multi-agent-workbench 0.0.0-stage → 0.1.0

package/LICENSE

@@ -0,0 +1,12 @@
+MIT License
+
+Copyright (c) 2026 Ruhul Amin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files, to deal in the Software
+without restriction, including without limitation the rights to use, copy,
+modify, merge, publish, distribute, sublicense, and/or sell copies of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.

package/README.md

@@ -1,3 +1,25 @@
-# Temporary Holding Version
+# Multi-Agent Workbench
 
-This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
+Run multiple coding-agent CLIs in parallel with isolated worktrees, micro-task queues, handoff history, and live status.
+
+## Quick start
+
+Create `tasks.json` in your project:
+
+```json
+[
+  {"id":"L1","owner":"claude","worktree":"../project-claude","task":"API task","prompt":"Implement the API task and commit it."},
+  {"id":"C1","owner":"codex","worktree":"../project-codex","task":"Frontend task","prompt":"Implement the frontend task and commit it."}
+]
+```
+
+Install and run:
+
+```bash
+npm install -g multi-agent-workbench
+multi-agent-workbench
+# or without installing
+npx multi-agent-workbench
+```
+
+The supervisor reads `tasks.json` from the current project and writes `.agent-workbench/status.json` and `.agent-workbench/supervisor.log`. Review each commit before merging or deploying.

package/bin/maw.mjs

@@ -0,0 +1,14 @@
+#!/usr/bin/env node
+import { spawn } from "node:child_process";
+import process from "node:process";
+import { fileURLToPath } from "node:url";
+import { dirname, resolve } from "node:path";
+
+const packageRoot = resolve(dirname(fileURLToPath(import.meta.url)), "..");
+const supervisor = resolve(packageRoot, "multi-agent-workbench/scripts/supervisor.mjs");
+const child = spawn(process.execPath, [supervisor, ...process.argv.slice(2)], {
+  cwd: process.cwd(),
+  stdio: "inherit",
+  env: process.env,
+});
+child.on("exit", (code, signal) => process.exit(signal ? 1 : (code ?? 1)));

package/multi-agent-workbench/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: multi-agent-workbench
+description: Orchestrate multiple local coding-agent CLIs in isolated worktrees with micro-task queues, handoffs, live status, review gates, and optional deployment triggers.
+---
+
+# Multi-agent workbench
+
+Use this skill when a software task benefits from multiple coding-agent CLIs working in parallel.
+
+- Split work into bounded micro-tasks with owners, dependencies, and acceptance checks.
+- Give each agent its own Git worktree and branch.
+- Assign frontend/integration tasks to Codex and backend/data tasks to Claude when requested.
+- Capture commit, tests, changed files, output, and risks after every task.
+- Review and cherry-pick centrally; never auto-merge unreviewed work.
+- Keep production tests/builds on the VPS when the repository uses a server-side deployment workflow.
+- Expose current state, task, commit, output, and completed history in a live status file/dashboard.
+
+See `references/task-schema.md` for handoff records and `scripts/supervisor.mjs` for the Node.js supervisor.

package/multi-agent-workbench/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Multi Agent Workbench"
+  short_description: "Help with Multi Agent Workbench tasks"

package/multi-agent-workbench/references/task-schema.md

@@ -0,0 +1,3 @@
+# Task and handoff schema
+
+Each task records an id, owner, worktree, prompt, dependencies, acceptance checks, state, commit, tests, and risks. Completed tasks must include the worker output and commit hash.

package/multi-agent-workbench/scripts/supervisor.mjs

@@ -0,0 +1,24 @@
+#!/usr/bin/env node
+import { mkdir, readFile, writeFile, appendFile } from "node:fs/promises";
+import { spawn } from "node:child_process";
+import process from "node:process";
+
+const root = process.env.WORKBENCH_ROOT || process.cwd();
+const dir = `${root}/.agent-workbench`;
+await mkdir(dir, { recursive: true });
+const tasks = JSON.parse(await readFile(process.env.WORKBENCH_TASKS || `${root}/tasks.json`, "utf8"));
+const statePath = `${dir}/status.json`, logPath = `${dir}/supervisor.log`;
+const state = { agents: {}, history: [], recent: [] };
+const save = () => writeFile(statePath, JSON.stringify({ ...state, updated_at: new Date().toISOString() }, null, 2));
+const log = async (line) => { const s = `[${new Date().toISOString()}] ${line}`; state.recent = [...state.recent, s].slice(-40); await appendFile(logPath, s + "\n"); await save(); };
+function run(cmd, args, cwd) { return new Promise(resolve => { const p = spawn(cmd, args, { cwd, stdio: ["ignore", "pipe", "pipe"] }); let out = ""; p.stdout.on("data", x => { out += x; process.stdout.write(x); }); p.stderr.on("data", x => { out += x; process.stderr.write(x); }); p.on("close", code => resolve({ code: code ?? 1, out })); }); }
+async function execute(task) {
+  state.agents[task.owner] = { state: "working", task: task.task, commit: null, output: [] }; await log(`${task.owner} start ${task.id}`);
+  const args = task.owner === "claude" ? ["--model", process.env.CLAUDE_MODEL || "haiku", "--effort", "low", "-p", task.prompt, "--dangerously-skip-permissions"] : ["exec", "-m", process.env.CODEX_MODEL || "gpt-6.1-sol", "-s", "danger-full-access", "--dangerously-bypass-approvals-and-sandbox", task.prompt];
+  const r = await run(task.owner === "claude" ? "claude" : "codex", args, task.worktree);
+  const commit = (r.out.match(/\b[0-9a-f]{7,40}\b/g) || []).at(-1) || null;
+  state.agents[task.owner] = { state: r.code === 0 ? "done" : "blocked", task: task.task, commit, output: r.out.split("\n").slice(-30) };
+  state.history = [...state.history, { id: task.id, owner: task.owner, task: task.task, commit, state: state.agents[task.owner].state, output: state.agents[task.owner].output, finished_at: new Date().toISOString() }].slice(-40);
+  await log(`${task.owner} ${state.agents[task.owner].state} ${task.id} ${commit || "—"}`); return r.code === 0;
+}
+await Promise.all(Object.entries(Object.groupBy(tasks, t => t.owner)).map(async ([, queue]) => { for (const task of queue) if (!await execute(task)) break; }));

package/package.json

@@ -1,6 +1,21 @@
 {
   "name": "multi-agent-workbench",
-  "version": "0.0.0-stage",
-  "stub": true,
-  "description": "Temporary package placeholder for staged publishing"
-}
+  "version": "0.1.0",
+  "description": "Run multiple coding-agent CLIs in parallel with task queues, isolated worktrees, handoffs, and live status.",
+  "type": "module",
+  "bin": {
+    "multi-agent-workbench": "bin/maw.mjs",
+    "maw": "bin/maw.mjs"
+  },
+  "files": ["bin", "multi-agent-workbench", "README.md", "LICENSE"],
+  "scripts": {
+    "start": "node bin/maw.mjs",
+    "check": "node --check bin/maw.mjs && node --check multi-agent-workbench/scripts/supervisor.mjs",
+    "pack:check": "npm pack --dry-run"
+  },
+  "engines": {"node": ">=20"},
+  "license": "MIT",
+  "repository": {"type": "git", "url": "https://github.com/ruhul0/multi-agent-workbench.git"},
+  "bugs": {"url": "https://github.com/ruhul0/multi-agent-workbench/issues"},
+  "homepage": "https://github.com/ruhul0/multi-agent-workbench#readme"
+}