LeoYeAI/agent-master-skills / skills/agent-comm-hub
agent-comm-hub
Flagged多智能体协同通信基础设施——基于 MCP+SSE 的实时消息、任务调度、记忆共享与进化引擎。支持 WorkBuddy、Hermes、QClaw 及任意 MCP 兼容 Agent 接入。53 个 MCP 工具、4 级权限、零外部依赖 Python SDK。触发词:agent通信、智能体通信、hub通信、多智能体、跨agent通信、任务调度、assign_task、send_message、hermes通信、workbuddy通信、agent hub、通信hub、mcp通信、记忆共享、进化引擎、策略共享、经验分享、共享记忆,共同进化
src/tools/consumed.ts
View on GitHub/**
* consumed.ts — MCP 工具:消费水位线模块
* 包含:mark_consumed, check_consumed
* 来源:tools.ts 第 936-1050 行
*/
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";
import { randomUUID } from "crypto";
import { type ConsumedEntry } from "../db.js";
import { consumedRepo } from "../repo/sqlite-impl.js";
import { type AuthContext } from "../security.js";
import { logError } from "../logger.js";
import { withRetry, requireAuth } from "../utils.js";
import { getErrorMessage } from "../types.js";
export function registerConsumedTools(server: McpServer, authContext?: AuthContext): void {
// ────────────────────────────────────────────────────
// Tool 12: mark_consumed (原有,添加权限检查)
// ────────────────────────────────────────────────────
server.tool(
"mark_consumed",
"记录 Agent 已处理某个资源(文件路径或信号 ID)。处理完 WorkBuddy 发来的任何文件或信号后必须调用,防止下次重复处理。",
{
agent_id: z.string().describe("执行方 Agent ID,如 hermes"),
resource: z.string().describe("文件路径(相对 shared 目录)或信号 ID"),
resource_type: z.enum(["file", "signal", "message"]).default("file"),
action: z.string().describe("执行的动作,如 reviewed_and_replied / acknowledged / processed"),
notes: z.string().optional().describe("处理说明,方便日后追溯"),
},
async ({ agent_id, resource, resource_type, action, notes }) => {
requireAuth(authContext, "mark_consumed");
try {
const entry: ConsumedEntry = {
id: randomUUID(),
agent_id,
resource,
resource_type,
action,
notes: notes || null,
consumed_at: Date.now(),
};
await withRetry(
() => consumedRepo.insert(entry),
"mark_consumed:insert"
);
return {
content: [{
type: "text",
text: JSON.stringify({
success: true,
resource,
resource_type,
action,
consumed_at: new Date(entry.consumed_at).toISOString(),
note: "已记录消费水位线,下次不会重复处理此资源",
}, null, 2),
}],
};
} catch (err: unknown) {
logError("mark_consumed_error", err);
return {
content: [{
type: "text",
text: JSON.stringify({
success: false,
error: getErrorMessage(err),
fallback: "水位线记录失败,建议稍后重试或检查 Hub 服务状态",
}),
}],
};
}
}
);
// ────────────────────────────────────────────────────
// Tool 13: check_consumed (原有,添加权限检查)
// ────────────────────────────────────────────────────
server.tool(
"check_consumed",
"查询某资源是否已被当前 Agent 处理过。在处理 WorkBuddy 发来的文件或信号前,先调用此工具检查,已处理的直接跳过。",
{
agent_id: z.string().describe("Agent ID,如 hermes"),
resource: z.string().describe("文件路径或信号 ID"),
},
async ({ agent_id, resource }) => {
requireAuth(authContext, "check_consumed");
try {
const record = await withRetry(
() => consumedRepo.check(agent_id, resource),
"check_consumed:query"
);
if (record) {
return {
content: [{
type: "text",
text: JSON.stringify({
consumed: true,
resource,
action: record.action,
notes: record.notes,
consumed_at: new Date(record.consumed_at).toISOString(),
advice: "此资源已处理过,无需重复操作。如需重新处理,请通知 WorkBuddy 发送新版本。",
}, null, 2),
}],
};
}
return {
content: [{
type: "text",
text: JSON.stringify({
consumed: false,
resource,
advice: "此资源尚未处理,可以正常处理。处理完成后请调用 mark_consumed 记录水位线。",
}, null, 2),
}],
};
} catch (err: unknown) {
logError("check_consumed_error", err);
return {
content: [{
type: "text",
text: JSON.stringify({
consumed: false,
resource,
warning: `水位线查询失败: ${getErrorMessage(err)}`,
advice: "无法确认是否已处理(查询出错),建议继续处理并在完成后调用 mark_consumed",
}, null, 2),
}],
};
}
}
);
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |