DeepSeek Harness Plugin: dsh-llm-codex
`dsh-llm-codex` is a DeepSeek Harness plugin that integrates by mounting and registers Codex CLI as an LLM provider. It supports locally prioritized Codex invocation (reusing the existing login state) and falls back to OpenAI-compatible endpoints, exposing Codex as a text-generation route rather than an agent. The plugin reads the model list from the Codex cache and supports sandbox mode for permission control. It is enabled by configuring a mount after installation and is suitable for scenarios that require using Codex capabilities within DSH, although the limitations of macOS and nested sandbox environments should be noted.
Read Moredsh-native-codex-cli — Driving Codex CLI Directly via DSH's Chat Interface
The DSH Native Codex CLI plugin enables a direct connection between DeepSeek Harness (DSH) and Codex CLI, with DSH serving only as the presentation layer and Codex handling task execution. The plugin supports opening existing conversations, creating new tasks, streaming output, and displaying tools. Messages are sent directly to Codex’s native `turn` without intermediate forwarding, reducing latency and avoiding the overhead of a secondary AI. Developers can drive Codex CLI in DSH through bound or standalone workspaces. The plugin is open-sourced under the MIT License.
Read Moredsh-codex: DeepSeek Harness Plugin for OpenAI Codex CLI
`dsh-codex` is a plugin that integrates the OpenAI Codex CLI with the DeepSeek Harness (DSH), allowing developers to run Codex using local configurations (such as DeepSeek) without an OpenAI login. Installation requires DSH to be installed and Codex CLI to be installed globally. It can be enabled via a local patch or by adding it to a profile. The plugin provides four native tools: `codex_status`, `codex_exec`, `codex_review`, and `codex_resume`, supporting status checks, one-off task execution, code review, and session resumption. It adopts a read-only sandbox mode by default and masks provider configurations to protect privacy. Be mindful of the tok for data transmission.
Read Moredsh-codex-bridge: A bidirectional plugin to integrate Codex CLI with DeepSeek Harness
**Introduction** When developing agents using DeepSeek Harness (dsh), you may encounter requirements such as having the agent in the conversation find an external coding agent—such as OpenAI's Codex—for a second opinion, or running a coding task in parallel. Manually handling this involves spawning a `codex` process, capturing JSONL output, polling for status, and then ingesting the results back into the conversation. This scaffold code is unrelated to the main task yet must be written from scratch every time. `dsh-codex-bridge` is designed to solve this problem. DSH's philosophy is "everything is a plugin," where capabilities are integrated into the harness as plugins. This project is a concrete implementation of that concept. Below, I introduce what it is and how to use it.
Read Moredsh-subagent-codex: Delegating tasks to local Codex CLI in DeepSeek Harness
# Introduction The philosophy of DSH is "everything is a plugin," allowing the main agent to delegate tasks to sub-agents via a subagent mechanism. However, standard subagents run within DSH and share the same environment as the main conversation. If you want to delegate a specific task to OpenAI Codex—using Codex's own model and tool chain within an isolated process—you must manually switch terminals, execute commands, and paste the results back into the session, which is a disjointed workflow. dsh-subagent-codex fills this gap. The following sections introduce its positioning, implementation, and usage. # What is this dsh-subagent-codex (current version 0.1.1) is maintained by mjylfz and uses MI...
Read More# Sentry Skill: Integrating Production Error Troubleshooting into AI Agent Workflows
Sentry is an Agent Skill maintained by OpenAI in the curated directory of the openai/skills repository, which enables read-only observability queries via the official Sentry CLI: listing unresolved issues, viewing event details, and calling issue explain/plan to generate root cause analysis and repair suggestions. This article introduces its positioning, core commands, installation methods for both the CLI and the Skill (Codex's $skill-installer and Cursor's .cursor/skills), as well as precautions including the default 24-hour production environment query scope, JSON output format and security desensitization, which is suitable for DevOps/SRE to integrate online troubleshooting into AI workflows.
Read More