dsh-agent-team-presets

Concept illustration. See Screenshots for the plugin interface; the captain uses the conversation's selected model.

English | 中文

Community plugin v0.1.9 · Tag

This release targets DeepSeek Harness 0.2.2-rc.1 and adds individual member chat: hover a Team in the composer, then select one member to run the Session as that member with its own role card, tools, Team Skills, and model route. It also moves member routing to agent.model.select() and per-step tool admission. Requires Agent Teams; keep 0.1.8 on older hosts. Prebuilt artifacts are included.

What's new in 0.1.9

• Talk to one member directly. The composer's Team picker now shows a member panel on hover. Selecting a member injects its role card, tool policy, Team Skills, and model route into the current Session; selecting the captain keeps the Session model unchanged.
• DeepSeek Harness 0.2.2-rc.1. Member routes are recorded through agent.model.select() and tool admission is evaluated per step. The plugin refuses an unusable member route before applying anything instead of falling back to the captain.
• Custom tool policies are native-only. On PTC presets the plugin preserves the deployment's executor and explicitly refuses custom allow-lists; PTC still works with the all-tools mode.
• Built-in troubleshooting skill. The global agent-team-presets-troubleshooting skill explains Team application, member creation, route evidence, Team Skill visibility, and install/upgrade failures.

Overview

dsh-agent-team-presets is a visual Team preset and private skill manager for DeepSeek Harness. Configure a Team once, assign per-agent isolated skills, then select it from the conversation composer whenever you need it.

A Team contains a captain and any number of member roles:

• The captain uses the conversation's selected model, with its own role description, system prompt, and tool policy.
• Each member can have an independent provider, model, reasoning effort, system prompt, tool policy, and assigned Team Skills.
• The captain summons members through spawn_team_member; native Agent Teams provides messaging, the shared task board, and runtime coordination.

This is a community plugin, not the Harness's bundled @deepseek-ai/dsh-experimental-agent-team-presets development package.

Why this plugin?

DeepSeek Harness already ships Agent Teams with multi-agent collaboration. In the Harness versions this plugin supports, per-Team configuration, skill isolation, and reuse are still left to the user, which is what this plugin addresses:

• Teams are hard to reuse. In those versions, native teams focus on runtime creation and collaboration, with no visual preset management; this plugin saves, duplicates, categorizes, and reuses named presets.
• Role setup is repetitive. Each role's name, description, system prompt, and tool policies are configured once instead of re-described every time.
• Splitting work across models is awkward. Every member picks its own model and reasoning effort, so one Team combines models by task, while the captain keeps leading on the Session's model.
• Tool permissions have no fine-grained entry point. In those versions the native tool surface offers no per-role allow-list; here the captain and each member carry their own, so roles differ in what they may use.
• Skills lack per-agent scope isolation. Shipped or user skills are typically registered globally, making all skills visible to every agent; this plugin provides a private Team Skill library where skills are discovered only by the specific Agent they are assigned to.
• Switching teams is inconvenient. Pick a preset Team directly from the composer instead of rebuilding roles by hand.

Design principle: native Agent Teams owns collaboration at runtime; this plugin owns configuring, managing, isolating, and reusing teams and their skills.

Features

• Reusable Teams: create, duplicate, edit, select, and delete named presets.
• Per-member model routes: assign models and reasoning effort to individual roles without changing the captain's model.
• Individual member chat: hover a Team in the composer to inspect its captain and members; select one member to inject that member's role card, tool policy, Team Skills, and model route into the current Session.
• Independent tool policies: choose all available tools or a custom allow-list for the captain and each member.
• Nine built-in presets across two series: three software development scale teams (Lightweight, Standard, Full-Stack) and six specialized work-mode teams (Discovery, Planning, Workflow, Engineering, Security Audit, Research).
• Display metadata: attach summary, tags, use cases, quick prompts (suggested tasks), and notes per Team. Strictly presentation-only: never injected into the runtime LLM context, saving context tokens.
• Local categories and search: organize presets into custom categories via a dedicated category manager; instantly search over name, summary, tags, and use cases in both Settings and the Composer picker.
• Private Team Skill library: import skill folders or ZIP archives into a plugin-owned store (~/.dsh/agent-team-presets/team-skills), completely isolated from global host skills.
• Per-agent skill isolation: a 3-column assignment grid on member pages assigns skills to specific roles. Assigned skills are registered strictly in that Agent's scope when summoned—never leaked globally.
• Official built-in skills & local overrides: ships two delivery skills (github-repository-presentation, git-release-hygiene) and two method skills (grilling, research), materialized into the private library and pre-bound to engineering, discovery, and research roles. Create local editable overrides and one-click restore them to the built-in copy (恢复为插件内置版本).
• Plugin-level troubleshooting skill: installing the plugin registers the global runtime skill agent-team-presets-troubleshooting (not a Team Skill, not per-Agent isolated). It covers Team application, member creation, tool-policy refusals, model-route evidence, Team Skill visibility, and install/upgrade failures.
• Guarded deletion with blocker modal: deleting a skill bound to any role, in use by an active member, or required as a dependency is refused, with a confirmation modal detailing every blocking holder.
• Dependency verification & MCP boundaries: checks declared CLI executables against host PATH (flags found/missing and refuses assignment when absent) and reports declared MCP servers (declarative display; never auto-connected or hard-blocking).
• Agent-facing tools: root sessions provide list_team_skills, assign_team_skill, unassign_team_skill, and remove_team_skill alongside get_team_preset and update_team_preset.
• Live settings feedback: see whether a Team is idle, busy, or awaiting an update in an online Session.
• Theme integration: robust light and dark mode adaptation across all cards, dialogs, inputs, and dropdowns.

Contents

• Overview
• Why this plugin?
• Features
• Screenshots
• Requirements
• Install and upgrade
• Configure and use a Team
• Display metadata, categories, and search
• Private Team Skills and per-agent isolation
• Share presets
• Agent-facing tools
• Tool permissions and security
• Troubleshooting and limitations
• How it works
• Development and contributing
• Related resources
• License

Screenshots

The first screenshots show the 0.1.9 composer with individual member chat. The rest illustrate the settings interface, Team Skill management, and the earlier composer flow. Every provider, model, Team, and member name below is placeholder data from an isolated demo profile, not a real deployment.

Browse and filter Teams in the composer

Hover a Team to open its member panel: captain, members, model route, and description

Hovering a row never changes the selection. The captain row carries the captain badge and session model; each member row shows its own provider and model, or session model when it follows the Session.

Click a member to talk to it alone: the trigger names it and the Session model follows its route

The member's role card, tool policy, Team Skills, and model route are injected into this Session. The Team trigger reads Team · member, and the model control switches to the member's configured route — Example Fast here.

Click the captain to select the Team normally: the Session model is left alone

The captain always follows the Session, so selecting it changes the Team and the role card but never the model. The chip above keeps Example Fast from the previous member selection.

Manage Teams: tabs, search, source and series filters (settings layout carried over from v0.1.8)

Private Team Skill library with origin badges and actions

Assign Team Skills to a member role

Skill details: file tree, editor, and local copy actions

Guarded skill deletion with blocking holders modal

Manage custom preset categories

Team editor: display metadata, category picker, and status notices

More screenshots (model routing, custom dropdowns, prompts, and tool policies)

Category dropdown in Team editor

Filter Teams by custom source

Configure member models and reasoning effort

Model picker

Captain and member system prompts

Tool policy controls

Requirements

• DeepSeek Harness >=0.2.2-rc.1 <0.3.0. Verified against 0.2.2-rc.1. Each member's route is recorded through agent.model.select() for fresh, forked, and cold-resumed execution; the captain keeps the conversation's model selection. The plugin manager enforces engines.dsh from package.json.
• Custom tool allow-lists require a native Agent preset (standard or cordis). This Host cannot restore an inherited executor after a temporary override, so the plugin preserves the deployment's executor and explicitly refuses custom policies on PTC. PTC remains available with the all-tools mode. Select a native Agent preset before using custom policies.
• Agent Teams enabled in the target profile. The standard integration is @deepseek-ai/dsh-experimental-agent-team-profile, which supplies the Team service, tools, and Web roster. This plugin configures and manages Teams; it does not replace that subsystem.
• A Web or Desktop profile with Settings and the required client services. Install into the profile you actually use, typically web for the Web GUI or desktop for Desktop.
• Durable storage and a continuable subagent backend for member execution. Member creation is refused if the storage domain or selected execution backend is unavailable. The default backend names are spawn and fork.

The plugin version (0.1.9) and the Harness version (0.2.2-rc.1, for example) are separate version lines.

Install and upgrade

Install and upgrade

Option 1 — npm package (recommended; receives update prompts)

Open Global panels → Plugins → Add plugin, paste the line below into Package name or address, and click Install:

dsh-agent-team-presets

Or install it from the CLI:

dsh plugin --profile <profile> add dsh-agent-team-presets

Replace <profile> with your active profile (e.g. web or desktop):

dsh plugin --profile web add dsh-agent-team-presets

The plugin manager compares the installed version against npm's latest dist-tag, so every later release is offered as an update.

Option 2 — floating GitHub install

Tracks the repository's default branch; an update is offered when package.json on that branch moves to a higher version:

dsh plugin --profile <profile> add github:bloodarea/dsh-agent-team-presets

Option 3 — reproducible pin (no update prompts)

dsh-agent-team-presets@0.1.9
dsh plugin --profile <profile> add github:bloodarea/dsh-agent-team-presets#v0.1.9

A fixed version or tag reproduces exactly one release. A #tag GitHub spec is only ever compared against that same tag, so the market never reports an update for it — upgrading means editing the spec by hand. Use this form only when you need a frozen install.

Install notes

• Registry selects which npm source the download comes from. Default registry uses pnpm's own configuration. Pick Official npm registry to bypass a mirror, or Custom address for an internal or cloud mirror.
• The field accepts package names, name@version, github:owner/repo, tarball URLs, or absolute filesystem paths.
• This package declares dsh.bundle, so the plugin manager automatically registers it as a profile bundle layer; do not add a loader entry by hand.
• Once installed, reinstalling the same package identity is blocked. To switch sources (e.g. from GitHub to npm), uninstall first, then install the new spec.
• GitHub and npm are separate release channels, so check the version this install would fetch before switching channels:

npm view dsh-agent-team-presets version

• After installation, reload or restart as prompted.

Verify and upgrade safely

After installation, follow the plugin manager's reload/restart prompts and navigate to Settings → Agent team presets. Verify that details display dsh-agent-team-presets, version 0.1.9, and a running component.

• Back up profile settings, Team definitions, and Session selections before upgrading.
• When migrating from a development link, remove @deepseek-ai/dsh-experimental-agent-team-presets first before enabling the community package.
• Restart Harness after switching package identities, then refresh the GUI.

Install the bundle; do not add a second loader declaration. The package already supplies its own bundle patch. Duplicate hand-written declarations in profile patches can prevent settings from saving. See Configuration writes are overridden.

Configure and use a Team

1. Open Settings → Agent team presets.
2. Select a built-in Team, duplicate an existing one, or click New Team.
3. Configure its name, purpose, display metadata, category, captain, and member roles.
4. For each member, configure its provider/model route, reasoning effort, tool policy, and assigned Team Skills.
5. Press Save in the shared footer. Edits remain staged drafts until saved.
6. Select the Team from the conversation composer's Team control, then prompt the captain to coordinate the task.

Example prompt for a Team with execution and review roles:

Use the selected Team. Have the executor implement the agreed changes and regression tests, then ask the reviewer to inspect them independently. Summarize changes, test results, and remaining risks.

A preset role is a template. Summoning creates an instance with a unique target such as executor or executor-2. Use send_message with the returned target to continue working with an existing instance rather than spawning a new one.

Selecting No team disarms the Team application once the captain and teammates become idle, restoring standard session contributions without changing the active model.

Talk to one member directly

Hover a Team row in the composer picker to open its member panel. The captain is listed first with the Session model route; every member follows with its configured provider · model and role description.

