Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Qwen Lane

ASecurity

Orchestrate named, messageable local or remote Qwen Code worker lanes from Claude Code. Use for Qwen delegation, reviews, comparisons, follow-ups, and federated Qwen targets.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsrustbash

Works with

claude codeterminalmcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add antst/sessionbus-peers --skill qwen-lane --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Qwen Lane?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Qwen Lane
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/antst-qwen-lane/badge)](https://www.skillsdirectory.com/skills/antst-qwen-lane)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: qwen-lane
description: Orchestrate named, messageable local or remote Qwen Code worker lanes from Claude Code. Use for Qwen delegation, reviews, comparisons, follow-ups, and federated Qwen targets.
---

# Orchestrate Qwen lanes

Use the process-attested `sessionbus.lane` MCP tool with `product: "qwen"`.
The daemon owns a durable native Qwen transcript and exposes it as a Sessionbus peer. Qwen remains the authority for its approval mode. Do not execute
`qwen-peer-lane` through Bash.

Call `doctor` with arguments `["--json"]` and `list` with `["--all"]` first. Require
contract version 2 and `ready: true`; do not launch when version, ACP, archive,
trusted-cwd, profile, integration, or non-secret credential configuration evidence
is missing. Readiness is session-free and does not prove a live provider login.

For another host set `host` on the same structured lane calls after
confirming `qwen-lane` capability. Never use SSH or silently fall back locally.
Federation owns lifecycle, so omit `--persistent` and
`--no-auto-archive` remotely.

```json
{
  "product": "qwen",
  "command": "start",
  "arguments": ["--name", "qwen-review", "--no-yolo", "--auto-archive-after", "300", "-"],
  "input": "<briefing text>"
}
```

Never put a briefing on argv. `start` returns `lane.ready`, not the answer. Use one
collector, then select the final agent message matching the last `turn.completed`.
A timeout exits 124 without cancelling. Execute a delivered
`QWEN_LANE_TERMINAL` structured collection hint through `sessionbus.lane`, preserving
its product, command, lane identity, host, and timeout arguments. The notice
itself is not an answer.

Use `--yolo` only with explicit authority, `--no-yolo` for native initial
`default`, or a supported `--approval-mode MODE`. Qwen may change mode natively
after launch; status reports the last corroborated mode or `unknown`.

The lane is messageable through the `sessionbus` skill. Messages serialize as
collectable turns. Collect debt before follow-up:

Call `resume` with arguments `["qwen-review", "--timeout", "600", "-"]`
and the follow-up as `input`. Call `interrupt` and `archive` with
`["qwen-review"]`.

Resume preserves the exact native Qwen UUID. Interrupt returns 130. Archive is
idempotent and retires manager, worker, tool roots, helper, sockets, and grouped
publication. Default lanes belong to this exact Claude parent; persistent lanes
survive parent exit but retain the normal 60-second terminal auto-archive grace.
Pair `--persistent` with `--no-auto-archive` only for indefinite idle retention,
then archive explicitly. Use `--inherit-groups` only deliberately and repeat
`--group NAME` for child-specific groups.

Attribution

antstantst
View sourceMore from antst →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →