agent-comm-hub 0.8.1 → 0.9.1

package/README.md

@@ -139,14 +139,14 @@ is manual (below).
 
 | Agent | Config file | Template | Skill location |
 |---|---|---|---|
-| MiniMax Code (mcode) | `~/.minimax/mcp.json` (+ `~/.minimax/mcp/mcp.json`) | [`agents/minimax-code/`](agents/minimax-code/) | `~/.minimax/skills/agent-comm-hub/SKILL.md` |
-| opencode | `~/.config/opencode/opencode.json` | [`agents/opencode/opencode.json`](agents/opencode/opencode.json) | `~/.config/opencode/skills/agent-comm-hub/SKILL.md` |
-| Kimi Code | `~/.kimi-code/mcp.json` | [`agents/kimi-code/mcp-entry.json`](agents/kimi-code/mcp-entry.json) | `~/.kimi-code/skills/agent-comm-hub/SKILL.md` |
-| Gemini CLI | `~/.gemini/settings.json` | [`agents/gemini-cli/settings.json`](agents/gemini-cli/settings.json) | `~/.gemini/skills/agent-comm-hub/SKILL.md` |
-| Codex | `~/.codex/config.toml` | [`agents/codex/config.toml`](agents/codex/config.toml) | `~/.codex/skills/agent-comm-hub/SKILL.md` |
-| zcode | `~/.zcode/cli/config.json` (`mcp.servers`) | [`agents/zcode/config.json`](agents/zcode/config.json) | `~/.zcode/skills/agent-comm-hub/SKILL.md` |
-| Claude Code | project `.mcp.json` (manual; `~/.claude.json` is never touched) | [`agents/claude-code/.mcp.json`](agents/claude-code/.mcp.json) | `~/.claude/skills/agent-comm-hub/SKILL.md` |
-| DeepSeek Harness (DSH) | `~/.dsh/profiles/*/cordis.patch.yml` (auto by `setup`) | [`agents/dsh/cordis.patch.yml`](agents/dsh/cordis.patch.yml) | `$DSH_HOME/skills/agent-comm-hub/SKILL.md` |
+| MiniMax Code (mcode) | `~/.minimax/mcp.json` (+ `~/.minimax/mcp/mcp.json`) | [`agents/minimax-code/`](agents/minimax-code/) | `~/.minimax/skills/agent-hub/SKILL.md` |
+| opencode | `~/.config/opencode/opencode.json` | [`agents/opencode/opencode.json`](agents/opencode/opencode.json) | `~/.config/opencode/skills/agent-hub/SKILL.md` |
+| Kimi Code | `~/.kimi-code/mcp.json` | [`agents/kimi-code/mcp-entry.json`](agents/kimi-code/mcp-entry.json) | `~/.kimi-code/skills/agent-hub/SKILL.md` |
+| Gemini CLI | `~/.gemini/settings.json` | [`agents/gemini-cli/settings.json`](agents/gemini-cli/settings.json) | `~/.gemini/skills/agent-hub/SKILL.md` |
+| Codex | `~/.codex/config.toml` | [`agents/codex/config.toml`](agents/codex/config.toml) | `~/.codex/skills/agent-hub/SKILL.md` |
+| zcode | `~/.zcode/cli/config.json` (`mcp.servers`) | [`agents/zcode/config.json`](agents/zcode/config.json) | `~/.zcode/skills/agent-hub/SKILL.md` |
+| Claude Code | project `.mcp.json` (manual; `~/.claude.json` is never touched) | [`agents/claude-code/.mcp.json`](agents/claude-code/.mcp.json) | `~/.claude/skills/agent-hub/SKILL.md` |
+| DeepSeek Harness (DSH) | `~/.dsh/profiles/*/cordis.patch.yml` (auto by `setup`) | [`agents/dsh/cordis.patch.yml`](agents/dsh/cordis.patch.yml) | `$DSH_HOME/skills/agent-hub/SKILL.md` |
 
 > Streamable-http support varies by agent version; the templates use the fields each agent documents. If a client lacks HTTP MCP, wrap the endpoint with a stdio shim.
