Bundle
dsh-managed-approval
Codex-inspired managed approval for DeepSeek Harness: risk-based MCP review, one-time grants, explicit denials, and human fallback on reviewer failure.
jalllychun
Browse
5 results
Bundle
dsh-permission-matrix
Permission matrix for DeepSeek Harness: 3 sandbox modes x 4 approval strategies = 9 selectable presets, with a global default, a separate LLM-robot default, four-tier risk policies, password-gated approval for high-risk operations, audit log and git checkpoint.
zhang8019
Bundle
@lytharalab/dsh-cons-auto-review
Con's 自动审查（DCAR）：确定性规则优先、LLM 按需升级的 DeepSeek Harness 工具审查插件，提供 CAutoR 权限模式。Deterministic-first auto review for DeepSeek Harness.
LytharaLab
Bundle
dsh-danger-reflection
Danger Reflection (危险反思): a DeepSeek Harness permission preset that replaces the human approval prompt for sandbox escalation with a same-model review that replays the whole conversation.
XIMOYA
Bundle
@lone-wolf-akela/dsh-sandboxie-redirect
DSH bundle adding a copy-on-write permission preset: shell commands run inside a per-workspace Sandboxie box, so writes outside the workspace land in the box's copy while the real disk is untouched.
lone-wolf-akela