At a glance
What it does
A dsh profile bundle that adds Claude Code-style settings precedence and permission rules.
Tui Profile, Web Profile
>=0.1.5-rc.1
Evidence-verified
Checked Sep 12, 2026, 2:06 PM UTC
Code-evidenced contributions
What it adds to DSH
Replaces the default settings provider with a five-level settings cascade and mounts allow/deny/ask permission rules for the dsh profile.
Mechanism evidence ↗Before you choose it
This bundle disables dsh's plain settings provider, then mounts a five-level settings cascade plus a permission-rule engine. It is intended to make dsh profiles honor merged permission settings with allow, deny, and ask rules.
Best for
DeepSeek Harness users who want Claude Code-style permission configuration in a dsh-cc terminal or web profile.
Common tasks
- Apply project and user permission settings through the dsh-cc settings cascade.
- Use allow, deny, and ask rules to govern agent tool approvals.
- Add the permissions layer when explicitly composing the dsh-cc TUI or web profile.
Permissions and data
Configuration-focused bundle that changes how dsh reads settings and evaluates permission rules.
Permissions- Reads the merged permissions settings namespace.
- Reads DSH_HOME/settings.json and project .claude settings files through the settings cascade.
- Uses local/profile and project settings to determine permission behavior.
Limitations
- This is a profile component, not a standalone coding application.
- The supplied evidence does not show a successful installation or runtime execution.
- The recorded npm version was not found; use the verified pinned Git source rather than assuming registry availability.
- It aims for Claude Code-style permission compatibility, not a claim of identical behavior.
What DSHub checked
- The package and its Cordis patch have verified structure.
- The patch disables the base settings row and mounts settings cascade, permission rules, and the permissions command integration.
- An immutable Git bundle distribution is verified.
What DSHub did not check
- Installation, boot, and permission-rule behavior were not executed for this record.
- Registry publication of version 0.6.3-rc.2 was not verified.
Pinned install
Install dsh-cc Permissions Bundle
This plugin bundle does not have a DSH Plugin install action. Use its source documentation for the delivery method.
Maintainer source
Project README
dsh-cc
English | 简体中文
Claude Code-style workflows. Your models. DeepSeek Harness.
dsh-cc turns DeepSeek Harness into a batteries-included coding environment for everyday development. Keep familiar project assets and interaction patterns while choosing the models, tools, permissions, and agent composition that fit your environment.
- Reuse familiar workflows:
.claude/agents,SKILL.md,CLAUDE.md, hooks, permissions, slash commands, and resumable sessions. - Bring your own model strategy: route aliases such as
sketch,draft,blueprint, andmasterplanto any provider/model pair supported by your dsh deployment. - Run a complete coding loop: TUI, MCP, memory, subagents, background tasks, worktrees, structured output, and deferred tool discovery.
- Stay composable: install the experience through native dsh profiles and plugins instead of maintaining a permanent DeepSeek Harness fork.
dsh-ccis not Claude Code and is not a wrapper around Claude Code. It implements familiar Claude Code-style workflows on the open, composable DeepSeek Harness runtime.
Quick start
Install DeepSeek Harness and the dsh-cc launcher, then start coding:
npm install -g @deepseek-ai/dsh @dsh-cc/cli
dsh-cc
dsh-cc requires dsh >= 0.1.5-rc.1; the default npm install -g @deepseek-ai/dsh currently satisfies this (as of 2026-09-12), and the launcher enforces the floor at bootstrap.
Already have dsh >= 0.1.5-rc.1? Install only the launcher:
npm install -g @dsh-cc/cli
dsh-cc
The launcher creates and boots the CC-oriented tui profile. To compose the profile explicitly instead:
dsh plugin --profile tui add \
@dsh-cc/bundle-permissions \
@dsh-cc/bundle-shell \
@dsh-cc/bundle-tui
dsh --profile tui
The same backend also works with the dsh web UI:
dsh plugin --profile web add \
@dsh-cc/bundle-permissions \
@dsh-cc/bundle-shell
dsh web
Optional: official plugins
The bundles above are the whole quick start. Two optional official plugins — shipped through the repo's dsh-cc marketplace — add preconfigured subagent lanes:
dsh-cc-agents— thedsh-cc-agents:critic(reasoning and plan review,opusalias) anddsh-cc-agents:executor(mechanical execution,sonnetalias) subagents, plus an orchestration routing skill.dsh-cc-shunt— PreToolUse gates that redirect bulk file reads and boilerplate generation to cheap-lane worker subagents, keeping large file corpora out of the main context (configure ahaikualias for real token savings).
Install them inside a session:
/plugin marketplace add dsh-cc/dsh-cc
/plugin install dsh-cc-agents@dsh-cc
/plugin install dsh-cc-shunt@dsh-cc
/plugin install flips the enabledPlugins flag for you; restart the session so the new agents and hooks are picked up. To update later, re-pull the marketplace and then update the plugin: /plugin marketplace update dsh-cc, then /plugin update <id>. Each plugin's own README (agents, shunt) covers configuration and known limits.
Why developers use dsh-cc
| Need | What dsh-cc provides |
|---|---|
| Keep project conventions | Loads Claude Code-style agents, skills, project memory, settings, hooks, and plugin commands |
| Mix fast and capable models | Maps stable aliases to deployment-controlled provider/model routes |
| Delegate larger tasks | Supports subagent dispatch, background work, task inspection, and resume-aware routing |
| Work safely in parallel | Adds permission rules, approval flows, worktree tools, and workspace boundaries |
| Avoid loading every tool up front | Provides deferred discovery through ToolSearch and MCP integration |
| Move between interfaces | Exposes the same CC-oriented backend through terminal and web profiles |
dsh-cc is developed with dsh-cc itself. The repository's current setup routes work across Kimi, GLM, and DeepSeek models; see Dogfooding dsh-cc for the concrete mapping.
Compatibility at a glance
<!-- parity:matrix:start -->| Category | Full | Partial | Missing | Non-goal |
|---|---|---|---|---|
| Engine subsystems | 11 | 10 | 4 | 2 |
| Hook events | 12 | 4 | 4 | 0 |
| Command surface | 21 | 7 | 1 | 2 |
| Sessions and context | 1 | 0 | 1 | 0 |
| Memory and CLAUDE.md | 0 | 1 | 1 | 0 |
| Skills | 0 | 1 | 0 | 0 |
| Subagents | 0 | 1 | 0 | 0 |
| MCP | 2 | 1 | 0 | 0 |
| Plugins and marketplaces | 0 | 2 | 0 | 0 |
| Settings | 2 | 1 | 0 | 0 |
| Permissions | 0 | 1 | 0 | 0 |
| Models | 0 | 1 | 0 | 0 |
| Workspace | 1 | 0 | 0 | 0 |
| Interactive UX | 1 | 2 | 0 | 0 |
Statuses were verified against upstream documentation retrieved as of 2026-09-05 (freshness threshold: 120 days).
For the exact feature-by-feature status and known gaps, see the Claude Code parity matrix.
<!-- parity:matrix:end -->Familiar coding-agent workflows
Subagents
Project-local Claude Code-style agent definitions under .claude/agents can be discovered and dispatched by the CC preset.
.claude/
agents/
reviewer.md
debugger.md
Agent frontmatter can continue using familiar model aliases while dsh decides which provider/model actually serves the request.
Skills
SKILL.md-based skills are discovered by the CC skill provider, including project-specific skills and bundled utility skills.
Memory
The memory layer supports CLAUDE.md-style context plus a dedicated write channel for durable memories. Memory is isolated by workspace, with optional shared team memory.
MCP
The CC profile includes an MCP client with:
- tools;
- resources;
- prompts;
- OAuth 2.1 flows.
Use /mcp to inspect and manage MCP connections.
Optional: Serena code intelligence
When your MCP configuration connects a Serena server, dsh-cc automatically takes advantage of it: the system prompt steers toward Serena's symbol tools for code questions, and the bundled explore subagent gains read-only symbol retrieval (find_symbol, find_referencing_symbols, get_symbols_overview). Serena is strictly optional — without it, sessions behave identically through the built-in Read/Grep tools, minus the steering hints.
Install Serena once so a local serena binary is on PATH:
uv tool install git+https://github.com/oraios/serena@v1.7.0
Then add it to ~/.dsh/.mcp.json (or a project .mcp.json) using the local binary:
{
"mcpServers": {
"serena": {
"command": "serena",
"args": ["start-mcp-server", "--context", "claude-code", "--project-from-cwd"]
}
}
}
Avoid launching it via uvx --from git+…: every server start would write ~/.cache/uv, which the session sandbox denies.
/doctor reports the connection under the mcp.serena check.
Hooks
Claude Code-style hooks can react to session, prompt, tool, permission, compaction, task, and subagent lifecycle events. Command and HTTP executors are supported, with additional prompt/agent executors available behind configuration gates.
This repository ships a tracked hooks.json (the CC preset loads it from the launch cwd). The PreToolUse remind hook requires serena-hooks on PATH — see Local development.
See the parity matrix for the currently bridged event set.
Slash commands
The CC preset exposes a growing command surface, including:
/cost token / cost information
/doctor session health report (--verbose / --json)
/status environment and session status
/memory inspect memories
/skills list installed skills
/config inspect or change settings
/permissions inspect or change permission mode/rules
/mcp manage MCP connections
/tasks inspect current tasks/jobs
/resume resume an interrupted session
/branch worktree branch management
/diff inspect CLAUDE.md / settings differences
/init scan a project and scaffold CLAUDE.md
/plugin manage plugins
/provider manage LLM providers (list/add/remove, rotate keys, set default)
/onboard re-run the first-run setup (clears the onboarding opt-out)
/release-notes show release notes
/version show version information
The TUI also provides terminal-oriented interactions such as todo inspection, approval flows, queued prompts, transcript export, usage/context display, and local shell commands.
/provider opens an overlay over your configured model providers: /provider list prints the current routes, /provider add <preset-id> walks a wizard for the built-in presets (Moonshot, Z.AI/Zhipu, DeepSeek) or a fully custom endpoint, and the per-route detail view rotates keys, refreshes the model list, sets the default, or removes the route. API keys are typed into a masked field and stored in the credential store (~/.dsh/.credentials.yaml), never in settings; keys already supplied by the environment are shown read-only. Changes take effect for new sessions immediately (credentials resolve per request); the running session keeps its current provider until you pick again with /model.
First-run onboarding
On a fresh install with no model configured, the boot seed settles with no default route and the TUI opens the provider panel automatically: pick a preset, paste your API key (stored only in the credential store), and set the default model — then you are ready to go. Dismissing the panel with Esc only skips it for the current session; the flow is re-offered on the next boot. To opt out permanently, set cc-onboarding.suppressed: true under the user settings namespace in ~/.dsh/settings.json, and re-arm any time with /onboard. Non-interactive (non-TTY) runs never trigger the flow and keep the plain "No model configured" notice.
Use the models you want
Claude Code-style agent definitions often refer to models using aliases:
model: sonnet
dsh-cc can route those aliases to provider/model pairs configured for your deployment.
Conceptually:
sonnet / draft -> <provider>/<general coding model>
opus / blueprint -> <provider>/<reasoning model>
haiku / sketch -> <provider>/<fast model>
fable / masterplan -> <provider>/<maximum-reasoning model>
architect -> parent agent route (planning / orchestration)
inherit -> parent agent route
Aliases are configuration, not hard-coded vendor bindings. This lets you preserve familiar agent definitions while choosing the models that fit your own environment.
Dogfooding dsh-cc
dsh-cc is now developed with dsh-cc itself. The project's current development setup uses the same model-alias routing described above, with this mapping:
| Alias | Model |
|---|---|
fable / masterplan |
kimi-k3 |
opus / blueprint |
glm-5.3 |
sonnet / draft |
glm-5.3-flash |
haiku / sketch |
deepseek-v4-flash-0731 |
architect |
inherit (main thread) |
This is a real project configuration rather than a required default: users can map the aliases to any provider/model combination supported by their DeepSeek Harness deployment.
How this is different
vs. Claude Code
Claude Code is a complete coding-agent product. dsh-cc instead brings many familiar interaction patterns to the DeepSeek Harness runtime, where the deployment controls models, tools, plugins, permissions, and agent composition.
vs. a DeepSeek Harness fork
This repository is designed primarily as an out-of-repo plugin stack. Most functionality is installed and composed through dsh profiles, reducing the amount of permanent fork maintenance required as upstream evolves.
A small number of upstream packages are vendored where the required extension point cannot currently be expressed as a wrapper. See Architecture notes below.
vs. model/API routers
This is not just a model-routing proxy. It extends the agent runtime and developer experience itself: UI, commands, tools, memory, subagents, hooks, MCP, permissions, sessions, and worktree workflows.
CC Mode
CC Mode is an additional dsh agent preset. The four built-in dsh modes remain behaviorally unchanged.
On the tui profile, CC Mode is the default. On other profiles it can be selected through the preset selector or configured as the default agent preset.
The terminal profile launches in fullscreen mode by default. To opt out for one invocation:
DSH_CCTUI_UI_MODE=regular dsh --profile tui
Configuration
Your profile remains ordinary dsh composition. Local tweaks can be placed in:
~/.dsh/profiles/tui/cordis.patch.yml
They are applied after the installed bundles.
Model alias configuration, permissions, settings precedence, hook behavior, memory options, and TUI behavior are exposed through the corresponding plugins/settings namespaces.
For exact semantics, use the package READMEs and the parity matrix as the source of truth.
Custom status line
On the tui profile, you can replace the built-in bottom status line with your own shell command (Claude Code-compatible). The block can live in the user file ~/.dsh/settings.json or in a project .claude/settings.json:
{
"statusLine": {
"type": "command",
"command": "~/.dsh/statusline.sh",
"padding": 0,
"refreshInterval": 10
}
}
Project .claude/settings.json files shared with a Claude Code checkout work as-is; if both a camelCase statusLine and a dsh-native kebab statusline key are present, the dsh-native key wins.
The command receives a Claude Code-compatible JSON session payload on stdin (the CC statusline docs describe the contract); dsh-cc supplies only the fields it can source truthfully. Its stdout's first line becomes the status line (ANSI escapes are passed through); a failure or empty output renders a blank line. The command reruns on session boot/resume, new messages, mode and model changes — and immediately when the command itself changes — plus on the refreshInterval timer, which is in seconds (minimum 1). Scripts get COLUMNS/LINES in their environment.
v1 caveats: only the first output row is rendered (CC renders every row), and edits to settings.json made outside the running session apply at the next restart.
Compatibility and known limits
The goal is useful Claude Code-style workflow compatibility, not byte-for-byte emulation of Claude Code.
Some areas are intentionally partial or depend on DeepSeek Harness extension points. Examples include parts of the hook event vocabulary, background subagent workflows, notification/IDE-shell behavior, and vendor-specific features.
