ai-safety

dsh-auto-review

PerryLink

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

dsh-permission-rules

PerryLink

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

dsh-agentfuse-plugin

MkaliezZ

Deterministic fail-closed tool-call authorization for DSH with evidence: allow/block/ask policy gate plus approval-chain deferral.

dsh-plan-lattice

1052326311

Execution-time drift firewall for long-running DeepSeek Harness agents. Real-Harness tests: unsafe stale mutations 12/12 native -> 0/12; valid controls 7/7 both; post-SIGKILL unsafe continuation 2/2 -> 0/2.

deepseek-forge

ophielel

DeepSeek Harness 开发锻造工坊：审批守卫、开发 Skills、GitHub/浏览器能力与 Token Watch 消耗监督，装上就能干活。

solidforge-dsh

maskshell

让测试绿了不等于你做对了 — 双轴收敛纪律 (spec-gaming orthogonal axis) 的 DeepSeek Harness 原生实现 | Two-axis convergence discipline for coding agents