• Selecting the captain applies the Team normally: the captain leads, may summon members, and keeps the model the Session already selected.
• Selecting a member starts an individual conversation with that member. Its role card (name, role description, and standing system prompt) becomes the Session persona, its tool policy and assigned Team Skills apply, and the captain briefing plus spawn_team_member are not installed. The Session model switches to that member's configured provider/model and reasoning effort. A member with no configured route keeps the Session's current model.
• Switching back to the captain does not restore an earlier model: the captain always follows whatever model the Session currently has selected.
• Role and model changes wait for a running task to reach its boundary, exactly like a Team change. A selection naming a member that no longer exists is refused and the Session stays locked rather than silently falling back to the captain.

Fields

Field	Purpose
Team name and purpose	Identify the preset and explain what work it handles.
Category	Assign the Team to a local category for organization in lists and picker.
Display metadata	Summary, tags, use cases, quick prompts, and notes. Purely presentation-only; never injected into LLM context tokens.
Captain	The lead agent. A nonempty captain prompt replaces its persona prefix; the captain keeps the conversation's model.
Members	Reusable role templates the captain can summon.
Name	Role display name and target base. ASCII letters/digits and hyphens (max 64 chars, not lead).
Description	Role responsibilities for the captain to select appropriate members (max 200 chars).
Color	Accent color distinguishing the role in settings and the roster.
Provider / Model	Members only. Route from the deployment's model catalog.
Reasoning effort	Members only. Options depend on model support; empty uses route default.
Allowed tools	Independent all-tools or custom allow-list policy.
Team Skills	Assigned private skills, registered exclusively in this Agent's scope upon creation.
System prompt	Standing role instructions. {{variable}} denotes prompt template variables.

Built-in presets

A fresh installation seeds nine editable Teams across two series:

研发规模系列 (Classic Development Scale)

Preset	Roles	Intended use
轻量研发团队 builtin-lightweight	Captain, fullstack-advisor, executor	Small features and module iterations. Captain plans and verifies, architecture advisor handles cross-layer technical contracts on demand, executor writes code, tests, and debugs. Pre-bound with official delivery skills.
标准研发团队 builtin-standard	Captain, system-architect, executor, code-reviewer	Standard software projects. Captain coordinates, system architect establishes interface contracts and module boundaries, executor develops and tests, independent code reviewer inspects quality. Pre-bound with official delivery skills.
全栈软件研发团队 builtin-fullstack	Captain, backend-architect, ui-designer, executor, reviewer	Complex full-stack engineering across Web, Desktop, and Android. Captain leads, backend architect and UI designer provide technical/UX contracts, reviewer enforces quality gates, executor implements. Pre-bound with official delivery skills.

工作模式系列 (Work Modes)

Preset	Roles	Intended use
需求探索 builtin-discovery	Captain, demand-analyst, solution-explorer, independent-challenger	Open-ended ideas where goal, technical path, or product direction is still exploratory; read-only research with independent challenge.
架构规划 builtin-planning	Captain, system-architect, technology-evaluator, compliance-auditor	Settled goals where systems, module boundaries, and cross-module contracts must be designed.
既定工作流执行 builtin-workflow	Captain, workflow-coordinator, task-executor, delivery-verifier	Established workflows where user specifies next task, and team implements, verifies, and delivers it.
工程研发协作 builtin-engineering	Captain, architect-advisor, executor, code-reviewer, repository-specialist	Feature development, cross-layer implementation, UI/UX, and debugging, with a dedicated repository delivery specialist (repository-specialist). Pre-bound with official delivery skills.
独立代码与安全审计 builtin-audit	Captain, vulnerability-expert, security-auditor, compliance-inspector	Independent read-only review of specified code, vulnerabilities, security configurations, and dependency compliance.
科研协作 builtin-research	Captain, domain-researcher, experiment-analyst, rigor-reviewer	Literature review, experiment design, scientific computing, data analysis, and academic rigor inspection.

Default presets are seeded once per profile. Deleting or editing a built-in preset is respected across restarts. Restore defaults restores shipped fields and official rosters while preserving local member model routes and tool policies.

