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.
git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-shareWrote 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.
[](https://agentmods.dev/commands/joonlab/joonlab-claudecode-setting-for-share/pipeline)<a href="https://agentmods.dev/commands/joonlab/joonlab-claudecode-setting-for-share/pipeline"><img src="https://agentmods.dev/badge/commands/joonlab/joonlab-claudecode-setting-for-share/pipeline.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00027 | $0.00986 |
| Opus 5 | $0.00014 | $0.00493 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
pipeline 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Pipeline Command
에이전트 파이프라인 실행 요청입니다.
요청 분석
입력: $ARGUMENTS
파이프라인 파싱
입력에서 ->로 구분된 에이전트 체인을 파싱:
- 예:
generator -> validator -> fixer= 3단계 파이프라인 - 마지막
->이후 에이전트가 아닌 텍스트는 컨텍스트로 처리
실행 지침
Step 1: 파이프라인 분석
각 에이전트의 역할과 데이터 흐름을 분석:
- 각 단계의 입력/출력 정의
- 의존 관계 확인
- 병렬 가능 구간 식별
Step 2: 실행 계획 출력 (필수!)
파이프라인 실행 계획
파이프라인: $ARGUMENTS
총 단계: N개
데이터 흐름
[입력/컨텍스트]
│
▼
┌──────────────────────────────────┐
│ Stage 1: agent-name-1 │
│ ─────────────────────────────────│
│ 입력: 사용자 요청 │
│ 처리: {작업 설명} │
│ 출력: {출력 형태} │
└──────────────┬───────────────────┘
│ 결과 전달
▼
┌──────────────────────────────────┐
│ Stage 2: agent-name-2 │
│ ─────────────────────────────────│
│ 입력: Stage 1 결과 │
│ 처리: {작업 설명} │
│ 출력: {출력 형태} │
└──────────────┬───────────────────┘
│
▼
[최종 결과]
예상 흐름
| Stage | 에이전트 | 작업 | 예상 결과 |
|---|---|---|---|
| 1 | agent-1 |
작업 설명 | 출력물 설명 |
| 2 | agent-2 |
작업 설명 | 출력물 설명 |
| ... | ... | ... | ... |
Step 3: 순차 실행
각 단계를 순서대로 실행하며, 이전 단계의 결과를 다음 단계의 프롬프트에 포함:
Stage 1 실행:
Task(subagent_type="agent-1", prompt="[초기 컨텍스트]", description="Stage 1: ...")
Stage 2 실행 (Stage 1 완료 후):
Task(subagent_type="agent-2", prompt="이전 단계 결과:\n{stage1_result}\n\n다음 작업: ...", description="Stage 2: ...")
Step 4: 중간 결과 보고
각 단계 완료 시:
## Stage N 완료: agent-name
**상태**: 성공 / 실패
**결과 요약**: ...
**다음 단계로 전달**: ...
---
Stage N+1 시작...
Step 5: 파이프라인 완료 보고
## 파이프라인 실행 완료
### 실행 요약
| Stage | 에이전트 | 상태 | 주요 결과 |
|:-----:|----------|:----:|-----------|
| 1 | agent-1 | ✅ | 결과 요약 |
| 2 | agent-2 | ✅ | 결과 요약 |
### 최종 결과
{마지막 단계의 결과물}
### 후속 작업 제안
- 필요시 추가 작업 제안
특수 문법
병렬 단계 (쉼표)
/pipeline [generator, analyzer] -> validator
= generator와 analyzer를 병렬 실행 후, 둘 다 완료되면 validator 실행
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.
- 8d ago First seen · 160 lines · 27 tokens per session scan A 1a72688deb57
pipeline is a command published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 986 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.