A workflow for moving a workspace or tab between Herdr sessions, where each session runs as a separate server. It snapshots the source, closes the selected items, and rebuilds them in the target so agents and shells can resume.

Use it to transfer a complete workspace or a single tab, including Claude or Codex agents, shells, and command panes, to an already running Herdr session.

It avoids manually recreating running work in another session. A preview shows what will be closed and rebuilt before the move is performed.

move — Skill for Claude Code by motlin/claude-code-plugins

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add motlin/claude-code-plugins

Claude Code

/plugin install herdr-reboot

Made for: Claude Code.

Or install herdr-reboot, the plugin that ships this one along with the rest of its 2 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/motlin/claude-code-plugins/move/github.svg)](https://agentmods.dev/skills/motlin/claude-code-plugins/move)

Your own site

<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/move"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/move/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/move"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/move.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 536 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00536
Opus 5.5	$0.00024	$0.00214
Sonnet 5.5	$0.00012	$0.00107
Haiku 4.5	$0.00006	$0.00054

Measured 9d ago against content hash acf6cabcb310, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

move 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 9d 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.

plugins/herdr-reboot/skills/move/SKILL.md · 34 lines

What it actually says

Move Herdr Workspaces Between Sessions

Each herdr session is its own server, so panes cannot be handed across. The move snapshots the source session, closes the selection there, and rebuilds it in the target with the restore logic: claude panes come back via claude --resume, codex via codex resume, shells in the same directory, and command panes re-run.

Resolve <plugin-root>: ${CLAUDE_PLUGIN_ROOT} in Claude Code; in Codex, the plugin root containing this loaded skills/move/SKILL.md.

Each selector is a workspace label (beta) or workspace/tab for one tab (alpha/dev), which lands in the target as its own workspace named after the tab. --from defaults to the session this runs in.

Preview first and show the user what would be closed and rebuilt:

python3 "<plugin-root>/scripts/move.py" beta --to later

Once the user confirms, run it for real:

python3 "<plugin-root>/scripts/move.py" beta --to later --go

Tell the user before running --go:

The target session must already be running. If it is not, the script says so and prints the herdr session attach <name> command; the user starts it in a terminal, then re-run. Never start it yourself.
A selected pane whose agent is working refuses the whole move, since closing it interrupts the turn. Wait for it to finish. A blocked pane is moved with a warning: its pending prompt is dropped.
The move refuses to include the pane it runs from. Run it from a pane outside the selection.
The full source snapshot is backed up to .llm/herdr-move-backup-<session>-<timestamp>.json before anything closes. Restoring that file with restore.py (run with HERDR_SESSION=<source>) recovers from a failed move.
--no-commands leaves dev-server command panes at a shell in the target, for when the source still holds their ports.
After the move, a summary counts the moved panes by agent and status in the target. Agents still starting may show unknown.

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.

9d ago First seen · 34 lines · 61 tokens per session scan A acf6cabcb310

Subscribe to this mod's changes

move is a skill published in the GitHub repository motlin/claude-code-plugins (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 536 once invoked, about $0.0002 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 2026-10-12.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens