Kimi Pursue — Project Management agent for Claude Code
Use this agent ONLY when the user has explicitly asked Kimi to pursue a stated objective AUTONOMOUSLY across multiple turns (experimental goal mode) — a multi-step task the user wants Kimi to drive to.
How to install Kimi Pursue
Installs to ~/.claude/agents/linxule-kimi-plugin-cc-kimi-pursue.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/linxule/kimi-plugin-cc/HEAD/agents/kimi-pursue.md -o ~/.claude/agents/linxule-kimi-plugin-cc-kimi-pursue.md Restart Claude Code, or start a new session, for it to be picked up.
What Kimi Pursue does
name: kimi-pursue description: Use this agent ONLY when the user has explicitly asked Kimi to pursue a stated objective AUTONOMOUSLY across multiple turns (experimental goal mode) — a multi-step task the user wants Kimi to drive to completion on its own, not a single bounded edit. This is the plugin's highest-autonomy surface: WRITE-CAPABLE, reusing the rescue trust boundary (the /kimi:setup PreToolUse hook + workspace allowlist gate every tool call on every continuation turn; it cannot muta
Alternatives in Project Management
- Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
- Claude Squad — Manages multiple AI terminal agents including Claude Code and Aider in parallel 5.6k ★
- Maestro — You are a specialized orchestration agent 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kimi Worker
Forward a coding, diagnosis, or review task to Kimi K3 (Moonshot) through the local kimi-worker.sh runtime. Us
iOS Legacy Auditor
iOS legacy and undocumented codebase expert. Use when onboarding onto an unfamiliar project, exploring a codeb
Task Executor
Use this agent when you need to implement, complete, or work on a specific task that has been identified by th
Kimi Rescue
Use this agent proactively when the user wants to delegate a substantial investigation or implementation task
Kimi K3 Worker
Coding worker on Kimi K3, served by the multi-model gateway's upstream. Use when the user says "use kimi", "ki
Pipeline Runner
Runs the complete /proceed pipeline for a single REQ in subagent mode (all phases sequential, no sub-agent dis
Related Skills
Pursue
Hand Kimi an objective to pursue AUTONOMOUSLY across multiple turns (experimental goal mode), bounded by a har
Focus.Prompt
Pin a session goal to keep all todos, delegation decisions, and verification steps aligned with a single state
Factory Goal
Start an Agent Factory campaign from one prompt — decompose the objective into Linear units, spawn an agent te