@bryan-cmf/dsh-infra-observability
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
71 results
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
Local, deterministic release risk checks for DeepSeek Harness.
DeepSeek Harness (dsh) plugin adapter for litkit — academic literature search, citation audit, and download tools. Root npm package of the polyglot litkit-search monorepo, so `dsh plugin add github:bpc-oss/litkit-search` installs the adapter directly.
Docker-container (WSL2 backend) shell executor for the DeepSeek Harness bash capability seam on Windows: every bash tool call runs in a disposable Linux container with the workspace bind-mounted.
此为 DSH 生态插件。Dolphin - 主动巡检型安全防御插件,支持本地扫描与远程 SSH 巡逻。将渗透测试方法论(信息收集→漏洞探测→利用验证→报告)转化为主动防御巡检流程:基于 Semgrep 的扫描层与基于 SSH 的执行层相融合,可对本地目录做静态扫描,也可将扫描命令经 SSH 下发至远程主机执行并回收结构化结果。
DeepSeek Harness 的 UI/UX 审查与优化闭环:无头 Chrome 取证 → 确定性判据(WCAG 2.2 / 平台指南)→ 可粘贴 CSS 修复 → 复测差值验证
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.
Audit a DeepSeek Harness session against the 14 consciousness indicator properties of Butlin, Long, Elmoznino, Bengio et al. (2023) and report an L1-L5 level
Always-on dependency and compatibility monitoring for DeepSeek Harness plugins, including exact paths, upstream changes, and isolated install/load evidence.
OS-isolated capability capsules for third-party DeepSeek Harness plugins
DSH plugin health scorecard: quality & security audit, rankings, search, score history and open-data export across the dsh-plugin ecosystem, with a workspace-persisted incrementally-synced catalog. 插件体检评分卡:质量/安全审计、榜单、搜索、历史评分曲线与开放数据导出(目录增量同步)。
Evidence-backed runtime nutrition labels for DeepSeek Harness plugins and tool namespaces
Runtime data-flow audit log for DeepSeek Harness: who mutated what, in what order — per-plugin, per-fiber attribution.
Static trust audit for DeepSeek Harness plugins: capabilities, injected prompts, token cost, provenance, and a reproducible 0-100 trust score
SuperPowers for the DeepSeek Harness: portable Superpowers skills, automatic bootstrap, and DSH-native Windows sandbox compatibility.
Audit a DSH profile for capabilities nothing consumes, and record completion claims with the evidence that supports them.
DSH security audit mode: threat modeling, vulnerability scanning, and triage pipeline with Web visualization.
Deterministic fact producers for security auditing: which deleted code came from a security fix, and which changed symbols no test ever executed.
Layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse
dsh-voredteam —— 单模式(网络安全模式)DSH 插件合集:黑板书 Fact/Intent/Hint 引擎 + 总控派发专业子 agent + 作战面板/设置 两个面板 + 唯一门禁(禁 DDoS/禁爆破/模糊测试低频)。
dsh plugin: shows the model name the upstream actually reported for each assistant step, backfilling pi-ai replay metadata from a non-invasive fetch observer when the adapter omits it
Patch-style file editing for DeepSeek Harness: one apply_patch tool accepting git/unified diff (default) and Codex apply_patch syntax (opt-in), with all-or-nothing application, read-before-write intent dance, sandbox-aware delete/move, and 0.1.2-rc.1 ~ 0.1.5-rc.2 compatibility.
DSH Cost Audit — per-turn and per-session token/CNY cost pills for the DeepSeek Harness Web GUI, including the compaction bill nothing else counts, plus a one-click advisor that re-measures whether its own advice actually saved money.