Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

146 plugins found

S

dsh-host-fs

sniperdown/dsh-host-fs

Adds the fs_remove and fs_move tools, executed in the DSH host process so they can delete paths the sandboxed shell cannot, gated by a session allow list and a path allow/deny list that denies by default.

0last monthTools & CapabilitiesMIT
A

dsh-multi-model-discussion

a331266223/dsh-multi-model-discussion

Multi-model deliberation pipeline for DeepSeek Harness: independent proposals, blind peer review, program-executed evidence verification, immutable revision and independent acceptance on a fresh context.

0last monthModels & ProvidersMIT
Z

dsh-egress-gate

zhengqiuyang/dsh-egress-gate

Deterministic network egress gate: web fetches and searches are checked against a destination allowlist in tools/pre-execute and denied before they run; shell fetch-verbs are observed (enforcement opt-in).

05 days agoSecurity & PermissionsMIT
W

dsh-whale-guard

wyr-233/dsh-whale-guard

Safety guard that makes self-killing commands impossible: a safe_kill tool that always excludes the caller and every ancestor process, a bash pre-execute check for pkill self-matches, sudo -S stdin grabs, rm -rf / and similar patterns, and an extensible rule library with block / warn / hint severities.

0last monthSecurity & Permissions
D

dsh-warden

dingchenhui0618-arch/dsh-warden

Adversarial review gate for tool calls. It hooks `tools/pre-execute`: a local regex pass over destructive commands (`rm -rf`, `git push --force`, `git reset --hard`, `DROP TABLE`, `format`, disk writes) and sensitive paths (`.env`, `id_rsa`, `.ssh`, `.git/`, `$DSH_HOME`) runs first with no latency, and only a hit is escalated to one review-model call that returns allow or deny. Plain reads and ordinary writes never enter that path, so everyday work pays no added delay. Every verdict is shown live in the Web GUI.

024 days agoSecurity & PermissionsMIT
B

simple-plan

bauerelizabeth07139/simple-plan

Strict verification for every task: plan 2-7 steps, execute them with worker subagents, verify each deliverable with an independent memoryless verifier subagent, and fix in at most three cycles before reporting honestly.

0last monthSkillsMIT
B

plan-guardian-skill

bauerelizabeth07139/plan-guardian-skill

A mandatory 7-step plan on every request, each step with a binary acceptance criterion, executed through worker subagents and validated by independent memoryless verifier subagents that report PASS or FAIL with evidence.

0last monthSkillsMIT
Z

dsh-sandbox-noop-escalation

zzstar101/dsh-sandbox-noop-escalation

Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.

0last monthSecurity & PermissionsMIT
W

dsh-plugins (dsh-thesis-workbench)

wxlei2004/dsh-plugins

Thesis and empirical-analysis workbench that drives IBM SPSS from the conversation: spss_check (environment self-check), spss_variables (list .sav variables with labels, types, measurement levels, case counts), spss_data (sample case rows to inspect missing and outlying values), spss_run / spss_run_file (execute SPSS syntax or an .sps file, relative CD and GET FILE paths auto-rebased), and spss_analyze (one-shot frequencies, descriptives, crosstabs with chi-square, t-tests, one-way ANOVA, correlation, linear regression). Results come back as structured tables extracted through OMS. SPSS 25-31 is auto-detected; the bundled MCP server is zero-dependency stdio.

02 months agoWorkflow & Automation
J

dsh-jev-loop

jwe24-code/dsh-jev-loop

Jev (TypeSafe System One) judgments at the DeepSeek Harness agent-loop gates: pre-step, pre-execute, post-execute, and turn-stopping. No UI dependencies; mount it in any Harness composition.

02 months agoSecurity & PermissionsMIT
C

dsh-skill-audit

caesarloo/dsh-skill-audit

Audit DSH skills automatically: a host-layer tools/post-execute plugin that ships both the skill body and the audit engine, runs the engine after skill files change (write/edit/shell) or after a bulk restore/backup (any tool invoked with mode: restore|bac

02 months agoSecurity & Permissions
Z

bazidiy (pkg)

zifan1117/bazidiy

BaziDIY ontology plugin: deterministic bazi/wuxing/bead/style rules as DSH tools (calculate_bazi, propose_designs, generate_design, save_design, load_design), plus bracelet SVG rendering and a bead editor; no LLM calls inside execute.

