플러그인
DeepSeek-Harness 플러그인을 찾아보고, 필터링하고, 설치하세요.
플러그인 256개 찾음
dsh-result-budget
wildchiken/dsh-result-budget
Trims each tool result to a token budget derived from the active model's context window (ratio of window minus reserved output, clamped), keeping head and tail with a notice on how to fetch the rest; mount globally or inside one agent preset.
guster
lumos-789/guster
Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on its own dimensions; and turns findings into reviewable migration plans that are validated against the published schema before apply, confine writes to declared roots, and back up every file before moving it. The format contract is a versioned spec (CTX rules, markdownlint-style IDs) following open conventions — the AGENTS.md open format, llms.txt-shaped indexes, YAML front-matter note headers — now backed by published JSON Schema contracts (draft 2020-12) for the hub manifest and the plan JSON, plus an editor modeline that validates hub.yaml with zero configuration. The hub is declarative (schema 2, zones, sections may live outside the hub root) with machine-readable register/v1 project ledgers and knowledge/v1 note headers; a one-pass check command runs scan, doctor and score, and state writes are atomic and lock-protected; scoring stays honest about missing evidence — a waiver greens the gate, never the score. Ships a stdlib-only Python CLI plus two skills; credentials are referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.
dsh-strata
light-cheng/dsh-strata
Layered context management: at each turn end older tool output becomes a deterministic card, the model can fold older ranges into its own summaries in up to three tiers (compress), and every original is archived locally for decompress and search_context. Works alongside DSH-Mem0: superseded runtime-context snapshots (such as recalled memories) are never archived, carded or folded, and are replaced by a one-line placeholder at turn end when the prompt cache is already broken, when the saving outweighs the cache miss, or above 75% of the window; a strataBudget service (pressure, allowance, countTokens) and a strata/fold-landed event are provided for other context plugins; strata_status warns when DSH's automatic compaction is off or its official summary keeps failing. Its L1 layer, archive rotation, prune guard and preset takeover are forked from dsh-live-compact 1.0.6 (MIT); uninstall dsh-live-compact or billion-context first — they replace the same compaction rows and Strata will not take over while either is installed.
dsh-goal-budget
boom-10/dsh-goal-budget
Sets token, cost and wall-clock caps on a DSH goal and blocks that goal when a cap is reached, instead of only reporting the spend. The figures come from the usage events DSH records for the session, priced per model, with a pill beside the composer that opens a per-model breakdown. The official DeepSeek tariff is built in, with peak/off-peak pricing toggleable because it depends on the route; other models are priced from configured rates, and a model with no rate has its tokens counted and its name listed rather than being guessed at.
dsh-family-budget
skyline66/dsh-family-budget
Monthly household budget page in the sidebar: income, fixed and variable expenses, savings, emergency fund, debt and a month-by-month review, with totals, per-item budget differences and a savings, debt or home goal. Bookkeeping only, no investment advice.
dsh-progress-beat
mabinogi-cichol/dsh-progress-beat
Makes the agent narrate progress during long tool chains instead of staying silent until the final answer: a standing system-prompt rule that travels with every request, plus a notice injected after every N tool calls. A panel on the plugin page tunes the cadence, the reminder budget, and both texts; changes apply live.
sapi-budget
lanstzz/sapi-budget
Cost display for AiSpot (sapi) relays: crawls the provider's group list from its public pricing endpoints instead of hardcoding it, lets you pick the active group from a dropdown in the conversation header, and shows a per-turn cost at the end of each turn plus a session total that recurses through every subagent subtree. Switching groups re-prices all history instantly, because the host publishes token buckets only and the browser applies the live rates.
dsh-team-dev
jiecore/dsh-team-dev
Per-turn tool-call step budget for Agent Teams teammates, shipped together with the team-dev and team-boot skills.
dsh-task-notifier
lizhijie429/dsh-task-notifier
Sends desktop notifications when a DSH turn finishes or fails, and sends 继续 automatically after the model-retry budget is exhausted.
dsh-workflow (l2-protocol)
weihao654/dsh-workflow
Plan-native multi-agent workflow for DeepSeek Harness: plan directs, work coordinates, code writes, and review audits read-only. Ordinary tasks need no authorization card or budget form. Includes 14 chain_* tools for explicitly authorized controlled rounds, with a frozen T0 baseline, layered evidence, and blocking close gates. Provides per-role model settings. Requires the sibling l1-presets bundle. For new installs, Weihao654/dsh-workflow#role-chain provides this runtime and the four presets in a single bundle. Do not enable role-chain alongside either legacy l1-presets or l2-protocol.
baton
lumos-789/baton
Runs an approved OpenSpec change to completion while the model stays a mechanical forwarder: a bundled Python CLI computes the ticket DAG frontier, claims tasks atomically, prepares one git worktree per assignment, and returns exact actions. The session delegates each action with the DSH subagent tool and reconciles the completion notice against a hash-bound receipt produced by re-running verification commands on a clean, advanced HEAD, so free-text "done" never counts. Runtime scope changes are plain tasks.md edits. Liveness is observable, not guessed: status returns a relay block (elapsed and lease budget, receipt presence, heartbeat and activity age, a suggested action); abandoning a plausibly-still-working attempt is refused with the judgment data unless --force; a late sealed receipt is revived by adopt after full re-verification instead of rebuilding the ticket; dispatched subagents refresh a progress heartbeat outside the worktree. Requires Python 3.10+ on PATH and a git project that uses OpenSpec.
dsh-obsidian-memory
aoyamabf-max/dsh-obsidian-memory
Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.
token-usage-statistic
zhiwuli0228/token-usage-statistic
Tracks token usage and estimated costs for every model call, with daily charts, session and workspace names, provider balances, budgets, and secret-free CSV/JSON exports.
dsh-mega-plugins (ui-memo-settings)
zhangj1164/dsh-mega-plugins
A Settings page for the memo plugin suite in DSH Web: edits the memo Host's AI route, archived-session summary language, length, transcript budget, template and prompt, and repository URL, adds a GitHub intake section for the claim label, per-run issue cap, autopilot switch and its working directory, preset, time zone and dispatch prompt, with per-field reset and saves that reach the running services without a restart, and carries an update entry that checks the npm registry and can install a newer release through the deployment's plugin manager.
dsh-science-legion
lengrufeng2008/dsh-science-legion
수학, 물리학, 천문학, 공학, 생의학 근거를 위한 단계형 멀티 에이전트 과학 캠페인 Skill 번들입니다. 공유 블랙보드, 독립 검증자와 레드팀, 울프팩·측면 공격 전술, 토큰·시간 예산, 정답이 알려진 평가를 제공합니다. 4 에이전트 진자 파일럿과 6 에이전트 4차 파일럿은 벤치마크 정답 키 오류를 찾아 수정했습니다. 미해결 문제를 풀었다고 주장하지 않습니다.
dsh-sap-ai-core
solstice621/dsh-sap-ai-core
공유 OAuth, Qwen 모델 5종, 사고 예산, 스트리밍, 도구 호출을 지원하는 SAP AI Core 제공자입니다. cn40에서 검증되었습니다.
dsh-budget-view
sushuheng/dsh-budget-view
DSH 플러그인입니다. 입력창과 새 세션 페이지에 Codex/OpenCode Go 할당량, DeepSeek 잔액, 피크/비피크 상태를 표시합니다. DeepSeek 공식 위안화 피크/비피크 요금으로 세션 비용을 추산합니다.
sleep-not-permitted
jjjacksong/sleep-not-permitted
DSH 에이전트의 포그라운드 대기를 거부합니다. sleep, wait, tail -f, watch, -c 없는 ping, 무한 루프 등의 대기 명령, wait_agent 및 wait: true인 job_output 같은 차단 대기 도구, 짧은 시간 안에 같은 확인 명령을 반복하는 폴링, sudo -n 없는 실행, BatchMode 없는 ssh, 로그인 흐름, 대화형 편집기, docker -it 등 사람의 입력/확인이 필요한 명령을 거부하고 백그라운드 실행 또는 턴 종료를 안내합니다. 예산과 폴링 창을 설정할 수 있고 메시지 언어는 system(zh/en)을 따릅니다. 런타임 종속성 없음.
dsh-context-budget
dsh-raising-plan/dsh-context-budget
긴 대화용 정리 도구입니다. `trim_context` / `estimate_context_tokens`는 system persona와 마지막 메시지를 유지하고 턴 또는 토큰 예산에 맞도록 가장 오래된 user/assistant 쌍부터 제거한 뒤 전후 추정치를 보고합니다. 도구가 호출되지 않으면 대화를 정리하지 않습니다.
dsh-compact-control
zdjmrq/dsh-compact-control
DSH 네이티브 자동 compaction이 시작되는 context window 비율을 조정합니다. 플러그인 관리자 페이지에서 슬라이더로 1~100%(기본 80%, 화살표 키로 1%씩)를 설정합니다. 임계값이 낮아질수록 보존 기록 예산도 줄어 일찍 compaction하는 효과가 사라지지 않습니다. 실제 compaction은 계속 네이티브 엔진이 실행합니다.
dsh-context-keeper
orliba/dsh-context-keeper
DeepSeek Harness 세션의 context budget을 감시합니다. 각 턴 footer에 공식 `contextPressure` projection 기반 색 점을 표시합니다(green <50%, yellow 50–65%, orange 65–80%, red >=80%). orange/red에서 한 번 클릭으로 새 세션 handoff를 하는 알림 패널과 `/context-watch`, `/handoff` 명령, 고정 reasoning-rule prompt 섹션을 제공합니다. 예산과 handoff는 로컬 session 파일만 읽으며 버튼을 누르기 전에는 배지와 알림이 토큰을 쓰지 않습니다.
dsh-plugin-task-budget
i1537725423-dotcom/dsh-plugin-task-budget
DeepSeek Harness 각 턴에 CNY 지출 상한(기본 ¥5)을 설정하고 상한에 도달하면 다음 모델 요청 전에 실행을 멈춥니다. 스위치와 금액은 composer 도크 오른쪽 끝에 있습니다.
dsh-prompt-enhance-keyless
ozjxnxh/dsh-prompt-enhance-keyless
composer 도구 모음에서 모델 선택기 왼쪽에 반짝이 버튼을 추가합니다. 클릭하면 호스트를 통해 초안을 바로 다시 쓰고, 잠시 원문 복원 실행 취소를 제공합니다. 설정에서 다음 메시지에 사용할 대화 모델(provider/model, 설정된 기본값으로 대체 가능) 또는 로그인과 토큰 예산이 필요 없는 keyless Pollinations 경로를 선택합니다. 후자는 30초마다 한 번만 응답할 수 있습니다. 대기 중 클릭은 거부하지 않고 대화 모델로 처리하며, 대기 시간이 끝난 뒤 첫 클릭은 자동으로 keyless 경로를 사용합니다. 초안의 언어를 유지하고 다른 언어 결과는 붙여넣지 않습니다.
dsh-web-firecrawl
xyonium/dsh-web-firecrawl
DeepSeek Harness 웹 백엔드로 Firecrawl을 사용합니다. web_search/web_fetch의 쿼리 라우팅, 필요 시 정보 보강, 크레딧 예산, 실패 기억을 제공합니다.