 
@@ -179,7 +179,7 @@ Copy `agents/claude-code/.mcp.json` into your project root (or merge `mcpServers
 }
 ```
 
-Copy `agents/SKILL.md` to `~/.claude/skills/agent-comm-hub/SKILL.md`, restart Claude, and have it `bridge_register("claude-code:myproject")`.
+Copy `agents/SKILL.md` to `~/.claude/skills/agent-hub/SKILL.md`, restart Claude, and have it `bridge_register("claude-code:myproject")`.
 
 ### opencode
 
@@ -315,7 +315,8 @@ history attribution move atomically — queued messages and acks stay
 continuous. Renaming yourself is open to everyone; renaming/kicking
 **another** peer (`bridge_unregister { peer }`) or reading another peer's
 history (`bridge_history { peer }` / `peer: "all"`) requires the **manager**
-role (`--manager-peers`, default `agent-hub-cli` — the desktop GUI identity).
+role (`--manager-peers`, default `agent-hub-cli,hub-admin` — the desktop GUI
+and the web console identities).
 This is a convention on top of the loopback trust model, not authentication.
 
 Rosters persist: `--state-file` (default `~/.agent-comm-hub/roster.json`,
@@ -351,7 +352,7 @@ agent-comm-hub service install|uninstall [options]   one-shot auto-start
                          (default herdr, resolved via PATH)
 --herdr-timeout-ms <n>   Default cap for one herdr call in ms (default 30000)
 --manager-peers <ids>    Comma-separated roster managers, or "all"
-                         (default agent-hub-cli — the desktop GUI identity)
+                         (default agent-hub-cli,hub-admin — desktop GUI + web console)
 --state-file <path>      Roster persistence file
                          (default ~/.agent-comm-hub/roster.json; "off" = memory only)
 --url <u> / --server-name <n> / --remove / --dry-run   (setup/service/status)
@@ -429,7 +430,8 @@ const hub = startHub({ port: 18764 }, console) // returns { hub, registry, serve
 ```bash
 pnpm install
 pnpm typecheck        # tsc --noEmit (strict)
-pnpm test             # test suite (263 checks: 138 smoke + 36 setup + 11 ops + 35 herdr + 23 discover + 20 e2e)
+pnpm test             # test suite (291 checks: 165 smoke + 37 setup + 11 ops + 35 herdr + 23 discover + 20 e2e)
+npm run build:admin   # admin/ workspace (npm) → single-file assets/admin.html
 pnpm run build        # esbuild → lib/{cli,index,setup}.js (zero deps)
 pnpm pack             # build + npm pack (publishing artifact)
 ```
@@ -479,4 +481,4 @@ Tests cover registration, duplicate rejection, chat routing, sender-filtered wai
 
 ## License
 
-MIT — see [LICENSE](LICENSE). Contributions welcome: keep the 64-check suite green (`pnpm test`) and zero runtime dependencies. Architecture: [ARCHITECTURE.md](ARCHITECTURE.md).
+MIT — see [LICENSE](LICENSE). Contributions welcome: keep the 291-check suite green (`pnpm test`) and zero runtime dependencies. Architecture: [ARCHITECTURE.md](ARCHITECTURE.md).

package/README.zh.md

@@ -124,14 +124,14 @@ curl -X POST http://127.0.0.1:18764/mcp \
 
 | Agent | 配置文件 | 模板 | Skill 位置 |
 |---|---|---|---|
-| MiniMax Code (mcode) | `~/.minimax/mcp.json`（+ `~/.minimax/mcp/mcp.json`） | [`agents/minimax-code/`](agents/minimax-code/) | `~/.minimax/skills/agent-comm-hub/SKILL.md` |
-| opencode | `~/.config/opencode/opencode.json` | [`agents/opencode/opencode.json`](agents/opencode/opencode.json) | `~/.config/opencode/skills/agent-comm-hub/SKILL.md` |
-| Kimi Code | `~/.kimi-code/mcp.json` | [`agents/kimi-code/mcp-entry.json`](agents/kimi-code/mcp-entry.json) | `~/.kimi-code/skills/agent-comm-hub/SKILL.md` |
-| Gemini CLI | `~/.gemini/settings.json` | [`agents/gemini-cli/settings.json`](agents/gemini-cli/settings.json) | `~/.gemini/skills/agent-comm-hub/SKILL.md` |
-| Codex | `~/.codex/config.toml` | [`agents/codex/config.toml`](agents/codex/config.toml) | `~/.codex/skills/agent-comm-hub/SKILL.md` |
-| zcode | `~/.zcode/cli/config.json`（`mcp.servers`） | [`agents/zcode/config.json`](agents/zcode/config.json) | `~/.zcode/skills/agent-comm-hub/SKILL.md` |
-| Claude Code | 项目根 `.mcp.json`（手动；**绝不碰 `~/.claude.json`**——含凭据） | [`agents/claude-code/.mcp.json`](agents/claude-code/.mcp.json) | `~/.claude/skills/agent-comm-hub/SKILL.md` |
-| DeepSeek Harness (DSH) | profile `cordis.patch.yml`（手动） | [`agents/dsh/cordis.patch.yml`](agents/dsh/cordis.patch.yml) | `$DSH_HOME/skills/agent-comm-hub/SKILL.md` |
+| MiniMax Code (mcode) | `~/.minimax/mcp.json`（+ `~/.minimax/mcp/mcp.json`） | [`agents/minimax-code/`](agents/minimax-code/) | `~/.minimax/skills/agent-hub/SKILL.md` |
+| opencode | `~/.config/opencode/opencode.json` | [`agents/opencode/opencode.json`](agents/opencode/opencode.json) | `~/.config/opencode/skills/agent-hub/SKILL.md` |
+| Kimi Code | `~/.kimi-code/mcp.json` | [`agents/kimi-code/mcp-entry.json`](agents/kimi-code/mcp-entry.json) | `~/.kimi-code/skills/agent-hub/SKILL.md` |
+| Gemini CLI | `~/.gemini/settings.json` | [`agents/gemini-cli/settings.json`](agents/gemini-cli/settings.json) | `~/.gemini/skills/agent-hub/SKILL.md` |
+| Codex | `~/.codex/config.toml` | [`agents/codex/config.toml`](agents/codex/config.toml) | `~/.codex/skills/agent-hub/SKILL.md` |
+| zcode | `~/.zcode/cli/config.json`（`mcp.servers`） | [`agents/zcode/config.json`](agents/zcode/config.json) | `~/.zcode/skills/agent-hub/SKILL.md` |
+| Claude Code | 项目根 `.mcp.json`（手动；**绝不碰 `~/.claude.json`**——含凭据） | [`agents/claude-code/.mcp.json`](agents/claude-code/.mcp.json) | `~/.claude/skills/agent-hub/SKILL.md` |
+| DeepSeek Harness (DSH) | profile `cordis.patch.yml`（手动） | [`agents/dsh/cordis.patch.yml`](agents/dsh/cordis.patch.yml) | `$DSH_HOME/skills/agent-hub/SKILL.md` |
 
 > 各 agent 对 streamable-http 的支持随版本演进；不支持的客户端可加 stdio 包装。
 