0Tools & CapabilitiesPossibly stale
A

dsh-sandbox-arg-guard

apex-mochen/dsh-sandbox-arg-guard

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

02 months agoSecurity & PermissionsMIT
K

dsh-orbit

kasenri/dsh-orbit

Deterministic engineering orchestration runtime for DeepSeek Harness: the orbit_controller tool and OrbitService run Commander, Executor and Smart Watchdog children through PLAN, EXECUTE, EVALUATE, bounded correction and runtime recovery, with durable state in <project>/.cx/state.json.

0yesterdayWorkflow & AutomationMIT
K

sbtd-plugins

kunolu/sbtd-plugins

DSH 宿主上的 SBTD workflow 适配器。当前为 T5:注册短中文 sbtd section、进程内会话状态、`sbtd_plan`、`sbtd_review`、`tools/pre-execute` / `agent/pre-step` hooks 门禁,以及从 640-skills 只读同步的 `manuals/`。

02 months agoWorkflow & AutomationApache-2.0
M

dsh-autopilot-public

my-denia/dsh-autopilot-public

Native Goal Autopilot Harness for DeepSeek Harness (dsh): plan-execute-audit gates, mechanical enforcement, and evidence-bound closeout as an out-of-tree plugin bundle.

02 months agoWorkflow & AutomationMIT
Z

dsh-paopaocat-suite

zmm863-commits/dsh-paopaocat-suite

泡泡猫皮肤 — 可爱猫咪主题,纯 CSS 自绘。 / Paopaocat skin — cute cat theme, pure CSS.

03 months agoThemes & AppearanceMIT
S

dsh-rs

saidoua/dsh-rs

The dsh grep and glob tools executed in-process by the dsh-rs addon, with the packaged-ripgrep spawn as the fallback

03 months agoTools & CapabilitiesMIT
J

dsh-plan-and-execute

jimmyzhang219/dsh-plan-and-execute

Plan-and-execute orchestration over ReactLoopAgent — turns a goal into reviewable steps with a web UI plan card.

02 months agoWorkflow & Automation
J

dsh-gsd-bundle

jaaty/dsh-gsd-bundle

Git Ship Done (opengsd-core) reimplemented as host-plane Cordis plugins: replaces the default agent loop with a spec/discuss/plan/execute/verify/ship phase loop.

03 months agoWorkflow & AutomationMIT
V

dsh-fs-deny-policy

vladlearns/dsh-fs-deny-policy

DeepSeek Harness plugin: a deployment deny list of filesystem roots the model may never touch - fences read, write, search, and shell tool calls at tools/pre-execute

03 months agoSecurity & PermissionsMIT
M

dsh_plugins

moveharder/dsh_plugins

DSWhale Copilot — 一条由 DSH 事件驱动的 DeepSeek 蓝色小鲸鱼伙伴:随 agent 会话的思考/回复/工具执行/审批/提问/完成等事件游泳、起伏、跳跃、间歇喷水,审批与提问时暂停移动并抖动提醒(可开启全浏览器醒目提醒),并带跟随鲸鱼位置的会话状态面板(支持深/浅主题)。A cute whale copilot for the DSH Web surface driven by agent session events.

03 months agoJust for Fun
B

dsh-notebook

beihzb/dsh-notebook

A stateful, Agent-controllable Jupyter workspace for DeepSeek Harness: a persistent ipykernel runtime the DSH agent can read, edit, execute, and inspect, with VS Code-aligned cell UI and .ipynb save/load.

03 months agoTools & CapabilitiesMIT
C

dsh-agent-preset-router

ctwctw9999/dsh-agent-preset-router

Auto Mode for DSH: a flash-model router that auto-picks the best agent preset (standard/code/minimal/cordis) for each new session and executes immediately, no confirmation.

03 months agoWorkflow & AutomationMIT