プラグイン

自動承認レビュー：読み取り専用ツールを自動承認し、危険なコマンドを自動拒否するフェイルクローズドなポリシーエンジン。

北京才知科技（深知可信智能）による政府/企業向けの信頼できるオフィススイート：3 つのスキル——信頼相談（引用マーカー + 由来 HTML 付きの政策/法規 Q&A）、信頼検索（追跡可能 HTML + クリーン Markdown による権威ある政策/標準の検索）、公文書作成（起草/書き換え/Word/紅頭文件納品）。全インターフェースは dknowc 信頼ワークベンチ MCP（Bearer 認証）経由、成果物はセッションワークスペースに保存、キー設定は一度で以後のセッションに永続。npm では dknowc-dsh として配布。

コンポーザーのコストチップ：公式の価格表（2026-08-17 のピーク/オフピークポリシーを含む）を用いて、現在のセッションの DeepSeek API 支出をメッセージ単位で価格計算します。ホバーで内訳、本日（DSH）の合計、アカウント残高を表示。DeepSeek モデルのみ。

エージェント型 AI 向けの権限レイヤーを DeepSeek Harness プラグインとして提供します。TapPass の /v1/govern ポリシー判定エンドポイントを通じて、すべてのツール呼び出しをビジネスルールに照らして統制します。

危険な操作へのポリシーチェック、出力の秘匿化、セキュリティレビューのワークフローを追加します。

Session-aware mesh relay for DSH agents: an Ed25519-signed receive route and delivery policy, plus outbound sending, a peer directory and a mesh-peer-registry client.

dsh plugin: unattended approval gate — subagent/scheduled/cron approval requests get a bounded answer window, then settle with a fail-closed default instead of hanging forever (per origin or per session)

Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.

Windows desktop control through UI Automation: nine tools that read a window control tree and drive elements by id through their own UI Automation patterns, with every write gated by an approval policy, an append-only action log and a settings panel.

Adds DSH restart and stop controls with token-aware reconnect and policy-based recovery for interrupted web sessions.

Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.

Preventive content policy for DeepSeek Harness tool results: rewrite matched text with regex rules, or drop/truncate unpredictable payloads by field path before they are normalised, rendered, or persisted. The upstream counterpart to dsh-plugin-redact.

DeepSeek Harness plugin bundle: grill_tree, a fixed-policy design-space search tool. Expands one decision per node, fans out independent proposers, has a separate judge prune the branches, beam-limits each depth, and ends with complete designs or an infea

Enforces your comment policy at write time, inside DeepSeek Harness. Reads the policy from your AGENTS.md or CLAUDE.md, blocks violating writes, and re-injects the policy verbatim so the model stops drifting from it.

Preventive content policy for tool results: rewrites matched text, and drops or truncates whole fields by path before a result is normalised, rendered or persisted, so an unreviewed payload never enters it. Ships inert with no built-in category or domain blocklist.

DSH plugin security guard: 28-rule static scanner, risk scoring, whitelist/blacklist policy, local web dashboard and in-DSH risk popups.

Zero-config per-turn git checkpoints: after every completed agent turn in a git workspace, stages all changes into one tagged \[turnsnap] commit (serialized queue, sandbox-policy aware), so any turn is a rollback point.

dsh plugin: bounded retry for gateway network_error failures the stock retry policy cannot classify (e.g. OpenCode Zen finish_reason: network_error)

DeepSeek Harness plugin: a deployment deny list of filesystem roots the model may never touch - fences read, write, search, and shell tool calls at tools/pre-execute

DeepSeek Harness plugin for Readproof: stable readproof:// identity, freshness policy, snapshots, per-run manifests, diff, byte-exact replay, and evidence bundles as model-callable tools.

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

Host-anchored provider, authentication, catalog, policy, and model-selection extension for DeepSeek Harness.

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Egress policy for DeepSeek Harness: a host allowlist on web_fetch and web_search enforced at connect time, audit-mode by default, with OCSF Network Activity records