Goal mode and autonomous execution plugin for DeepSeek Harness: a sticky top banner keeps the current goal visible across turns while the agent works toward it autonomously.
Install
# from npm (prebuilt)
dsh plugin --profile web add @goodandready/dsh-goal
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:GooDAnDReaDY/dsh-goal
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
⚡ Overview & The Problem
Complex engineering tasks require multi-step autonomy: decomposing high-level objectives into milestones, executing successive iterations without manual user re-prompting, and maintaining clear visibility into task progress.
@goodandready/dsh-goal brings autonomous goal execution to DeepSeek Harness via the /goal command:
- 🎯 Sticky Top Goal Banner: Pinned status header with live timer (
• 2s,• 1m 45s), active goal title, and interactive control buttons. - ⏸️ Play / Pause / Cancel: Instantly pause the autonomous loop or resume execution on demand.
- 📋 Milestone Breakdown Drawer: Interactive checklist showing sub-tasks, percentage completion, and iteration logs.
- 🤖 Autonomous Agent Tools: Provides
goal_set_milestones,goal_update_progress, andgoal_finishtools directly to the agent. - 🛡️ Safety Guardrails: Configurable
maxIterationslimit to prevent runaway loops.
🏛️ Architecture
graph TD
subgraph Input ["User Interaction"]
Cmd["Slash Command: /goal <objective>"]
API["REST API: POST /dsh-goal/action"]
end
subgraph GoalEngine ["Goal Lifecycle Engine (lib/index.js)"]
State["State Manager (IDLE, RUNNING, PAUSED, COMPLETED)"]
Milestones["Milestone Tracker & Decomposition"]
Disk["Persistence Store (~/.dsh/goal-state.json)"]
end
subgraph AgentLoop ["Autonomous Agent Drive"]
ToolSet["goal_set_milestones"]
ToolProgress["goal_update_progress"]
ToolFinish["goal_finish"]
LimitGuard{"maxIterations Guard"}
end
subgraph UI ["DSH Web Interface"]
Banner["Sticky Top Goal Banner"]
Timer["Live Elapsed Timer"]
Drawer["Milestone Checklist Modal"]
Settings["Settings Card (Schemastery)"]
end
Cmd --> GoalEngine
API --> GoalEngine
GoalEngine --> State
State --> Disk
State --> Banner
State --> Drawer
GoalEngine --> AgentLoop
AgentLoop --> LimitGuard
ToolSet --> GoalEngine
ToolProgress --> GoalEngine
ToolFinish --> GoalEngine
📦 Installation
dsh plugin --profile web add @goodandready/dsh-goal
Restart your DeepSeek Harness instance and refresh the browser.
💬 Usage & Quick Start
Start a goal directly in chat:
/goal Refactor the authentication middleware and add integration tests
Or trigger via REST API:
curl -X POST http://localhost:3080/dsh-goal/action \
-H "Content-Type: application/json" \
-d '{"action":"start","title":"Optimize database queries"}'
⚙️ Configuration Reference (settings.yaml)
dsh-goal:
maxIterations: 25
autoDrive: true
enableSound: true
| Parameter | Type | Default | Description |
|---|---|---|---|
maxIterations |
number |
25 |
Safety limit: maximum autonomous iterations per goal |
autoDrive |
boolean |
true |
Keep the autonomous agent loop running between turns |
enableSound |
boolean |
true |
Play completion audio chime when a goal finishes |
🧪 Testing
Run the automated test suite:
npm test
📄 License
MIT © GooDAnDReaDY
Links
More in this category
zhu1090093659/dsh-web#packages/dsh-skill-explorer★ 7488
Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.
GanyuanRan/Aegis★ 1182
Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.
superdesigndev/superdesign-skill★ 547
Design skill for UI and marketing graphics on the Superdesign canvas: reads the repo for context, extracts its design system, then generates and iterates branchable design drafts, flow pages, and reusable components through the Superdesign CLI.
linhay/harmony-next.skills★ 347
HarmonyOS NEXT skill bundle for DeepSeek Harness with offline API references and DevEco, HDC, and emulator automation guidance.
sandbaseai/sandbase-skills★ 165
Mounts 88 packaged research, social-intelligence, marketing and business Agent Skills into dsh through the filesystem Skill provider.
dhicoc/dsh-reverse-skill★ 135
Complete reverse-skill pack (85 SKILL.md) as a DeepSeek Harness Cordis plugin: reverse engineering, authorized pentesting and security-research skill router.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.