dsh-smart-approval
Fail-closed LLM-assisted approval reviewer for DeepSeek Harness
32 results
Fail-closed LLM-assisted approval reviewer for DeepSeek Harness
Rule-gated automatic approval for DeepSeek Harness sandbox escalations with an optional LLM reviewer and native human fallback.
MCP bridge: lets ChatGPT Web create, view, continue and control DeepSeek Harness (DSH) agent sessions through the official MCP protocol. The bridge only connects; DSH keeps its session, agent, tool, approval and workspace security model.
Ponytail, lazy senior dev mode, for DeepSeek Harness: 6 skills (ponytail, ponytail-audit, ponytail-debt, ponytail-gain, ponytail-help, ponytail-review) adapted from DietrichGebert/ponytail (MIT)
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
Model-reviewed Auto Approve permission preset for the DeepSeek Harness Web UI
Fully customizable keyboard shortcuts for the DeepSeek Harness WebUI — macOS-first defaults, 34 pre-registered features across session/view/clipboard/model/permission/system groups, one-click recording to add your own bindings, silent permission cycling with color feedback.
Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.
DSH Auto Mode — pre-execution rule interception + delivery-time independent subagent security review. The native auto-mode for long-running agents in DeepSeek Harness (Codex/Claude Code auto mode 的 DSH 原生实现).
Independent Codex Guardian-style approval reviewer for DSH.
DSH AI 代码安全审查插件:secure_scan/secure_diff/secure_fix_verify/secure_report/secure_export/secure_baseline/secure_deps/secure_policy_show/secure_policy_set 九工具,40+ 确定性规则、密钥熵检测、git diff/staged 审查、SARIF 导出、基线接受与 SBOM-lite,零运行时依赖。
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
AI代码审查:找出代码中的bug、安全漏洞、性能问题和风格建议
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
A DeepSeek Harness (dsh) bundle that turns code review into a hard gate: deterministic severity rules, LLM-assisted findings, team approval quorum and a compliance audit trail.
Portable DSH WebUI skill security inspection with local rules and optional model review
Structured code review skill for DeepSeek Harness -- bugs, security, performance, style
Codex-style Guardian reviews, audit, and manual override for DeepSeek Harness
DSH web plugin: play a notification chime when the agent asks the user a question (ask_user_question / plan review) or requests approval (sandbox escalation, tool approval).
DeepSeek Harness bundle that routes real sandbox escalation prompts through a dedicated approval reviewer
Tiered auto-review for DeepSeek Harness (DSH): static-rule safety net + LLM reviewer + human fallback. Auto-approve safe actions, auto-deny irreversible ones, ask a human for the rest. PURE VIBE CODING - not audited, use at your own risk.
Sessionless LLM sandbox approval reviewer for DeepSeek Harness.
Fifth DeepSeek Harness mode with configurable Codex, Claude Code, or DSH audits, user-approved remediation turns, progressive Cordis/skill elevation, safety pauses, and Web/TUI review controls.
Native Auto Review for DeepSeek Harness with automatic host compatibility selection