seen_sessions map.
  3. Check _shared.md:
    • Read file's mtime (stat -f %m .sync/_shared.md on macOS; stat -c %Y on Linux)
    • If mtime > last_seen_shared → read file, show "Shared Context updates since last check" section
  4. Check other session files: For each .sync/*.md file (except _shared.md and <current-session>.md):
    • Get mtime
    • If mtime > last_seen_sessions[<name>] (or never seen) → flag as "new/updated"
    • Read file, summarize:
      • Last-active timestamp
      • Scope (1 line)
      • Any Open questions tagged @<current-session> → highlight these prominently
      • Top 3 entries under "Next steps" / "Touched files"
  5. Update _active.json: set sessions.<current>.last_seen_shared = now, and sessions.<current>.last_seen_sessions[<other>] = now for each one shown.

Output format

📋 Sync check für Session: <current-name>

═══ Shared Context (updated X min ago) ═══
<relevant diff, or "nichts Neues">

═══ Andere Sessions ═══
▸ checkout-redesign (last active 2h ago)
  Scope: Neues Checkout-Flow mit Stripe
  ⚠️  @<current-name>: Brauchst du User-Session im Cookie oder Header?
  Next: Payment-Intent endpoint finalisieren

▸ auth-feature (last active 10min ago, updated since last check)
  ...

═══ Für dich direkt ═══
- checkout-redesign fragt: <question>
- (none)

If no other sessions exist, say: "Du bist die einzige registrierte Session. Leg los."

Remember after this command: user has seen all updates.

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.