Coordinate material messages between explicitly selected desktop-backed agents, including Claude, Codex and bb. Separates exact inbox delivery, native task wake, receiver ACK and completed work.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use for desktop peer coordination, not ordinary solo work or CLI-only tasks. Read desktop-mesh-peer; when multiple desktop agents coexist read desktop-multi-agent. Record repository root, socket, exact sender/inbox, native task ID, team and run nonce. Never assume generic ia-codex-desktop or ia-claude-desktop names belong to this task.
The shell agent_send_logged helper has not acquired the JS helper's protections. If used, independently verify exact recipient and fresh complete render. Do not blindly combine shell injection with direct PTY writing. Never reuse historical TTY paths. Use provider-specific helpers for idle CLI TUIs, not desktop-inbox shortcuts. Never use Ctrl-C to clear Codex input. A busy pane is not an idle receiver.
No timer is required for ordinary exchange. For requested unattended work qualify native exact-task re-entry and independent alert supervision using the canonical cookbook, chapters 8-12 and Appendix I. See the Codex adapter, Claude adapter, or bb guide. Do not assume those mechanisms exist in every host.
At each authorized wake read own inbox, durable scoped work and the entire CURRENT outstanding-request set; use ledger context as a fallback, not a new authority source. Match sender/target exactly and exclude retired identities and closed nonces. A dated suffix is valid when it belongs to the current registered seat; do not ban all dated IDs. Record owner, scope, cadence, quiet policy, last controlled wake and retirement rule. Reconcile before updating cursors. Restart, route/task change or replacement makes prior liveness evidence STALE until retested. Armed is not HEALTHY. WAKE_RECEIVED proves re-entry; WORK_COMPLETE needs actual work evidence.
Include sender/target, native task address, run/request nonce, bounded ask, authorized paths, forbidden effects, evidence path/hash and ACK requirement. A relayed human decision needs quoted/file-backed evidence; it cannot expand direct authorization. Keep credentials and unnecessary personal data out of the plaintext ledger.
At closeout report actual render/wake/ACK/work evidence and remaining blockers. Mirrors must match the canonical skill; update only intended files after preservation. The bulk deploy-skills.sh script wipes mirror children and is not a harmless refresh.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Method for adding agent comments and work to a shared file without overlapping other agents. Creates isolated workspaces per agent with UTC timestamps. Use when told to add comments, reviews, or work to any file.
中文简介正在准备中。当前显示原文说明。
Check any artifact against an explicit specification and report adherence using the add-comments workspace format. Use when validating plans, scripts, docs, or code changes against a source-of-truth spec.
中文简介正在准备中。当前显示原文说明。
Join the Antigravity CLI (agy, Gemini 3.5 Flash) to the Interlateral mesh as a native CLI peer with its own tmux session, identity stamping, and the agy.js send helper. Use this instead of the Antigravity desktop-app CDP path.
中文简介正在准备中。当前显示原文说明。
Agents work in parallel on the same task; judges evaluate and select the winner.
中文简介正在准备中。当前显示原文说明。
Boot the explicitly selected CLI(s) as the human's concierge: a project-aware side channel that sits ABOVE the running agent system in a shared writable terminal. It answers status questions and handles the human's ad hoc tasking while the working agents collaborate on the mesh — it is not a worker, manager, or gatekeeper, and team progress never waits for it.
中文简介正在准备中。当前显示原文说明。
Multiple agents draft a structured document through federated co-authorship and formal voting.
中文简介正在准备中。当前显示原文说明。