Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HelixDevelopment/codenpx agentmods add skills/helixdevelopment/code/session-syncWrote 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.
[](https://agentmods.dev/skills/helixdevelopment/code/session-sync)<a href="https://agentmods.dev/skills/helixdevelopment/code/session-sync"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/session-sync/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/helixdevelopment/code/session-sync"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/session-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.01349 |
| Opus 5.5 | $0.00033 | $0.00540 |
| Sonnet 5.5 | $0.00016 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
session-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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Sync Skill — Bidirectional Claude Code Session Import/Export via SSH
Revision: 1 Last modified: 2026-07-13T00:00:00Z Status: active
Purpose
Syncs ALL Claude Code project data — memories, session transcripts, settings, agent definitions, remember-logs, and handoff documents — between the SAME project on a REMOTE host and the local machine. Supports pull (remote→local), push (local→remote), and bidirectional sync.
After running, the local project can CONTINUE work EXACTLY where the remote session left off — same memories, same session history, same settings. This is the bridge between multi-track workstations (§11.4.187).
When to use
- Starting work on a new machine — pull all session state from the primary workstation so you resume exactly where you left off.
- Switching between workstations — push your session state back before leaving, pull when you arrive.
- After a remote session completes major work — pull the updated memories and handoff docs so the local project knows the latest state.
- Before/after a rebuild cycle — sync session state to keep all tracks aligned.
How to invoke
This skill provides the session-sync.sh script at:
constitution/skills/session-sync/session-sync.sh
# Pull everything from remote workstation (DEFAULT):
bash constitution/skills/session-sync/session-sync.sh user@host /path/to/project
# Push local state to remote:
bash constitution/skills/session-sync/session-sync.sh --push user@host /path/to/project
# Bidirectional two-way sync:
bash constitution/skills/session-sync/session-sync.sh --bidirectional user@host /path/to/project
# Quick mode (recent sessions only, faster):
bash constitution/skills/session-sync/session-sync.sh --quick user@host /path/to/project
# Preview without copying:
bash constitution/skills/session-sync/session-sync.sh --dry-run user@host /path/to/project
What it syncs
| Data | Description |
|---|---|
| Memories | Project-specific memory files (.md with frontmatter) |
| Session JSONL | Full Claude Code session transcripts |
| Session dirs | Per-session working directories |
| Settings | .claude/settings.json + settings.local.json |
| Agents | .claude/agents/ — custom agent definitions |
| Remember logs | .remember/ — session handoff + daily logs |
| Handoff docs | docs/SESSION_RESUME.md + docs/CONTINUATION.md |
| Provider config | Global CLAUDE.md, history.jsonl, settings.json |
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.
- 2d ago Changed · +82 lines · +60 tokens per session 3af0f3493d9c
- 1mo ago First seen · 44 lines · 22 tokens per session scan A a30859b1be8f
session-sync is a skill published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,349 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
session-summaries
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.
search-shared-sessions
Search an Agent Relay workspace's shared coding-agent sessions for prior work, decisions, fixes, or the context behind a task or pull request. Use when team history could answer the user's question or prevent repeating an investigation.
make-skill
A guided workflow for turning a conversation's solution into a reusable skill for coding agents.
hqe
Comprehensive codebase health auditing, remediation, and verification skill based on the canonical HQE Protocol v5.0.0.
list-learned-actions
Explicit Codex workflow: List persisted reusable actions, UI skeletons, and legacy feedback memories before composing device primitives.