プラグイン

DeepSeek Harness 向けの証拠優先型脆弱性リサーチワークベンチ：ネイティブ監査ビュー、29 の OMV ツール、Evidence.v1 の検出事項、再現可能な実行、Campaign ワークフロー、隔離された PoC 証拠。

エビデンス優先の運用キット: 6 個の読み取り専用ツール（機能カタログ、段階的ワークフロー計画、パッケージ化された Skill リーダー、範囲限定のローカルメモリ検索、リポジトリリリース監査、リリースチェックリスト）と 5 個のパッケージ化された Skill——計画と監査のみで、リモートへの書き込みは一切行わない。

Codex、Claude Code、WorkBuddy、CodeBuddyのメタデータ向け、制限付き・プライバシー安全なローカルスキャナー：キー付きエビデンスをアトミックに集約し、組み込みDSH presetと任意の機能を決定論的に提案 — コンテンツ保持・ネットワークアクセス・preset変更なし。

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in report files at the workspace root.

DSH self-discipline companion with recurring tasks, a gaze-tracking desktop mascot, evidence logs, final AI review, reminders, and window intervention on Windows and GNOME Wayland.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

Cordis-native, evidence-driven full-stack engineering workflow: inspect-first planning, explicit verification evidence, and approval-aware gating for sensitive operations.

21 read-only lifecycle governance tools in one self-contained DSH plugin: task tiering, state/plan/evidence validation, gate precheck and aggregation, release/install audits, context and progress analysis, critical path, resume reconciliation, and a mutation preview that always denies execution. Installs from npm as @240xu/dsh-tech-lead.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in two fixed report files at the workspace root.

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

Cross-session experience memory for DSH. Lessons are evidence-graded, injected when the turn is about the same thing, and shown just before an action only when the record declares which call it applies to. A rule that holds whatever the turn is about — "always answer in Chinese" — can be marked **standing** and is then carried every turn: measured on 24 isolated real-model turns, a standing rule is followed 6/6 against 0/18 for the controls (empty store, same record unmarked, unrelated standing record). A guess still cannot become always-on: a standing record needs a verified passage like any other. What nobody looks up is retired, reversibly. Five tools, seven slash commands, zero runtime dependencies.

Read-only DSH/Cordis composition doctor for plugin conflicts and upgrade rehearsal: scan profile manifests and patches, find duplicate rows, hook-order and UI ownership conflicts, compare redacted snapshots, diff plugin/row/hook changes, and preflight target DSH releases with explicit evidence boundaries — without mutating a real profile.

Evidence-governed experience memory for DeepSeek Harness

Combines fault knowledge-base symptom-to-cause rules with similar past cases to rank candidate motor diagnoses with evidence terms and suggested extra tests.

Summarises the case evidence, diagnosis, repair procedure, parts list and cost-option comparison for a motor into a Markdown repair recommendation report with data provenance.

Pre-install static audits for npm-installable DSH plugins; emits and validates the open `dsh-vet/v1` report with severity, confidence, evidence, derived grades, a CI Action, and auditable badges.

Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

Evidence-first GitHub research subagent with bounded tools and in-memory request caching.

An approval-gated OME engineering delivery preset with session-isolated lifecycle evidence.

Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Slash commands ported from other coding agents (setup, connect, install, trust, browse, doctor, status, model, memory, compact, resume, review, mcp, init, suggest, improve, refactor), a zero-dependency static scanner for plugin source, and an in-repo catalog of audited plugin report cards that cite file-and-line evidence.

21 read-only lifecycle governance tools in one self-contained DSH plugin: task tiering, state/plan/evidence validation, gate precheck and aggregation, release/install audits, context and progress analysis, critical path, resume reconciliation, and a mutation preview that always denies execution. Installs from npm as @240xu/dsh-tech-lead.