Display metadata, categories, and search

Presentation-only display metadata

Each Team preset supports rich metadata:

• Summary: One-line description shown on cards and intros.
• Tags: Keyword chips for filtering and categorization.
• Use cases: Recommended project scenarios.
• Quick prompts: Ready-to-use task templates shown when selecting the Team.
• Notes: Operational reminders or cautions.

Token economy: Display metadata is stored in the preset document and used by the UI for search, grouping, and cards, but is never injected into the runtime LLM prompt context.

Local categories and hierarchical filtering

• Category manager: Click 管理团队预设分类 in the Settings list to open a dedicated management page. Create, rename, reorder, and delete categories, and inspect team counts per category.
• Local isolation: Categories and team-category bindings are saved in profile settings and are never exported with shareable preset documents.
• Two-level filters: The Teams list provides two independent filter rows:
  • 来源 (Source): 全部 (All), 插件内置 (Built-in), 自定义 (Custom).
  • 分类 (Category): For built-in teams, filters by official series (研发规模 / 工作模式); for custom teams, filters by user-created categories.
• Instant search: A responsive search box searches team names, summaries, tags, use cases, and quick prompts with real-time matched count reporting.
• Composer integration: The conversation composer's Team picker mirrors these source filters and search capabilities, with 不使用团队 pinned to the top.

Private Team Skills and per-agent isolation

Private store and scope isolation

Traditional skills in Harness are typically registered into the global environment, exposing every skill to every agent. This plugin introduces a Private Team Skill subsystem:

1. Private library: Skills live in a plugin-managed directory (~/.dsh/agent-team-presets/team-skills or storage domain), isolated from host and profile skills.
2. Per-Agent registration: When a Team member is summoned, its assigned skills are registered exclusively inside that member's Agent scope. Other members and the captain cannot see or invoke them unless explicitly assigned.
3. Official built-in skills: four shipped skills: delivery (github-repository-presentation, git-release-hygiene) and method (grilling — clarify before acting; research — primary sources only). Default bindings: engineering executor/repository-specialist receive the delivery skills; the Discovery captain receives grilling, its technical-scout/product-scout and the Research evidence-scout receive research.
4. Local overrides & one-click restore: Built-in skills are read-only by default. Users can create an editable local copy ("本地副本"). If the built-in skill updates in a new plugin version, an updateAvailable status is displayed, and users can restore to the built-in copy (恢复为插件内置版本) with one click.
5. Origin labels and badges: Skills display clear color-coded origin tags across all views:
   • 插件内置 (Built-in, blue)
   • 自定义 (Custom, purple)
   • 本地副本 (Override, amber)

Import, directory scan, and dependencies

• Folder and ZIP import: Import external skill folders or .zip packages directly in the Web GUI.
• Directory scan: Scans candidate folders in the import path, reporting eligibility and reasons for any rejected folder. Users can copy the absolute library path with one click.
• Dependency checks and MCP boundaries:
  • CLI executables: Declared CLI executables in SKILL.md are resolved against host PATH, using PATHEXT on Windows. Directories and non-executable files do not satisfy the dependency. Missing required executables are flagged and assignment is refused (dependency-missing).
  • MCP servers (declarative only, not auto-connected): Declared MCP servers are strictly declarative dependencies displayed in the UI (skillsDeclared). The plugin never connects, launches, or manages external MCP servers automatically (their lifecycle belongs to the Harness environment and profile). Because MCP connectivity is an environment-level fact, declared MCP servers are reported as unverified rather than hard-blocking role assignment. When an MCP server is configured and running in the Harness profile, its exposed tools (mcp__<server>__<name>) appear under the MCP tool group in the role's tool configuration and can be authorized via tool policies.
• Guarded deletion: Deletion is strongly guarded. If a skill is currently bound to any team role, used by a running member, or required by another skill, deletion is blocked. The confirmation dialog explicitly lists every holding team and member role (e.g. 标准研发团队 → executor), keeping the confirm button disabled until bindings are cleared.

Share presets

Export saves one Team as a JSON document (format version 2). Import preset reads the document and stages it in the editor.