@@ -206,7 +206,7 @@ agent-comm-hub service uninstall
 
 ### 花名册管理（别名、踢人）
 
-每个 peer 带一份**档案**：连接时上报的客户端名/版本，外加可选的**显示别名**（`bridge_rename`）。别名纯展示——只出现在 `bridge_peers` / `bridge_status` 和桌面端花名册里；路由、信箱、历史、ack 始终使用 peer id，因此改名不会丢消息、不迁移状态。管理端还能对已注册 peer 做**真改名**（`bridge_rename { peer, peerId }`）：信箱、等待器、session 绑定与历史归属原子迁移，排队消息与 ack 路由保持连续。给自己改别名人人可以；改**别人**的别名、踢人（`bridge_unregister { peer }`）、读别人的历史（`bridge_history { peer }` / `peer: "all"`）需要**管理端**身份（`--manager-peers`，默认 `agent-hub-cli`，即桌面 GUI 的身份）。这是叠加在本机信任模型上的约定，不是鉴权。
+每个 peer 带一份**档案**：连接时上报的客户端名/版本，外加可选的**显示别名**（`bridge_rename`）。别名纯展示——只出现在 `bridge_peers` / `bridge_status` 和桌面端花名册里；路由、信箱、历史、ack 始终使用 peer id，因此改名不会丢消息、不迁移状态。管理端还能对已注册 peer 做**真改名**（`bridge_rename { peer, peerId }`）：信箱、等待器、session 绑定与历史归属原子迁移，排队消息与 ack 路由保持连续。给自己改别名人人可以；改**别人**的别名、踢人（`bridge_unregister { peer }`）、读别人的历史（`bridge_history { peer }` / `peer: "all"`）需要**管理端**身份（`--manager-peers`，默认 `agent-hub-cli,hub-admin`，即桌面 GUI 与网页管理台的身份）。这是叠加在本机信任模型上的约定，不是鉴权。
 
 花名册可落盘：`--state-file`（默认 `~/.agent-comm-hub/roster.json`，`off` 关闭），别名与客户端信息在 hub 重启后保留。
 
@@ -276,7 +276,8 @@ const hub = startHub({ port: 18764 }, console) // 返回 { hub, registry, server
 ```bash
 pnpm install
 pnpm typecheck        # tsc --noEmit（strict）
-pnpm test             # 测试套件（240 项：135 冒烟 + 36 安装器 + 11 运维 + 35 herdr + 23 发现）
+pnpm test             # 测试套件（291 项：165 冒烟 + 37 安装器 + 11 运维 + 35 herdr + 23 发现 + 20 e2e）
+npm run build:admin   # admin/ 工作区（用 npm）→ 单文件 assets/admin.html
 pnpm run build        # esbuild → lib/{cli,index,setup}.js（零依赖）
 pnpm pack             # 构建 + npm pack（发布产物）
 ```

package/agents/README.md

@@ -23,14 +23,14 @@ Codex（TOML 追加）/ zcode（`mcp.servers`）。Claude Code 和 DSH 需手动
 
 | Agent | 配置文件 | 片段 | Skill 位置 |
 |---|---|---|---|
-| MiniMax Code (mcode) | `~/.minimax/mcp.json` + `~/.minimax/mcp/mcp.json` | `minimax-code/mcp-entry.json` | `~/.minimax/skills/agent-comm-hub/SKILL.md`（或跑 `minimax-code/install-mcode.ps1`） |
-| opencode | `~/.config/opencode/opencode.json` | `opencode/opencode.json` | `~/.config/opencode/skills/agent-comm-hub/SKILL.md` |
-| Kimi Code | `~/.kimi-code/mcp.json` | `kimi-code/mcp-entry.json`（`transport: "http"`，url 自动推断为 http） | `~/.kimi-code/skills/agent-comm-hub/SKILL.md` |
-| Gemini CLI | `~/.gemini/settings.json` | `gemini-cli/settings.json` | `~/.gemini/skills/agent-comm-hub/SKILL.md` |
-| Codex | `~/.codex/config.toml` | `codex/config.toml` | `~/.codex/skills/agent-comm-hub/SKILL.md` |
-| zcode | `~/.zcode/cli/config.json` | `zcode/config.json` | `~/.zcode/skills/agent-comm-hub/SKILL.md` |
-| Claude Code | 项目根 `.mcp.json`（手动复制；**不碰 `~/.claude.json`**——含凭据且无法安全往返） | `claude-code/.mcp.json` | `~/.claude/skills/agent-comm-hub/SKILL.md` |
