beginner · 15 min 01
What Is DeepSeek Harness?
From models to Agents to the Harness, build a concept map you won't confuse.
STEP 1 Read →
Tutorial index
Follow the evidence, layer by layer.
Learn in order, or jump straight to your current problem. Every tutorial carries its applicable version, verification date and next step.
Start here
02 tutorials
beginner · 20 min 02
Launch DeepSeek Harness in 10 Minutes
Start the Web UI with the official npm command, check the port, and prepare your first session.
STEP 2 Read →
Daily use
05 tutorials
beginner · 22 min 01
Configuring Models and Compatible Endpoints
Understand the boundaries of Providers, API Keys, and custom OpenAI-compatible Endpoints.
STEP 3 Read →
beginner · 25 min 02
Workspaces, Sessions, and Permission Approvals
Understand what the Agent can see, which operations require approval, and how to set safe trial boundaries.
STEP 4 Read →
beginner · 28 min 03
Troubleshooting Installation and Startup
Locate problems along the shortest path, from Node, ports, and networking to model configuration and workspace permissions.
STEP 7 Read →
intermediate · 30 min 04
Use Plan Mode to Build an Executable Task Contract
Agree on goals, boundaries, acceptance evidence, and rollback before the Agent edits files.
STEP 9 Read →
intermediate · 32 min 05
Build Feedback Loops and Independent Review
Use tests, logs, static checks, and a separate reviewer as external evidence.
STEP 10 Read →
Plugins
05 tutorials
intermediate · 24 min 01
How to Tell Plugin, Tool, Skill, and MCP Apart
The four most easily confused extension concepts, explained at once by responsibility and runtime boundary.
STEP 5 Read →
intermediate · 30 min 02
Installing Third-Party Plugins Safely
Four checks — source, permissions, versioning, and rollback — to reduce the risk of adding third-party code to the Agent Runtime.
STEP 8 Read →
intermediate · 35 min 03
Build Project Memory with Skills
Load reusable workflows on demand instead of placing an entire handbook in every prompt.
STEP 12 Read →
advanced · 42 min 04
Design Tools the Model Can Use Correctly
Build reliable names, schemas, canonical outputs, errors, and idempotent effects.
STEP 14 Read →
advanced · 55 min 05
Build Your First Cordis Tool Plugin
Walk from apply(ctx) through configuration, tool registration, result observation, and unload verification.
STEP 16 Read →
Architecture
04 tutorials
intermediate · 28 min 01
Profiles and Bundles
Understand how dsh composes the plugin tree layer by layer at startup, and the difference between web and headless.
STEP 6 Read →
advanced · 35 min 02
Manage Context with Compaction, Sessions, and Forks
Preserve decisive facts, remove noise, and isolate alternate work paths.
STEP 11 Read →
advanced · 38 min 03
Permissions, Sandbox, and Runtime Invariants
Separate soft instructions, human approval, filesystem enforcement, and tool policy.
STEP 13 Read →
advanced · 40 min 04
Subagent Orchestration: Split, Isolate, and Synthesize
Parallelize only independent work, with explicit ownership and acceptance evidence.
STEP 15 Read →