dsh-agent-conductor

dsh plugin --profile web add dsh-agent-conductor

<div align="center">

<img src="docs/social-preview.png" alt="dsh-agent-conductor — in-session cross-agent dispatch for DeepSeek Harness" width="100%">

⚡ dsh-agent-conductor

Let your DeepSeek Harness agent dispatch tasks to 11 external agent CLIs — Codex, Claude Code, TraeCode, OpenCode, Gemini, Cursor, Kimi, Qwen, Copilot, WorkBuddy, Grok — headlessly, and bring results back into the conversation.






English · [简体中文](docs/lang/README_ZH.md)

</div>

---

DeepSeek Harness is a great reasoning engine — but sometimes the job is better done by another coding agent: a Codex translation, a Claude Code investigation, a Cursor refactor. This plugin lets your DSH agent recognize when to delegate (by skill-description matching), dispatch a self-contained task to one of 11 external agent CLIs in headless mode, and bring the stdout result back as the answer.

Inspired by Multica — the "agent squad" idea as a zero-install DSH skill.

🎯 When to use Conductor

• Independent second opinion: ask Codex, Claude Code, or Gemini to review the same design and compare their reasoning.
• Legacy-code investigation: have one agent trace a call chain while another checks risks, regressions, and migration options.
• Cross-model implementation: use an agent whose toolchain or model fits the job, then bring its result back to DSH.

✨ What you get

Capability · What it does · Cost

🧠 Auto-triggered dispatch · Say "have Codex translate this README" — the model matches the skill, runs the dispatch script, and answers from the result · Free (uses the target CLI's quota)

🔧 conductor_dispatch tool (optional bundle) · The same registry as a first-class DSH tool, installed into a profile with one command · Free

🩺 doctor self-check · python3 dispatch.py doctor probes which CLIs are installed (resolves PATH + tries --version) before you dispatch · Free

👀 Dry-run preview · Preview the target, working directory, argv, and shell-equivalent command without starting an external agent · Free

👥 11 agent CLIs · Codex, Claude Code, TraeCode, OpenCode, Gemini, Cursor, Kimi, Qwen, Copilot, WorkBuddy, Grok · Their login quotas

🔒 Privacy · Task text goes only to the CLI's own provider; keys stay local · —

🧭 Why a Skill (and not just a plugin)

· profile plugin / bundle · dynamic plugin · Skill (this repo)

Install · write profile + restart · define in-session · copy a folder

Trigger · manual · model calls a tool · description matching, model auto-recognizes

Risk · touches the host · session-scoped, gone on restart · read-only script, host-agnostic

Result · tool result · tool result · stdout directly becomes the answer

One SKILL.md + a zero-dependency dispatch.py (Python stdlib only).

⚡ Quick start (Skill)

Copy skills/conductor/ to any skill root (project-level .dsh/skills/ or global ~/.dsh/skills/):

mkdir -p .dsh/skills/conductor
cp -R skills/conductor/. .dsh/skills/conductor/

No restart needed — from the next message on, just say:

• "派 codex 把这份 README 翻译成繁体中文" (have Codex translate this README)
• "让 Claude Code 查一下这个报错的成因" (ask Claude Code to investigate this error)
• "用 Codex 独立实现一个 XXX" (have Codex implement XXX independently)

The agent auto-recognizes the need (SKILL.md description matching) → runs dispatch.py → returns the result.

Before an unfamiliar or potentially write-producing dispatch, preview it without consuming the target agent's quota:

python3 skills/conductor/scripts/dispatch.py --dry-run claude-code "Read src/auth.ts and explain the token refresh flow. Do not edit files."

🧭 Agent capability matrix

Task · First choices · Why

Architecture review / second opinion · Codex, Claude Code, Gemini · Different reasoning styles are useful for catching design blind spots

Legacy-code call-chain investigation · Claude Code, Codex, Copilot · Good for tracing repository-local dependencies and attaching evidence

GitHub-centric issue or Actions analysis · Copilot, Codex · Natural fit for repositories, pull requests, and CI diagnostics

Editor-coupled refactor · Cursor, Codex · Useful when the workflow is tightly connected to an existing project tree

Chinese localization / Chinese docs · TraeCode, Qwen, Kimi, Codex · Strong Chinese-language options; keep terminology consistent in the task

Fast alternative implementation · OpenCode, Qwen, Kimi · Useful for bounded spikes where a separate login/toolchain is available

The matrix is a routing starting point, not a hard rule. Prefer an installed, logged-in CLI that has access to the correct workspace.

📋 Copy-ready dispatch recipes

1. Safe diagnosis:

You are investigating a bug in the current repository. Do not edit files.
Reproduce the issue from this description: <paste error and steps>.
Read only the minimum relevant files. Return:
1) root cause, 2) evidence with file:line, 3) three ranked fix options,
4) tests that should be added or updated.

2. Independent architecture review:

Review this design as an outside staff engineer. Do not assume hidden context.
Design summary: <paste PRD/technical plan>.
Challenge scalability, failure modes, security boundaries, and migration risk.
Return disagreements first; for each, include impact, evidence, and a fal

…(truncated)