device-sync

device-sync is a skill for Claude Code, Codex from hmennen90/claude-device-sync. It costs 33 tokens per session (352 once invoked), scanned A, original, MIT.

A tool for syncing Claude Code sessions and memory files between devices through a sync repository. A repository is shared storage that keeps project or session data available across machines.

In plain words
What is it for?
Use it to push or pull sessions and memory, list synced sessions by user or project, and check synchronization status. It can also install hooks and purge old sessions with a preview option.
Why use it?
It prevents session context and memory from being stranded on one device. It also supports automatic synchronization when hooks are installed and lets users preview or remove old sessions.

Skill for Claude CodeCodex

Part of the claude-device-sync plugin — 5 skills, 4 hooks shipped together

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 skills/hmennen90/claude-device-sync/sync
Any agent
npx skills add hmennen90/claude-device-sync --skill sync
Clone the repo
git clone --depth 1 https://github.com/hmennen90/claude-device-sync

Made for: Claude Code, Codex.

Or install claude-device-sync, the plugin that ships this one along with the rest of its 5 skills, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for device-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmennen90/claude-device-sync/sync.svg)](https://agentmods.dev/skills/hmennen90/claude-device-sync/sync)
Your own site
<a href="https://agentmods.dev/skills/hmennen90/claude-device-sync/sync"><img src="https://agentmods.dev/badge/skills/hmennen90/claude-device-sync/sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 352 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 $0.00033 $0.00352
Opus 5 $0.00016 $0.00176
Sonnet 5 $0.00007 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 3d ago against content hash 501dfc60bcf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

device-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 3d 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.

skills/sync/SKILL.md · 82 lines

What it actually says

Device Sync - Push & Pull

Manage cross-device synchronization of Claude Code sessions and memory.

Push (Upload)

Push the current session and memory to the sync repository:

# Push everything (session + memory)
device-sync push

# Push only memory files
device-sync push --memory-only

# Push only the current session
device-sync push --session-only

Pull (Download)

Pull the latest state from the sync repository:

# Pull everything
device-sync pull

# Pull only memory files
device-sync pull --memory-only

Status

Check the current sync status, registered devices, and configuration:

device-sync status

Sessions

List all synced sessions across devices:

# List all sessions
device-sync sessions

# Filter by user (team mode)
device-sync sessions --user <username>

# Filter by project
device-sync sessions --project <path>

Purge

Delete old sessions to free space:

# Delete sessions older than 30 days (default)
device-sync purge

# Custom retention period
device-sync purge --days 7

# Preview what would be deleted
device-sync purge --dry-run

Notes

  • Push/pull is automatic when hooks are installed (device-sync hooks install)
  • Memory sync only affects the current project's memory directory
  • Sessions are encrypted with ChaCha20-Poly1305 before being stored
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. 3d ago First seen · 82 lines · 33 tokens per session scan A 501dfc60bcf7

Subscribe to this mod's changes

device-sync is a skill published in the GitHub repository hmennen90/claude-device-sync (1 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 352 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Related

Other skills, from other repositories

self-service-and-knowledge

Builds the help center, in-product guidance, and knowledge base that let customers resolve problems without contacting anyone — content, findability, maintenance, and deflection measurement. Use this to build or fix a help center, reduce support volume, write documentation for customers, improve findability, or decide…

cbrock84/headcount · 75 tokens

agent-memory

3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge. TRIGGER when: reading or writing agent memory files, choosing which memory tier an insight belongs in, or starting a task needing prior context. SKIP: vector recall (use semantic-memory-mcp); distilling conversations into…

komluk/scaffolding · 70 tokens

memory

Unified memory CRUD: write/update/delete/query file-based markdown entries and sync to MCP semantic store. TRIGGER when: saving a new memory entry, updating or deleting an existing entry, querying stored memories, or deduplicating before write. SKIP: 3-tier agent memory (use agent-memory); in-task vector recall (use…

komluk/scaffolding · 73 tokens

semantic-memory-mcp

Proactive use of semantic-memory MCP tools (semanticsearch, semanticrecall). TRIGGER when: an agent should search vector memory for prior insights mid-task. SKIP: file-based 3-tier memory (use agent-memory); storing a new memory (use semantic-memory-store).

komluk/scaffolding · 61 tokens

distill

Knowledge distillation methodology: candidate extraction, confidence scoring, tier routing, conversation-scoped mode. TRIGGER when: running /learn or /distill, deciding if an insight is memory-worthy, or scoring a knowledge candidate. SKIP: ad-hoc memory reads/writes (use agent-memory); vector storage (use…

komluk/scaffolding · 71 tokens

operate-hermes-agent

Install, update, migrate to, configure, run, secure, and troubleshoot Hermes Agent across its CLI, TUI, desktop, dashboard, profiles, tools, skills, memory, models, goals, voice, sessions, worktrees, and terminal backends.

gaelic-ghost/socket · 57 tokens