codeloop
Controls autonomous agent development loops via start, stop, and status commands.
Install
mkdir -p .claude/skills/codeloop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11126" && unzip -o skill.zip -d .claude/skills/codeloop && rm skill.zipInstalls to .claude/skills/codeloop
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
AI 자율 개발 루프 제어 스킬. codeloop start/stop/status 서브커맨드로 Stop Hook 기반 무한 루프를 시작·중지·모니터링한다. Triggers: codeloop, codeloop start, codeloop stop, codeloop status, 루프 시작, 루프 중지, 루프 상태, ループ開始, ループ停止, 循环启动Key capabilities
- →Initialize autonomous development loops
- →Monitor task progress
- →Manage stop hooks for loop termination
- →Display loop status and metrics
How it works
The agent controls autonomous development cycles by reading configuration files and managing state files to track progress and termination conditions.
Inputs & outputs
When to use codeloop
- →Autonomous development cycles
- →Monitoring agent task progress
- →Managing stop hooks for long-running agents
About this skill
/codeloop — AI 자율 개발 루프 제어
인자로 start, stop, status 중 하나를 받는다. 인자 없으면 status로 동작한다.
start
루프를 시작한다. codeloop.yaml이 프로젝트 루트에 있어야 한다.
실행 절차
codeloop.yaml존재 확인- 없으면: "codeloop.yaml not found — run
/codeloop-initfirst." 출력 후 중단
- 없으면: "codeloop.yaml not found — run
codeloop.yaml에서 설정 읽기:prompt: PROMPT.md 경로model: Claude 모델 (opus/sonnet/haiku)gates: 완료 조건 목록project.name: 프로젝트 이름
- PROMPT.md 읽기
.claude/codeloop.state.md상태 파일 생성:--- active: true iteration: 0 started_at: "{현재 ISO 8601 시각}" config: "codeloop.yaml" --- {PROMPT.md 전문}- 사용자에게 안내 메시지 출력:
🚀 codeloop 루프 시작 ───────────────────────── 프로젝트: {project.name} 모델: {model} 게이트: {gates 목록} 프롬프트: {prompt 경로} ───────────────────────── ⚠️ --dangerously-skip-permissions 모드로 실행됩니다. 중지하려면: /codeloop stop - 사용자에게 안내:
사용자가 이 세션에서 직접 실행을 원하면:⚠️ 루프 실행은 별도 터미널에서 ./start.sh 로 실행하세요. 이 세션에서는 루프가 유지되지 않습니다.claude --dangerously-skip-permissions --model {model} -p "$(cat .claude/codeloop.state.md)"
중요
- Stop Hook이 매 세션 종료 시 자동으로 usage-gate → gates → dashboard를 실행
- 상태 파일이 존재하는 한 루프가 계속됨
- 모든 게이트가 통과되면 Stop Hook이 상태 파일을 삭제하여 루프 종료
stop
루프를 즉시 종료한다.
실행 절차
.claude/codeloop.state.md삭제- 출력:
⏹️ codeloop 루프 종료 - 상태 파일이 없으면:
ℹ️ 실행 중인 루프가 없습니다.
status
현재 루프 상태를 표시한다.
실행 절차
.claude/codeloop.state.md존재 확인- 없으면: "ℹ️ 실행 중인 루프가 없습니다." 출력
.claude/loc-status.md읽기 (대시보드)- 상태 요약 출력:
📊 Codeloop Status ───────────────────────── 프로젝트: {project.name} 반복: #{iteration} Phase: {phase} LOC: {current} / {target} ({progress}%) API 사용량: 5hr {five_hr}% · Weekly {weekly}% 게이트: {gate 상태 목록} ───────────────────────── - 대시보드 파일이 없으면 LOC Gate를 직접 실행하여 현재 LOC 표시
When not to use it
- →Running non-autonomous tasks
- →Executing tasks without a configuration file
Prerequisites
Limitations
- →Requires codeloop.yaml in project root
- →Loop execution requires external terminal
How it compares
It automates the management of long-running autonomous development loops, ensuring safe termination through stop hooks.
Compared to similar skills
codeloop side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| codeloop (this skill) | 0 | 5mo | Review | Intermediate |
| opencode-cli | 14 | 7mo | Review | Advanced |
| claude-automation-recommender | 47 | 2mo | Review | Beginner |
| mcp-integration | 21 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
opencode-cli
SpillwaveSolutions
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
mcp-integration
anthropics
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
hook-development
anthropics
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
swarm-advanced
ruvnet
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows