プラグイン

Policy-driven Git sync for DSH settings and profile configuration, with secret-aware projections, conflict review, and per-line apply controls.

Registers a SpecWorkflow skill pack for requirement clarification, implementation specs, execution, delivery review, repair planning, bug diagnosis, and source-backed research.

Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs and comments (dead design citations, PR vantage, change narration, review choreography), shipping the cot-trim fixing skill as the installable bundle.

DSH bundle porting Matt Pocock's 25 promoted engineering and productivity agent skills (grilling, TDD, code review, domain modeling, etc.).

Spec-driven development discipline for dsh: five keel skills (anchor/spec/probe/build/audit), three review tools and six spec templates enforce specs-before-code, assumption verification and scope control.

Bundles an engineering-methodology skill library as one Cordis plugin: 14 Agent Skills (planning, testing, debugging, review, delivery) registered on ctx.skills for DeepSeek Harness.

Document workshop skill pack: four pure-prompt Agent Skills that turn a codebase into READMEs, PR descriptions, changelogs and code reviews, installed into dsh via a dsh.bundle plugin row.

OMX-style workflow skills for DeepSeek Harness: deep-interview, ralplan, ralph, autopilot, team, code-review and 19 more, rewritten on native DSH tools, without vision skills.

Publish an HTML document as a shareable link that opens in one tap and previews as a card in chat apps; publish, update, and export to PNG/PDF/Word.

Headless-browser verification tools so the agent opens the page it just built, reads the rendered DOM and computed styles, checks the console, and screenshots the result; ships a frontend-verify skill.

Preview conversation file links in the web UI (images / text / Markdown / highlighted code / git diff) — click a link to open a preview modal instead of the desktop opener; loopback-fenced routes with weak ETag/304 caching and DOMPurify sanitization.

Ecommerce operator workbench: CSV batch preview with marketplace column adapters, reproducible profit/six-dimension scoring, public product-page snapshots, Chinese skills, and a replaceable store-policy KB.

Reuse-first capability evolution for agents: resolve existing tools and skills, discover and review exact-commit DSH plugins, install with one-time approval, verify real tool round trips, and minimally adapt partial matches instead of rebuilding from scratch.

Headless Claude Code consultations with advisor, reviewer, and designer roles, returned as reference answers.

PostgreSQL-backed durable memory for DSH agents: MCP memory tools plus a Web panel for reviewing memories and candidates.

Session manager for the DSH Web UI: browse all and archived sessions, restore/unarchive, delete with two-step confirmation, and preview conversation content from the Settings panel.

Export complete Web Sessions to local Markdown or self-contained HTML, with stable rendered previews, default redaction, and opt-in bounded tool-call details.

Track human decisions for related DSH session branches: keep, discard, or follow up with reasons, labels, and external links.

Archived conversations list in the sidebar footer with read-only previews of the most recent messages, for sessions the product deliberately keeps hidden and unreopenable.

Floating workspace file-preview window for the Web client: lazy file tree, CodeMirror preview and in-window edit with save, Markdown and image preview, Quick Open search, and opening paths clicked in the conversation.

Client-only right-edge chat input index rail: one bar per user message, two-stage hover preview (15 chars, expandable to 40), click-to-jump, and scroll-follow highlight; static npm bundle with no host half.

DeepSeek Harness 向けの、会話形式による UI/UX ビジュアルレビュープラグイン。vision_review / vision_ask ツールは、任意の OpenAI 互換マルチモーダルエンドポイント(例: agnes-2.5-flash)を利用します。

DeepSeek Harness(DSH)向けの、読み取り専用の神経科学データプレビュープラグイン。

ローカル AI によるコードレビューゲート。管理された ocr.js を通じてワークスペース/ブランチ/コミットの差分をレビューし、トークン統計付きの構造化された指摘結果を返します。ゲートモードでは指摘があると失敗として扱われます。