Plaaasma/dsh-subagent-claude-live ↗★ 0
dsh-subagent-claude-live
Claude Code as a real, streaming dsh subagent: session-backed child, free model/effort choice per call, live model list from the CLI
安装
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Plaaasma/dsh-subagent-claude-live说明文档
阅读完整 README ↗Configuration
Defaults from the bundle layer (cordis.patch.yml). Override by targeting subagent-claude-live in your profile's cordis.patch.yml — a config override replaces the whole object, so restate the keys you keep.
- id: subagent-claude-live
config:
providerName: claude # name on ctx.subagents
toolName: claude_code
modelsToolName: claude_models
defaultModel: fable # preset, alias, full id, or '' for the CLI's own default
presets: # friendly name -> what the CLI accepts
fable-5.1: claude-fable-5-1
fable: fable
opus: opus
sonnet: sonnet
haiku: haiku
permissionMode: bypassPermissions
allowPermissionModeOverride: true
executable: '' # '' = `claude` on PATH / ~/.local/bin; 'bundled' = SDK payload; or a path
env: {} # layered over the scrubbed parent environment (e.g. ANTHROPIC_BASE_URL)
disposeGraceMs: 3000
modelsCacheMs: 600000
maxTurns: 0 # 0 = CLI default
bypassPermissions is the default because a delegated coding task that stops at the first permission prompt is a failed task — there is no human on the child's side to answer it. It means the child edits and executes in the parent session's working directory with no checks. Set permissionMode: dontAsk (deny anything not pre-authorized in your Claude settings) or plan (read-only, returns a plan) if that is not what you want, and allowPermissionModeOverride: false to stop the model raising it per call.