-| DeepSeek Harness (DSH) | profile `cordis.patch.yml`（手动合并） | `dsh/cordis.patch.yml`（`@deepseek-ai/dsh-mcp-client`，**serverName: `agent-comm-hub`**，工具名为 `mcp__agent-comm-hub__bridge_*`；刻意不用 `agent-hub`，避免与 MCP 管理器动态挂载同名冲突） | `$DSH_HOME/skills/agent-comm-hub/SKILL.md` |
+| MiniMax Code (mcode) | `~/.minimax/mcp.json` + `~/.minimax/mcp/mcp.json` | `minimax-code/mcp-entry.json` | `~/.minimax/skills/agent-hub/SKILL.md`（或跑 `minimax-code/install-mcode.ps1`） |
+| opencode | `~/.config/opencode/opencode.json` | `opencode/opencode.json` | `~/.config/opencode/skills/agent-hub/SKILL.md` |
+| Kimi Code | `~/.kimi-code/mcp.json` | `kimi-code/mcp-entry.json`（`transport: "http"`，url 自动推断为 http） | `~/.kimi-code/skills/agent-hub/SKILL.md` |
+| Gemini CLI | `~/.gemini/settings.json` | `gemini-cli/settings.json` | `~/.gemini/skills/agent-hub/SKILL.md` |
+| Codex | `~/.codex/config.toml` | `codex/config.toml` | `~/.codex/skills/agent-hub/SKILL.md` |
+| zcode | `~/.zcode/cli/config.json` | `zcode/config.json` | `~/.zcode/skills/agent-hub/SKILL.md` |
+| Claude Code | 项目根 `.mcp.json`（手动复制；**不碰 `~/.claude.json`**——含凭据且无法安全往返） | `claude-code/.mcp.json` | `~/.claude/skills/agent-hub/SKILL.md` |
+| DeepSeek Harness (DSH) | profile `cordis.patch.yml`（手动合并） | `dsh/cordis.patch.yml`（`@deepseek-ai/dsh-mcp-client`，**serverName: `agent-comm-hub`**，工具名为 `mcp__agent-comm-hub__bridge_*`；刻意不用 `agent-hub`，避免与 MCP 管理器动态挂载同名冲突） | `$DSH_HOME/skills/agent-hub/SKILL.md` |
 
 > 各 agent 对 streamable-http MCP 的支持随版本演进，模板里的字段以官方文档为准；
 > 不支持的版本可退化为 stdio 包装（见下）。

package/agents/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agent-comm-hub
-description:
+description: >-
   Real-time two-way communication with other AI agents connected to the local
   agent-comm-hub. Use when the user mentions another agent, the hub, group
   chat, sending messages or tasks to another agent, waiting for another
@@ -23,23 +23,28 @@ Optional: call `bridge_register(peerId)` to claim a readable id
 
 ## Tools
 
-- `bridge_chat(to, message)` — send a chat message to a peer; `to: "all"`
-  broadcasts.
-- `bridge_task(to, prompt, context?, deliverable?)` — delegate a structured
-  task.
-- `bridge_ack(ref, status, note?)` — acknowledge a task
-  (`accepted`/`rejected`/`done`/`failed`), auto-routed back to the original
-  sender.
-- `bridge_task_status(ref)` — one task's ledger state + full ack timeline.
+- `bridge_chat(to, message, threadId?, ref?)` — send a chat to a peer, group
+  id, or `"all"` (broadcast). `threadId` groups a multi-turn dialog; `ref`
+  marks a reply-to and is capped at 5 hops per chain (see Notes).
+- `bridge_task(to, prompt, context?, deliverable?, timeoutMs?, threadId?)` —
+  delegate a structured task. `timeoutMs` is a soft SLA: the hub marks the
+  task `timeout` if no terminal ack arrives in time.
