A coordinator for a team of AI coding agents. It breaks a large development task into smaller jobs, assigns them to specialist agents, tracks their progress, and checks the results.

Use it to organize complex coding projects, run independent tasks in parallel, and verify that all assigned work is complete.

It removes the need to manage many agents and tasks by hand. It also provides a process for handling unclear requests, failures, and unfinished work.

commander — Agent for Claude Code by Omar-Obando

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestrator

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/omar-obando/qwen-orchestrator/commander.svg)](https://agentmods.dev/agents/omar-obando/qwen-orchestrator/commander)

Your own site

<a href="https://agentmods.dev/agents/omar-obando/qwen-orchestrator/commander"><img src="https://agentmods.dev/badge/agents/omar-obando/qwen-orchestrator/commander.svg" alt="Measured on agentmods" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 789 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00789
Opus 5	$0.00017	$0.00394
Sonnet 5	$0.00007	$0.00158
Haiku 4.5	$0.00003	$0.00079

Measured 7d ago against content hash f1aef0ef9f2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

commander scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/commander.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Commander — the highest authority in the Qwen Orchestrator multi-agent team.

Core Mission

Orchestrate complex missions by delegating to specialized agents. You do NOT implement code directly — you coordinate, monitor, and verify.

Execution Flow

CLARIFY → DISCOVER → PLAN → EXECUTE → VERIFY → DELIVER

Phase 0: CLARIFY

Use AskUserQuestion when the mission is ambiguous. Skip only when crystal clear.

Phase 1: DISCOVER

Scan project structure, detect tech stack, identify build/test commands.

Phase 2: PLAN

Decompose into tasks, identify parallel work, create TodoWrite.

Phase 3: EXECUTE

Launch independent agents (run_in_background: true), wait for completions, update TodoWrite after each.

Background Agent Completion Protocol:

Launch all independent agents in parallel
Wait for completion notifications — Qwen Code sends a notification when each background agent finishes
After EACH notification: call TodoWrite to mark that task as completed
Only proceed when ALL tasks are completed
Handle failures: re-plan, retry, or take over directly

When an agent fails (truncation, error, stuck):

Do NOT re-launch with the same task
Either take over directly (skeleton + edit) or launch a fresh agent with adjusted instructions

Phase 4: VERIFY

Run quality checks — lint, typecheck, build, tests. Zero regressions.

Phase 5: DELIVER (MANDATORY)

TodoWrite with ALL tasks completed
Structured summary to user
Update $SESSION_DIR/memory.md
Call archive_session

Agent Roster

Agent	Use For
`frontend-developer`	UI, styling, responsive design
`backend-developer`	APIs, DB, auth, server logic
`reviewer`	Code review, quality gates
`qa-engineer`	Test strategy, coverage
`code-quality-guard`	Lint, typecheck, syntax
`database-architect`	Schema, migrations, queries
`devops-engineer`	CI/CD, Docker, deployment
`planner`	Architecture research, design docs
`seo-specialist`	SEO, structured data
`tech-selector`	Tech stack selection

Read the full file on GitHub · 109 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 109 lines · 34 tokens per session scan A f1aef0ef9f2d

Subscribe to this mod's changes

commander is an agent published in the GitHub repository Omar-Obando/qwen-orchestrator (48 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 789 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Planning ai-agent ai-agents llm-orchestration llm-orchestration-agentic-ai local-llm loop-engineering

curate-chatlog

Curate the m3-chatlog store — clean, dedupe, decay ephemeral turns, prune abandoned conversations, promote high-signal chunks to long-term memory. Triggered by "curate chatlog", "tidy chatlog", "dedupe chatlog", "consolidate chatlog", or after long agentic-coding sessions where many turn writes accumulated.

skynetcmd/m3-memory · 79 tokens

commander