플러그인

text-only models를 위한 디자인 충실도 QA: `deepseek_vision` 도구가 어떤 OpenAI 호환 vision route에서든 한 쪽 눈을 빌려와 모델이 구현이 mock과 일치하는지 판단할 수 있게 하며, 그 판단 뒤에 있는 벤치마크(4개 fixture, 23개 주입 결함, raw transcripts)와 그것이 의존하는 질문 규율까지 함께 제공합니다.

dsh에 등록된 모델의 contextWindow를 구성하여, 긴 세션이 더 이상 컨텍스트 오버플로로 잘못 판단되지 않게 합니다.

OMK — 관찰. 측정. 파악. AI 애플리케이션을 위한 증거 기반 지식 변화.

로컬에서 분석된 시스템 오디오를 DSH Web의 음악 반응형 대화 효과, 리듬 게임 판정, 점수 및 콤보 피드백, 선택적 RGB 스펙트럼 바에 매핑합니다.

3계층 에이전트 메모리 하니스: 항상 활성화된 L1 CLAUDE.md, L2 인덱스, 템플릿이 있는 L3 상세 스켈레톤, 보호된 파일 쓰기를 1회성 승인 토큰 없이는 차단하는 게이트, 판단 없는 이벤트 로깅, 주간 증류, TDD 실행 루프 스킬.

분리된 Git worktree에서 3개 또는 5개의 코딩 에이전트 후보를 실행하고, 프로젝트 명령으로 패치를 검증하며, 통과한 후보만 순위 매기고 승격 전에 별도 승인을 요구합니다.

파인만 학습 모드 플러그인: 가르치기 → 되짚어 설명하기 → 평가 → 재설명의 루프를 리치 HTML 수업 카드로 렌더링(mermaid 다이어그램 + shiki 코드 하이라이팅)

Resumes an agent turn that ended after narrating its next action without calling a tool: the guard replays the turn log on agent/turn-stopping, asks a judge model one true/false question, and steers the same turn to run one more step.

독립적인 승인 서브에이전트가 모든 샌드박스 에스컬레이션을 판단하며, 구성 가능한 모델과 감사 로그를 갖추고 있습니다.

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log.

Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate

Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Destructive-command interception gate for dsh: parses shell semantics, judges risk against 41 built-in rules, and holds irreversible rm -rf, git reset --hard, and git push --force style commands at a confirmation gate.

DeepSeek Harness용 2단계 모델 라우터 — LLM-Judge 라우팅, 다중 모델 폴백 체인, 지수 백오프 장애 조치, 작업 단위 오케스트레이션(pi-shift-router의 DSH 이식판)

Cross-project experience recall for DeepSeek Harness: when the running work matches something your memory store already learned elsewhere, that lesson is injected before the next step. Runs fully locally, judged by a local small model.

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

DeepSeek Harness plugin for CVE impact retesting: fingerprint a target, judge it against a CVE's affected range, gather passive evidence, and report a verdict with confidence and limitations.

Resume screening plugin for HR in DeepSeek Harness: ingest up to 100k Word/PDF/Excel resumes into one searchable library with skills / coarse categories / ingest time, auto-ingest & de-dupe new resumes, then screen by plain-language criteria — rule pre-filter in the database plus LLM fine-judge on the shortlisted few, CSV export.

Shared toolkit for authoring DeepSeek Harness plugins, published as @perrylink/dsh-plugin-kit: a pluggable provider registry seam, fail-closed approval and session-event gates, shared sanitize/pricing/judge modules and a new-plugin skeleton.

Multi-role parallel argumentation for DeepSeek Harness: runs the real Codex and Claude CLIs in parallel, has the DSH model (Judge) write a third-party verdict back into the conversation, plus Obsidian-style single-agent direct chat and per-role model config.

DeepSeek Harness 插件：生成前注入「人味」风格约束 + AI 味检测报告（纯代码、零 token、结果可复现）。dsh plugin: human-flavor style injection + AI-flavor detection report, judged by code.