130 results
并行多角色代码评审小队：/review 一条命令派出安全/正确性/测试/风格四名只读评审员子代理（每人可单独指定模型与思考强度），汇总为按严重度分组的结构化报告。Parallel multi-role code review squad: /review dispatches security/correctness/tests/style reviewer subagents (each on its own model) and aggregates one severity-grouped report.
DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.
DeepSeek Harness plugin to audit and correct llm-pi-ai model capability declarations by probing the endpoint itself: out-of-range maxTokens, contextWindow, reasoning levels, image input.
Lock, verify and govern AI agent skills: a DSH plugin that makes the agent check what a skill can do before installing or updating it, and notice when it changes.
判定 Python 代码是原创还是演绎作品：给出与上游最长相同表达片段、逐条豁免依据和风险清单。纯本地 AST 分析，零依赖、不联网、不调模型。
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.
DSH security audit mode: threat modeling, vulnerability scanning, and triage pipeline with Web visualization.
Three-mode visible-session advisor plugin for DeepSeek Harness with configurable tool permissions, local-subagent coverage, and task-tree budgets.
DeepSeek Harness security bundle: auto-audits newly installed plugins with the harness's own model (settings panel + batch tools), and ships the Security-Audit-Mode agent preset with the OpenAI Codex Security workflow skills and dsh_security_* scan tools. One package, one `dsh plugin add`.
Strict check: verify code and commands against real checkers instead of reading them — Lean 4 kernel checking with an axiom audit, language type/syntax checks, and static defect rules.