A command that runs one or more project agents, either one after another or at the same time. Project agents are saved instructions for handling specific kinds of work.

Use it to launch named agents, run several independent agents together, or pass work through a sequence of project agents.

It removes the need to find and start each agent manually, while allowing related tasks to run in parallel when they do not depend on each other.

agents — Command for coding agents by joonlab: A command that runs one or more project agents…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/joonlab/joonlab-claudecode-setting-for-share/agents

Clone the repo

git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-share

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/joonlab/joonlab-claudecode-setting-for-share/agents.svg)](https://agentmods.dev/commands/joonlab/joonlab-claudecode-setting-for-share/agents)

Your own site

<a href="https://agentmods.dev/commands/joonlab/joonlab-claudecode-setting-for-share/agents"><img src="https://agentmods.dev/badge/commands/joonlab/joonlab-claudecode-setting-for-share/agents.svg" alt="Measured on agentmods" height="20"></a>

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 891 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00030	$0.00891
Opus 5	$0.00015	$0.00445
Sonnet 5	$0.00006	$0.00178
Haiku 4.5	$0.00003	$0.00089

Measured 5d ago against content hash 2c6c3edb724a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude/commands/agents.md · 128 lines

What it actually says

Agent Execution Command

사용자가 에이전트 실행을 요청했습니다.

요청 분석

입력: $ARGUMENTS

실행 지침

Step 1: 에이전트 목록 확인

먼저 프로젝트의 에이전트 디렉토리를 확인:

.claude/agents/*.md (프로젝트 에이전트)
~/.claude/agents/*.md (사용자 에이전트)

각 에이전트 파일의 YAML frontmatter에서 name과 description을 읽어 표시.

Step 2: 요청 파싱

입력에서 다음을 파악:

에이전트 이름 (쉼표 또는 공백으로 구분된 여러 개 가능)
--parallel 플래그 유무
추가 컨텍스트/지시사항

Step 3: 실행 계획 출력 (필수!)

에이전트 실행 전 반드시 다음 형식으로 계획 출력:

에이전트 실행 계획

요청된 에이전트: 에이전트-이름-1, 에이전트-이름-2 ... 실행 모드: 병렬 / 순차 / 단일

에이전트별 역할

순서	에이전트	역할	의존성
1	`agent-1`	설명...	없음
2	`agent-2`	설명...	없음 (병렬) 또는 agent-1 완료 후

실행 플로우 다이어그램

병렬 실행 시:

Phase 1 (동시 실행)
┌──────────────┐  ┌──────────────┐
│  agent-1     │  │  agent-2     │
│  작업 내용   │  │  작업 내용   │
└──────┬───────┘  └──────┬───────┘
       │                 │
       └────────┬────────┘
                ▼
         [결과 병합]

순차 실행 시:

┌──────────────┐
│  agent-1     │
└──────┬───────┘
       │ 결과 전달
       ▼
┌──────────────┐
│  agent-2     │
└──────────────┘

Step 4: 에이전트 실행

단일/순차 실행: Task 도구를 순서대로 호출. 각 호출에서:

subagent_type: 에이전트 이름
description: 작업 요약 (3-5 단어)
prompt: 구체적인 작업 지시

병렬 실행 (--parallel): 하나의 응답에서 여러 Task 도구를 동시에 호출. 모든 Task 호출을 하나의 메시지 내 별도 tool_use 블록으로 작성하면 Claude가 동시에 실행함.

Step 5: 결과 종합

모든 에이전트 완료 후:

각 에이전트의 결과 요약
전체 작업 결과 정리
필요시 후속 작업 제안

사용 예시

목록 확인

/agents
/agents list

단일 실행

/agents slidev-generator 슬라이드 3개 추가

병렬 실행

/agents slidev-generator, slidev-validator --parallel

파이프라인 실행

/agents slidev-generator -> slidev-validator -> slidev-fixer

(순차 실행, 각 단계 결과를 다음 단계에 전달)

에이전트가 없는 경우

에이전트 디렉토리가 없거나 비어있으면: "이 프로젝트에 정의된 에이전트가 없습니다. .claude/agents/ 폴더에 에이전트를 추가하세요."

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 128 lines · 30 tokens per session scan A 2c6c3edb724a

Subscribe to this mod's changes

agents is a command published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 26d ago), licensed MIT. It adds 30 tokens to every session and 891 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

agents