+- `bridge_ack(ref, status, note?, progress?)` — acknowledge a task.
+  Statuses: `accepted` | `working` | `rejected` | `done` | `failed`.
+  `working` + `progress` (0–100) report intermediate state. Terminal
+  statuses lock the task (later acks are recorded on the timeline but do
+  not reopen it). The ack is auto-routed to the original sender of `ref`.
+- `bridge_task_status(ref)` — one task's ledger state, per-assignee state,
+  and full ack timeline.
 - `bridge_tasks(role?, status?, limit?)` — list tasks you sent or received.
-- `bridge_wait(from?, ref?, timeoutMs?)` — long-poll for the next message
-  (default 30 s; `ref` waits specifically for that task's ack; loop it to
-  hold a real-time conversation).
+- `bridge_wait(from?, ref?, threadId?, timeoutMs?)` — long-poll for the next
+  message (default 30 s; `ref` waits for that task's ack; `threadId` narrows
+  to one dialog). Loop it to hold a real-time conversation.
 - `bridge_poll(from?)` — non-blocking drain of every queued message.
 - `bridge_status()` / `bridge_peers()` — hub health and who is online.
-- `bridge_history(peer?, limit?)` — recent messages (newest first). `peer`
-  defaults to you; pass another peer's id to read their conversation, or
-  `"all"` for the unfiltered tail across every peer.
+- `bridge_history(peer?, limit?, channel?)` — recent messages (newest first).
+- `bridge_group_create/send/list/delete` + `add_member`/`remove_member` —
+  named channels for a subset of peers.
 
 ## When to use
 
@@ -52,9 +57,11 @@ Optional: call `bridge_register(peerId)` to claim a readable id
 3. Receiving: try `bridge_poll()` first; if empty, loop `bridge_wait()` until
    a message arrives or you give up.
 4. On receiving a `task` (content is `{prompt, context?, deliverable?}`):
-   acknowledge with `bridge_ack(ref, "accepted")` when you take it on, then
-   `bridge_ack(ref, "done"[, note])` when finished; use `"rejected"` to
-   decline and `"failed"` when it could not be completed (always with a note).
+   - `bridge_ack(ref, "accepted")` when you take it on
+   - `bridge_ack(ref, "working", note?, progress?)` for long-running work
+   - `bridge_ack(ref, "done"[, note])` when finished
+   - `bridge_ack(ref, "rejected")` to decline (with a reason)
+   - `bridge_ack(ref, "failed")` when it could not be completed (with a note)
 5. Unsure whether the peer is online: check `bridge_peers()` first.
 
 ## Common workflows (plain language)
@@ -64,29 +71,45 @@ Follow the scenario directly (tool names stay as-is):
 **1. Someone delegates a task to you (e.g. codex plans -> you build)**
 - On receiving a task: acknowledge first — `bridge_ack(ref, "accepted")`,
   say "got it, starting".
+- For work that takes a while: `bridge_ack(ref, "working", note, progress)`
+  so the delegator can see it is moving.
 - When done: send the result and a delivery note back to the delegator
   (`bridge_chat` / `bridge_task`), then `bridge_ack(ref, "done", note)` so it
   can review.
 - If you can't do it: `bridge_ack(ref, "rejected")` with the reason.
 
 **2. You delegate to someone else (wait vs don't-wait)**
-- Wait for delivery: after `bridge_task`, loop `bridge_wait()` until the
-  result arrives, then take it over.
+- Wait for delivery: after `bridge_task`, loop `bridge_wait({ref})` until the
+  terminal ack arrives, then take the result over.
 - Don't wait: send it and move on; the peer sends the result back when done —
   collect it later with `bridge_poll()` / `bridge_wait()` /
   `bridge_history()` (messages queue while you are away).
+- Need a deadline: pass `timeoutMs` on `bridge_task`; the ledger will show
+  `timeout` if the assignee never finishes.
