Objective Start — Development skill for Claude Code
Start a governed objective with explicit wake and budget policy.
How to install Objective Start
Installs to ~/.claude/skills/th3vib3coder-vibe-research-environment-objective-start/SKILL.md
mkdir -p ~/.claude/skills/th3vib3coder-vibe-research-environment-objective-start && curl -fsSL https://raw.githubusercontent.com/th3vib3coder/vibe-research-environment/HEAD/commands/objective start.md -o ~/.claude/skills/th3vib3coder-vibe-research-environment-objective-start/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Objective Start does
description: Start a governed objective with explicit wake and budget policy allowed-tools: Read, Bash model: sonnet dispatch: module: environment/objectives/cli.js export: startObjectiveCommand scope: objective-start wrappedByMiddleware: false
/objective start
Purpose
Create and activate an objective record with explicit operator intent.
Invocation
node bin/vre objective start --title --question --mode --wake-policy
Alternatives in Development
- Harness Improvement — Update Kandev harness files from session learnings or explicit cross-platform harness requests 697 ★
- Galatea Garden Wake Bridge — 独立的 Galatea Garden 智能体唤醒桥:订阅 Garden SSE 事件,并通过可替换的 Runtime Adapter 将消息注入 Codex、Claude Code 等 Agent Runtime 225 ★
- Prompt Sensei — Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analy 107 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Pursue
Hand Kimi an objective to pursue AUTONOMOUSLY across multiple turns (experimental goal mode), bounded by a har
Claude Retro Skill
An end-of-session /retro skill for Claude Code: the agent reviews its own session, keeps only lessons that cle
Factory Goal
Start an Agent Factory campaign from one prompt — decompose the objective into Linear units, spawn an agent te
Harness Session
Start or end a harness-tracked agent session. Provides context from previous sessions, sets focus feature, sta
Compliance Review
Run governed compliance review using the verified local compliance registry.
Adb Android Control
Comprehensive Android device control via ADB — typed Python package + CLI + Claude Code skill. Master Tester D
Related Agents
Spawner Agent
Agent Designer of the Governed Multi-Agent Delivery System. Invoked only after Master Orchestrator approves a
Governance Reviewer
Reviews a change for governance compliance using PromptWise — security scan, policy check, quality gate, and a
Effectiveness Strategist
Use when the decision depends on short versus longer marketing horizons, demand capture versus brand effects,