Guide accessibility reviews for UI, documents, and workflows. Use for WCAG-oriented audits, keyboard review, semantics, contrast, and remediation planning.
日本語の概要は準備中です。原文の説明を表示しています。
Create temporary Herdr panes below the caller, resize and move owned panes, and clean up without stealing focus or overwriting user layout changes. Start with ls-herdr-task-routing.
日本語の概要は準備中です。原文の説明を表示しています。
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
Read the master first if it is not already loaded: ls-herdr-task-routing
Use localsetup herdr pane --help for the current argument contract.
For a temporary work area in the caller's managed pane:
localsetup herdr --workspace "$HERDR_WORKSPACE_ID" --pane "$HERDR_PANE_ID" \
--state-dir "$task_state" pane ensure --cwd "$PWD"
Here task_state is the existing task's absolute private state directory.
Keep the returned result.owner_id and result.pane.pane_id. Pass that owner
back as pane ensure --owner-id <owner-id> to reuse the same verified pane,
or pane cleanup <owner-id> when finished. Read the handles from JSON; do not
predict IDs or clear a pane after a reuse conflict.
The default temporary split is downward at 30%, without focus. If the geometry cannot support the request, report the concrete space limit and available owned-pane alternatives. Do not silently create a new workspace or worktree.
The tool records endpoint, parent, child, ownership, and relevant geometry. Use those records instead of pane labels as ownership proof. A label identifies display intent; it is not authorization to close or replace the occupant.
Restore prior geometry only when the affected topology still matches the tool's expected layout. Never apply a stale whole-tab snapshot after a user resize, move, or split. If ownership, occupant, or a mutation result is uncertain, inspect read-only and retain the record; do not close a guessed pane.
Use native JSON IDs and the shared core. Never resize through screenshots, keyboard simulation, sidebar order, or duplicated client-specific algorithms.
まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Guide accessibility reviews for UI, documents, and workflows. Use for WCAG-oriented audits, keyboard review, semantics, contrast, and remediation planning.
日本語の概要は準備中です。原文の説明を表示しています。
Use when choosing a LocalSetup Agent-* lane for exploration, research, bounded implementation, or review. Consult the static capability matrix; do not probe account or network availability.
日本語の概要は準備中です。原文の説明を表示しています。
Guide agent email inbox workflows with prompt-injection defenses. Use for inbound email processing, webhooks, routing, and safety review.
日本語の概要は準備中です。原文の説明を表示しています。
Navigate and understand codebases using agentlens hierarchical documentation. Use when exploring new projects, finding modules, locating symbols in large files, finding TODOs/warnings, or understanding code structure.
日本語の概要は準備中です。原文の説明を表示しています。
Use for Agent Q signed encrypted file-drop or mail ship and ingest, private registry v2 setup, queue status, and transport maintenance.
日本語の概要は準備中です。原文の説明を表示しています。
Inventory wrapper for the alirezarezvani Claude skills bundle. Use when triaging its broad skill catalog and large script surface before any targeted import.
日本語の概要は準備中です。原文の説明を表示しています。