mike-sl-ig

Dsh Agent Bridge — Testing skill for Claude Code

Testing community

Data-driven agent bridge plugin for DeepSeek Harness: JSON recipes, cross-platform launcher, recipe wizard, self-test, registry import.

How to install Dsh Agent Bridge

This entry records only its repository, not the path inside it, so there is no exact command to give. Open mike-sl-ig/dsh-agent-bridge and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Dsh Agent Bridge does

Data-driven agent bridge plugin for DeepSeek Harness: JSON recipes, cross-platform launcher, recipe wizard, self-test, registry import.

Alternatives in Testing

Claude Codepro — by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcemen 1.6k ★
N9e Config Driven E2e — Maintain config-driven Nightingale E2E tests that convert JSON config data into UI-readable normalized values 301 ★
Symfony Fixtures — Create test fixtures using Foundry factories for realistic test data 206 ★

README

dsh-agent-bridge

**English** | [简体中文](README.zh-CN.md)

[![CI](https://github.com/mike-sl-ig/dsh-agent-bridge/actions/workflows/ci.yml/badge.svg)](https://github.com/mike-sl-ig/dsh-agent-bridge/actions/workflows/ci.yml) [![npm version](https://img.shields.io/npm/v/dsh-agent-bridge.svg)](https://www.npmjs.com/package/dsh-agent-bridge) [![npm downloads](https://img.shields.io/npm/dm/dsh-agent-bridge.svg)](https://www.npmjs.com/package/dsh-agent-bridge) [![license](https://img.shields.io/npm/l/dsh-agent-bridge.svg)](LICENSE) [![node](https://img.shields.io/node/v/dsh-agent-bridge.svg)](package.json) [![dependencies](https://img.shields.io/badge/dependencies-0-brightgreen.svg)](package.json)

Bridge **DeepSeek Harness** to whatever coding-agent CLI your machine already has — OpenCode, Claude Code, Codex, Gemini, or anything you write a recipe for — and use it as an independent worker for cross-model verification, cheap bulk work, or a second opinion.

The plugin never hard-codes a vendor. An agent is described by a **JSON recipe**, so adding one — or fixing one whose CLI changed its flags — is a data change, not a code change. Recipes are data on purpose: that is what makes it safe to fetch them from a community registry later.

What it gives you

A button in the session header. Pick the default agent, enable any of the three role features, choose a model, and see what the last run did.
Three tools the model can call:
- agent_list — which agents were found, where, what they cost, what they support (probe: true also runs --version).
- agent_run — run one agent as an independent worker; returns the answer, session id, timing, tool calls and the path of a run report.
- agent_mode — read/change the state the button shows.
A report per run: a Markdown file (prompt, answer, tool calls, tokens, cost, raw log paths) plus last-run.json for the panel.