Configuration
What kli init Sets Up
Running kli init in your project configures five things:
- MCP servers — Claude gets access to task management and pattern tools
- Hooks — Automatic context injection at session start and during tool use
- Skills — Domain knowledge that Claude loads when you invoke kli commands
- Commands — Slash commands like
/kli:plan,/kli:implement,/kli:research - Agents — Specialized sub-agents Claude spawns during workflows (reflector, curator, graph analyst, etc.)
You don't interact with any of these directly. They are infrastructure that Claude uses behind the scenes when you run slash commands like /kli:plan or /kli:implement.
Hooks
kli installs Claude Code hooks that run automatically during sessions:
| Hook | Event | What It Does |
|---|---|---|
| session-start | SessionStart | Registers session, detects parallel sessions, injects git state and active task context |
| tool-call | PostToolUse | Records tool usage events for behavioral fingerprinting and domain detection |
| session-task-write | PostToolUse | Writes session files when tasks are claimed or released |
| file-conflict | PostToolUse | Warns when you edit a file recently touched by another session |
| playbook-activate | UserPromptSubmit | Detects programming domains from prompts and nudges pattern retrieval |
| feedback-nudge | Stop | Reminds Claude to give feedback on activated patterns before stopping |
| session-leave | SessionEnd | Cleans up session files and records session departure |
See the Hooks Reference for detailed documentation on each hook.
Skills
Skills are domain knowledge documents that Claude loads on demand:
| Skill | Loaded When You Run | What Claude Learns |
|---|---|---|
| kli-research |
/kli:research | How to explore codebases, select agents, define exit criteria |
| kli-planning |
/kli:plan | How to design phases, define success criteria, reuse research |
| kli-implementation |
/kli:implement | TDD methodology, verification gates, design principles |
| kli-reflection |
/kli:reflect | Pattern extraction, feedback loops |
| kli-workflow | All commands | Phase transitions, artifact flow between commands |
MCP Servers
kli runs two MCP servers alongside Claude Code. These give Claude access to tools for task management and pattern learning — you never call these tools yourself:
- Task server — Claude uses this to create tasks, record observations, query the task graph, and detect conflicts between parallel sessions
- Playbook server — Claude uses this to search for relevant patterns, give feedback on what worked, and retrieve proven approaches
Both start automatically and shut down after idle timeout.
CLAUDE.md
kli init adds a small section to your project's CLAUDE.md that tells Claude the task MCP server is available. You can customize this if needed, but the defaults work for most projects.