 
 **3. Multi-agent real-time discussion**
 - After you've said your piece, stay in the conversation: loop
   `bridge_wait()` to keep listening — nothing arrived this round, wait the
   next — until a conclusion is reached or the user says "done".
 - A timeout (`{type:"timeout"}`) is not a failure; keep waiting.
+- Optional: put the dialog on one `threadId` so `bridge_wait({threadId})`
+  only sees that conversation.
 
 ## Notes
 
-- Messages travel on loopback only (127.0.0.1:18764); never put credentials
-  in bridge messages.
+- Messages travel on loopback only (127.0.0.1:18764) in local mode; never put
+  credentials in bridge messages.
 - A timeout is not a failure: `bridge_wait` returning `{type:"timeout"}` just
   means nothing arrived — try again.
 - Cadence: use 10–30 s short polls when the peer is active; check
   `bridge_peers()` when unsure.
+- Task terminal states (`done`/`failed`/`rejected`/`timeout`) cannot be
+  reopened; start a new task instead of re-acking.
+- **Reply chains are capped at 5 hops.** Every message carrying `ref` sits one
+  hop deeper than the message it points at, and the hub rejects the 6th with
+  `hop limit exceeded`. You only run into it when you keep replying
+  (`ref`) or re-delegating along one chain instead of starting a new message —
+  two agents answering each other's replies forever is exactly what the cap
+  exists to stop. When it happens, stop extending that chain: send a fresh
+  message with no `ref` (a new `threadId` keeps it readable as one dialog) and
+  restate the context in it, or continue with `bridge_task` for new work.

package/agents/install-all.ps1

@@ -117,25 +117,21 @@ Write-Step '- mcode'
 foreach ($f in @((Join-Path $userHome '.minimax\mcp.json'), (Join-Path $userHome '.minimax\mcp\mcp.json'))) {
   Merge-JsonServer 'mcode' $f 'mcpServers' $mcodeEntry
 }
-Sync-Skill 'mcode' (Join-Path $userHome '.minimax\skills\agent-comm-hub')
 
 # ---------- opencode: mcp.<name> in ~/.config/opencode/opencode.json
 $opencodeEntry = [ordered]@{ type = 'remote'; url = $Url; enabled = $true }
 Write-Step '- opencode'
 Merge-JsonServer 'opencode' (Join-Path $userHome '.config\opencode\opencode.json') 'mcp' $opencodeEntry
-Sync-Skill 'opencode' (Join-Path $userHome '.config\opencode\skills\agent-comm-hub')
 
 # ---------- Kimi Code: mcpServers at root of ~/.kimi-code/mcp.json
 $kimiEntry = [ordered]@{ transport = 'http'; url = $Url; startupTimeoutMs = 30000; toolTimeoutMs = 120000 }
 Write-Step '- kimi-code'
 Merge-JsonServer 'kimi-code' (Join-Path $userHome '.kimi-code\mcp.json') 'mcpServers' $kimiEntry
-Sync-Skill 'kimi-code' (Join-Path $userHome '.kimi-code\skills\agent-comm-hub')
 
 # ---------- Gemini CLI: mcpServers in ~/.gemini/settings.json
 $geminiEntry = [ordered]@{ type = 'http'; url = $Url }
 Write-Step '- gemini-cli'
 Merge-JsonServer 'gemini-cli' (Join-Path $userHome '.gemini\settings.json') 'mcpServers' $geminiEntry
-Sync-Skill 'gemini-cli' (Join-Path $userHome '.gemini\skills\agent-comm-hub')
 
 # ---------- Codex: append [mcp_servers.<name>] to ~/.codex/config.toml (incremental append only)
 $codexFile = Join-Path $userHome '.codex\config.toml'

package/agents/minimax-code/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agent-comm-hub
-description:
+description: >-
   Real-time two-way communication with other AI agents connected to the local
   agent-comm-hub. Use when the user mentions another agent, the hub, group
   chat, sending messages or tasks to another agent, waiting for another