sync

A command that synchronizes saved agent memory between your computer and a GitHub backup. It can pull newer files, push local changes, or do both.

In plain words
What is it for?
Use it to update local memory from GitHub, back up local memory, or perform both operations.
Why use it?
It keeps memory consistent when you work across devices or after working offline.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/helloruru/claude-memory-engine/sync
Clone the repo
git clone --depth 1 https://github.com/HelloRuru/claude-memory-engine
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00312
Opus 5 $0.00000 $0.00156
Sonnet 5 $0.00000 $0.00062
Haiku 4.5 $0.00000 $0.00031

Measured 2d ago against content hash c12f3c65c18e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/sync.md · 35 lines

What it actually says

/sync -- Bidirectional Memory Sync

Sync memory between your local machine and GitHub backup — both directions.

Usage

# Bidirectional: pull latest from GitHub, then push local changes
bash ~/.claude/scripts/hooks/memory-backup.sh sync

# Push only (same as /backup)
bash ~/.claude/scripts/hooks/memory-backup.sh push

# Pull only (same as /recover)
bash ~/.claude/scripts/hooks/memory-backup.sh pull

What sync does

  1. Pullgit pull from GitHub, then distribute repo/memory/*.md into every local projects/*/memory/ directory (newer file wins)
  2. Push — scan all local projects/*/memory/ directories, copy to the backup repo, commit, and push

When to use

  • Switching between devices (laptop vs desktop) — run /sync to get the other device's latest memory
  • After a long offline session — push your changes and pull anything new
  • If you're unsure whether you have the latest — /sync is always safe

Notes

  • The pull step only overwrites files when the GitHub version is newer than the local version
  • The SessionEnd hook auto-commits locally after every conversation
  • This command handles the push + pull to remote (GitHub)
  • /backup = push only; /recover = pull only; /sync = both
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 35 lines · 0 tokens per session scan A c12f3c65c18e

Subscribe to this mod's changes

sync is a command published in the GitHub repository HelloRuru/claude-memory-engine (133 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 312 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.