• Shared fields: Team name, purpose, display metadata (summary, tags, use cases, quick prompts, notes), captain/member names, descriptions, prompts, and colors.
• Local fields: Model routes, reasoning effort, tool permissions, and local category bindings are never exported. Documents containing them are rejected on import.
• Name collisions: Choose between replacing the existing preset or creating a renamed copy. Replacement preserves local routes and tool policies on matched roles.
• Review imported prompts before executing tasks, especially when using documents from third parties.

Agent-facing tools

Root sessions register tools allowing agents to inspect and update presets and skills programmatically, subject to tool policies:

Team preset tools

• get_team_preset: Reads the active or specified Team preset, returning its purpose, role descriptions, prompts, roster, and settings revision.
• update_team_preset: Updates team/captain descriptions and member prompts/descriptions using compare-and-set revision checks. Requires direct human turn and Host approval. Returns team-busy if affected members are currently active.

Team Skill tools

• list_team_skills: Lists installed private Team Skills, origins, dependencies, and role assignment status.
• assign_team_skill: Assigns one Team Skill to a role in a Team (isolated to that agent scope).
• unassign_team_skill: Removes a Team Skill assignment from a role.
• remove_team_skill: Deletes a Team Skill from the library, enforcing blocker checks.

Tool permissions and security

Policy modes

• Default: all tools: No allow-list restriction beyond deployment permissions and role rules.
• Custom allowed tools: Permits only selected tool names. Coordination tools (send_message, list_agents, team_task_*) must be explicitly allowed if needed.
• Captain and member policies are independent. Granting a tool to the captain does not grant it to members.
• The skill tool is always admitted, and is not offered as a choice. It publishes the catalog and loads instruction text rather than granting a capability, and the Host withholds that whole catalog from an Agent that cannot see it. A custom allow-list therefore cannot remove it, and the settings page does not list it: a checkbox for it would be a control that can never do anything. Documents written by an earlier version that still name it keep loading unchanged — the entry is admitted implicitly, never reported as unavailable, and never needs removing.

What a member's first turn guarantees

An assigned Team Skill is only useful if the member can load it on the turn that asks for it, so the plugin makes the registration part of member creation rather than a background step:

• Members: the creation edge awaits that Agent's own registration before it completes. A role that holds assigned Team Skills but whose deployment cannot publish them — no skill service composed, the private library unreadable, or the registration refused — is refused at creation with the reason, instead of starting with an empty catalog while every surface says the skill is bound. Roles with no assignment keep working on deployments that compose no skill service.
• The captain: the same registration is performed inside the Session's creation edge, after the Team application it depends on. A captain whose assignment cannot be published does not refuse the Team — a Session that is already running must not lose its capability policy — and the failure is reported at the Agent identity.
• Unreadable library is not an empty library. When the private store cannot be opened the plugin cannot even enumerate a role's bindings, so it refuses member creation rather than reading the unknown as "no assignment". Repair the library path (or start again) to recover.

Known limitation: Windows verification

The path-separator and executable-resolution fixes are exercised by unit tests that normalize separators and by ENOTDIR cases, but no Windows machine was available here. Junction handling across volumes, PATHEXT resolution against a real PATH, and the full native build chain still need a Windows run before the release is described as Windows-verified.

Security boundaries

• The allow-list is not a filesystem, process, or network sandbox. Allowed tools (such as bash) retain their native capabilities. Maintain appropriate Harness sandbox and approval policies.
• Custom policy mode disallows general-purpose run_code and ordinary subagent / workflow delegation to preserve strict policy contracts. Use preset Team members for delegation.
• Managed members require their durable configuration on resume. Missing or corrupted records are refused loud rather than falling back to unrestricted defaults.

Troubleshooting and limitations

Configuration writes are overridden

If saving or selecting a Team reports:

Configuration for "agent-team-presets" is overridden by a home patch or command-line overlay

Check profile patches, $DSH_HOME/cordis.patch.yml, and --patch overlays for duplicate hand-written agent-team-presets declarations. Remove duplicate declarations while preserving Host-managed settings rows.

