플러그인

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

DeepSeek Harness(dsh)용 해시 기반 read/edit/batch_edit/undo_last_edit 도구. 모든 줄에 편집 후에도 안정적으로 유지되는 고유한 3자리 해시(A-Za-z0-9)가 부여됨; 오래되었거나 모호한 앵커는 거부되며 절대 유사 매칭하지 않음. 재시작 후에도 실행 취소 이력 유지

프롬프트, 도구 인자, 결과 텍스트를 저장하지 않고 턴별 도구 호출 수와 대략적인 검증 신호를 로컬 JSONL로 기록합니다.

안전 실패(fail-closed) 방식의 Feishu(Lark) 채널 브리지입니다: 봇과 대화하면 dsh 에이전트의 턴 결과를 돌려받습니다. 공식 Python SDK만 사용하는 통합(버전 고정)이며, 기본 거부 방식의 허용 목록, 웹훅 서명/타임스탬프/재전송 검증, 채팅별 고정 세션을 제공하고 이중 언어 문서를 갖추고 있습니다.

Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.

플러그인 스토어: npm 공식 카탈로그 + awesome 큐레이션 목록(550개 이상 플러그인, 11개 카테고리), dsh 필드 품질 검증, 공식 `dsh plugin add/remove` 원클릭 설치, 사이드바 + 설정 진입점

엔지니어링 규율 가드: 첫 수정 전에 요구사항을 검증하고, red/green 테스트 증거 게이트를 강제하며, 포크된 어드버서리로 결과물을 감사(grill-requirements 스킬 + 도구 정책 게이트)

세션 실행 분석 기능: 단계, 도구 호출, 실패, 반복 동작, 토큰 사용량, 검증 신호를 텍스트/Markdown/JSON 리포트로 제공합니다.

Multi-agent math problem-solving & verification framework: brainstorm → solver iteration → multi-verifier debate → Verified knowledge base, with checkpoint resume and manual/auto intervention (also ships as an agent preset).

실제 연산 검증 게이트: 수식 단순화, 논리 증명, 정규식 검증, E-prover FOL, 상태 머신 검사, 코드 복구, Go로 컴파일된 바이너리 기반(미리 빌드된 Windows 실행 파일 포함)

Bundled Xiaohongshu/RED viral-note agent skill: hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing.

Rust dev domain plugin for DeepSeek Harness (dsh): verification pyramid fmt→clippy→build+test→miri+audit(+semver) as model-facing tools + graph-layer governance (anti-Goodhart 8 rules incl. #[allow] density / deleted tests, blind-spot via Cargo.toml & pub

Linux kernel dev domain plugin for DeepSeek Harness (dsh): verification pyramid L1-L4 as model-facing tools + graph-layer governance (anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md contract as a system-prompt section. Plain JS, no build step.

Open plugin marketplace: live GitHub dsh-plugin topic search with per-repo package.json verification (dsh.bundle/dsh.client manifest badges and a verified-only filter), npm-first installs with same-source anti-squatting checks, update detection, and five agent tools for headless use.

Anti-bot HTTP fetch tools hardened by SXS's production scraping stack (millions of requests/day): UA-pool rotation, retry with exponential backoff, anti-bot wall detection (captcha / verification challenges) and adaptive rate limiting — tools: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

DeepSeek Harness community Bundle for the BeforeDone evidence gate

Conversational DSH plugin finder: four-source unified index, BM25 pre-filter plus LLM semantic ranking, candidates carry evidence grades and local static security audit, safe install flow with post-install verification.

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.

Verification toolkit for DSH agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), and read-only URL/npm/GitHub submission-readiness probes.

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

Multi-agent deep long-form article pipeline skill for DeepSeek Harness, running 7 roles across 5 phases with parallel literature/data/case retrieval, an evidence base, independent audit and human verification gates.

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.