Engineering workflow layer for DeepSeek Harness (dsh): a disciplined-engineer agent preset with five gated phases — requirements clarification, plan approval, TDD, parallel subagent execution, and verified finishing. Skills adapted from obra/superpowers.
DeepSeek Harness plugin that locks the web chat composer Enter-send. Toggle with a lock button or Ctrl+Shift+K to prevent accidental sends while typing or editing long prompts; unlock to send. IME-safe and per-session.
Workspace-scoped Python virtual environment management for a DeepSeek Harness project — discover, create, install into, and remove virtual environments without sandbox, network, or subprocess pitfalls.
Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. A jev_decide tool for DeepSeek Harness (dsh).
Remote development for DeepSeek Harness: pick a remote workspace over SSH and let the agent work on it with the same local tools. No extra model tools, no third-party UI plugin.
Real-time chain-of-thought trajectory profiling for DeepSeek Harness: live wording indicators, profile-family judgment, per-session measurement records
MCP server bridge for DeepSeek Harness: stdio / streamable-http / legacy-SSE transports, web settings UI (form + JSON), tools as mcp__<server>__<tool>. Burp Suite ready out of the box.