The project tracks those differences explicitly instead of hiding them:
Read the full Claude Code parity matrix →
Architecture
The repository is a monorepo of small plugins and bundles grouped by responsibility:
packages/
settings/ settings cascade and migrations
interaction/ permissions and slash commands
mcp/ MCP client and configuration
hooks/ hook protocol and CC bridge
core/ tools, ToolSearch, NotebookEdit, StructuredOutput, Sleep
skill/ SKILL.md support
preset/ CC agent preset and agent compatibility
compat/ plugin loader, model aliases, output styles
memory/ CLAUDE.md memory and consolidation
workspace/ worktree tools
subagent/ coordinator / subagent integration
compaction/ micro-compaction
session/ cost, export, and stats commands
bundle/ installable profile bundles
ui/ terminal UI
launcher/ optional dsh-cc executable
Most packages are normal out-of-repo dsh plugins.
A few packages vendor upstream implementations when the required changes need private/internal extension points rather than composition. These currently include the tools registry, MCP client, hook protocol, and Claude Code hook bridge. At runtime they are mounted under distinct package names while preserving the expected service interfaces.
Local development
This repository expects a sibling DeepSeek Harness checkout at ../deepseek-harness for local link: development dependencies.
pnpm install --frozen-lockfile
pnpm run typecheck
pnpm test
Serena (serena-hooks on PATH)
Dogfooding this repo loads the tracked hooks.json. Its PreToolUse remind hook runs serena-hooks remind --client claude-code on every Read/Grep, so the binary must already be on PATH:
uv tool install git+https://github.com/oraios/serena@v1.7.0
That pin provides serena, serena-agent, and serena-hooks. Do not invoke uvx --from git+… from the hook: that writes ~/.cache/uv on every call, the session sandbox denies it, and Read hangs behind PreToolUse.
Health-check and index remain one-shot uvx commands; see docs/code-intelligence-health.md.
To test unpublished packages against a real profile:
pnpm run build
bash scripts/sync-local-profile.sh web
dsh web
To prove the production bundle set actually boots in a user-grade
environment (fresh DSH_HOME, harness-healed fallback, pseudo-TTY, no LLM
calls) — the same gate presubmit and publish run:
pnpm smoke:profile-boot
To install/update the CC preset during local development:
bash scripts/sync-cc-preset.sh
See docs/dev.md for offline development details and repository-specific dependency rules.
Packages and releases
Published plugins use the @dsh-cc npm scope. The root monorepo package is private; installable packages are released individually through the repository release tooling.
Release process details: docs/release.md.
Project status
dsh-cc is evolving alongside DeepSeek Harness. The compatibility surface can change as upstream adds new extension points or changes existing ones.
If you find a workflow that works differently from Claude Code, the parity matrix is the best place to check whether it is implemented, partial, intentionally out of scope, or still missing.
Contributions, compatibility reports, and focused upstream extension proposals are welcome. Useful ways to help include:
- compatibility reports with reproduction steps and
/doctor --jsonoutput; - focused fixes and tests for one capability;
- upstream extension proposals that reduce vendored code;
- real-project model-routing and workflow examples.
Open an issue · View pull requests
License
Operate deliberately
Install and manage
Prerequisites and target Profile
Target: Tui Profile, Web Profile
Delivery: Dsh Bundle Git — dsh-cc/dsh-cc#a5116127a12b79f23a4b02c9adda39b4bed8b5ea。
Verify, update, and remove
Show lifecycle commands
dsh plugin --profile tui listCompatibility and access
Dsh Cc requires DeepSeek Harness dsh >= 0.1.5 Rc.1: >=0.1.5-rc.1。
Review compatibility evidence ↗
Risk facts
Reads permission settings from DSH_HOME and project .claude settings files, so enabling it can change tool approval behavior.
Evidence ↗The pinned Git bundle is verified, while the recorded npm version was not found.
Evidence ↗Evidence and editorial reviewManifest, Bundle patch, distribution and freshness
Immutable evidence
Review status and source activity
Assess the effective settings files and permission rules in your environment before enabling this bundle.
AI reviewed Sep 12, 2026, 2:07 PM UTC。GitHub facts last checked Sep 12, 2026, 2:07 PM UTC。
No material source change has been recorded since this evidence baseline.