dsh-codex-approval
Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.
62 results
Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.
DSH 规则执行引擎 v3:容器解析 AGENTS.md + 理解器 + 匹配机 + 执行框架
Per-provider & per-model rate limiting (token bucket, reject/queue modes) plus gateway identity rules for DeepSeek Harness
Long-term memory for DeepSeek Harness agents: automatic recall each turn, a retain/recall/reflect tool, standing rules, and visibility you scope to the whole bank, a preset, or a session.
Portable DSH WebUI skill security inspection with local rules and optional model review
DSH web plugin: Cursor-like Settings pages (AGENTS.md Rules, Skills, MCP servers, import) plus a pinned 'latest input' chat bar with a backward walk
Lazy senior dev mode for DeepSeek Harness: always-on minimal-code ruleset, intensity switching, and short review/audit/debt/gain/help skills
Claude Code-style `paths:` rule injection for DeepSeek Harness (DSH): inject rules from ~/.dsh/rules, <project>/.dsh/rules and <project>/.claude/rules into the model context.
统一管理 DSH 规则:编辑全局规则 ~/.dsh/AGENTS.md、编辑项目 AGENTS.md、LLM 自动拆分项目规则为分层 AGENTS.md + skills。合并自 dsh-global-rules 与 dsh-rule-splitter。
DSH plugin development boundary skill: platform capability boundaries (Client↔Host channels, filesystem limits, dynamic vs bundle lifecycle, install/debug rules)
A public DeepSeek Harness preset for main-brain orchestration, execution gating, and reusable AI-LAW rules.
让 DeepSeek Harness 打开工作区时自动载入 Claude Code 配置:Skills/Rules/Hooks/Agents 四样资产,固定双位置(工作区自身 .claude + ~/.claude)运行时直读、零写入。Claude Code 兼容层。
DSH adapter for everything-wp — WordPress plugin dev AI toolkit. Phase 3: 18 commands + 5 agents with mode gating and inline rules.
Installation safety gate & data-protection guard for DeepSeek Harness: 60 static signature rules (31 high/24 medium/5 low) scan plugin sources for malicious install scripts, credential theft, obfuscation, persistence and network callbacks before 'dsh plugin add', plus 12 destructive-command patterns and workspace-boundary checks against accidental deletion. | 安装安全闸门与数据保护闸:60 条静态签名规则(31 高危/24 中危/5 低危)扫描插件恶意行为、持久化与外传,12 种危险命令模式与边界检查拦截误删。
Academic mode for DeepSeek Harness (dsh): a research persona, anti-fabrication rules for citations and data, and bilingual conventions. Pairs with dsh-ai4scholar (literature tools) and dsh-research (research skills).
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
DSH plugin to manage rule files (one .md per rule) at global and project scope, with a settings-page UI (Host webServer HTTP routes + Client settings section).
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.
The authority layer for agentic AI, as a DeepSeek Harness plugin. Governs every tool call against your business rules via the TapPass /v1/govern policy decision point.
Configurable near-field trigger that reminds a DeepSeek Harness agent to load the J-Space Cognition Suite only when rules say it is worth it
Ponytail for DSH — the lazy senior dev. Live intensity switching (off/lite/full/ultra) with a toggle in the composer, injecting a minimal-code ruleset before every step to cut token usage.
DSH plugin: model reasoning levels plus CLI request mimic, with a unified Daily Optimization settings section.
Global and workspace rules for DeepSeek Harness agents: configurable storage paths, system-prompt injection and a rules_read model tool.
The pet that grows with your DeepSeek Harness agent: stage evolution from real signals (verified rules, sessions, tool calls), agent-state mirroring, and one-click growth share cards.