Built-in troubleshooting skill

The plugin registers agent-team-presets-troubleshooting on the global skill layer as soon as the profile composes the skill service. It is a host-level skill, not part of the private Team Skill library and not isolated per Agent: every Session can load it with the skill tool. Use it when a Team does not apply, a member cannot be summoned, a tool is refused, a member's model route is questioned, a Team Skill is invisible, or an install/upgrade behaves unexpectedly. The guide also states the evidence order: configuredRoute, model/selection, request/header.config, and the member snapshot route outrank subagent/descriptor or roster display values.

Common issues

Symptom	What to check
Settings page is absent or plugin pending	Confirm profile type, peer dependencies, Agent Teams enablement, and client services.
Skill deletion button is disabled	The skill is protected: inspect the blocker list in the modal (bound roles or dependencies must be unassigned first).
Skill assignment refused (dependency-missing)	A required executable declared by the skill is absent from host PATH. Note that declared MCP servers are reported for visibility and do not block assignment; ensure MCP servers are configured in your profile.
Member creation refused	Check storage domain availability, subagent execution backend (spawn/fork), model quota, and concurrency limits.
Model route display mismatch	list_agents.model can return an inherited or fallback model even when the member actually runs on its configured route. Verify actual routing via spawn_team_member's configuredRoute, model/selection, the first request/header.config, and the member snapshot route.
A selected member's route is unusable	The Host refuses the application and keeps the Session's previous composition and model instead of falling back to the captain. Correct that member's provider/model (and reasoning effort) in Settings → Agent team presets, then reselect it. The composer reports missing members but does not display a Host refusal; check the member route and the deployment's provider catalogue.

How it works

The plugin integrates via Cordis and Harness lifecycle extension points without patching host source code:

1. Profile configuration: Stores Team presets, display metadata, local categories, and active session selections.
2. Session application: Installs the captain persona, tool policy, and spawn_team_member at Agent scope. Selecting one member instead installs that member's role card and tool policy, omits the captain briefing and member tool, and selects the member's configured model route on the Session.
3. Member creation & skill scoping: Validates route and delegation limits, persists an instance snapshot, and launches the subagent. The serial agent/created hook injects model selection, persona, tool filters, and assigned Team Skills strictly into that member's Agent scope.
4. Private skill manager: Encapsulates skill storage (~/.dsh/agent-team-presets/team-skills), crash-recovery journaling, dependency resolution, and guarded deletion.

Source navigation

Area	Source
Plugin lifecycle and settings reconciliation	src/index.ts, src/settings-reconcile.ts
Built-in team catalog and series	src/builtin-teams.ts, src/team-catalog.ts
Team application and member tool	src/application.ts
Member snapshots and runtime injection	src/member-store.ts, src/member-identity.ts, src/member-runtime.ts
Private Team Skills subsystem	src/team-skills/store.ts, src/team-skills/manager.ts, src/team-skills/service.ts, src/team-skills/tools.ts
Tool policies and presentation	src/tool-policy.ts, src/presentation.ts
Preset tools and transfer	src/preset-tools.ts, src/preset-transfer.ts
Browser client UI	src/client/

Development and contributing

Source development requires a compatible, dependency-installed Harness checkout with its Host types and generated Typert Remote artifacts built first (the Harness build:lib:host pipeline provides them):

export DSH_CHECKOUT=/absolute/path/to/deepseek-harness
npm test
npm run typecheck
npm run bundle

Bug reports and pull requests are welcome at GitHub Issues and Pull requests.

Thanks to 张灏焱 for contributing the grilling and research method Team Skills (PR #2), and to Matt Pocock for the upstream skills they adapt (MIT, see NOTICE).

Related resources

• DeepSeek Harness — Host and plugin architecture.
• Built-in preset documents — Shipped team JSON definitions for reference or custom imports.
• Bundled skill documents — Shipped skills (SKILL.md bundles) materialized into the private library.
• Method skill upstream — Source of grilling and research (MIT; pinned commit recorded in NOTICE).
• GitHub Releases — Published release packages.

License

MIT. Bundled dependency notices are in THIRD-PARTY-NOTICES.txt; source and MIT attribution for the bundled method skills are in NOTICE.