agent-teams SKILL.md skillA
agent-teams from this-hw/claude-code-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add this-hw/claude-code-kit/agent-teams@git:20260907.f1c5a64Pins git:20260907.f1c5a64 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- this-hw/claude-code-kit
- Path
plugins/common/skills/agent-teams/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260907.f1c5a64, committed Sep 7, 2026
- First version recorded
- Apr 9, 2026
- Size
- 4,632 bytes
- Repository stars
- 4
- License
- MIT
SUPERSEDED by control-loop (kept through claude-code-kit 2.x; removed in the successor hiway-kit) — large-scale parallel work guidance. Routes 10+ parallel independent tasks to native dynamic workflows, with legacy experimental Agent Teams as fallback. See control-loop for the current multi-session delegation discipline.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Agent Teams / 대규모 병렬 처리 스킬 > **폐기 예고 (D-7 1단계, v2.19.0) — 2.x 에서는 제거되지 않는다.** 여기 담겨 있던 > 절차·규율은 `control-loop` 스킬로 흡수됐다 — 결정 대 조사를 페이즈로 나누고, > 워커 디스패치·검증·병합을 다룬다. **`claude-code-kit` 2.x 는 이 스킬을 끝까지 > 유지한다**: 스킬 삭제는 그 자체로 파괴적 변경이고, 2.20.0 은 파괴적 변경 없이 > 닫는 최종 릴리스이기 때문이다. 실제 제거는 후속 킷 > [`hiway-kit`](https://github.com/This-HW/hiway-kit) 에서 일어났다 — 거기로 옮겨 > 갈 때 `control-loop` 로 갈아타면 된다. > **Spec 2 / W-006 업데이트:** 대규모 병렬 오케스트레이션의 1순위는 이제 네이티브 > **dynamic workflow(`ultracode`)** 입니다. 실험적 자체 Agent Teams 조율은 네이티브가 > 흡수했으며, 이 스킬은 그 경로를 안내합니다. --- ## 사용 시점 ``` ✅ 대규모 병렬: - Large 작업 (10개 이상 파일 변경) - 병렬 가능한 독립 작업 (테스트 + 문서 + 구현) - 장기 실행 작업 ❌ 사용하지 않음: - Small/Medium 작업 → auto-dev 스킬 주도 플랫 위임 (main이 Agent 병렬 dispatch) - 순차 의존 작업 (A 완료 후 B) ``` > 오케스트레이션 모델 전체: `CLAUDE.md` → "Orchestration Model — Scale-Appropriate Primitives" --- ## 1순위: 네이티브 Dynamic Workflow (`ultracode`) 네이티브 워크플로우 엔진이 백그라운드에서 10~100+ 에이전트를 오케스트레이션하며, main 컨텍스트를 소비하지 않습니다. ``` 사용자가 프롬프트에 ultracode 키워드로 트리거: ultracode <대규모 작업 설명> - 백그라운드 오케스트레이션 + 라이브 에이전트 카운트 - /workflows 로 실행 현황 확인 ``` > ⚠️ `ultracode`는 **사용자 대화형 트리거 전용**입니다 — 스킬/비대화형에서 프로그래밍 > 호출이 불가합니다(2026.6 기준). 따라서 auto-dev는 Large 작업을 감지하면 청크로 …
Read the whole file at its exact version.
How to install
mdr add this-hw/claude-code-kit/agent-teams@sha256:d163151731572af6The line at the top of this page pins the label git:20260907.f1c5a64, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hrntsuphmbslec4u)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 9, 2026 and Sep 7, 2026, about one every 38 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260907.f1c5a64 latest | 2026-09-07 | f1c5a64 | 4,632 B | A | view · diff |
| git:20260907.02f34c9 | 2026-09-07 | 02f34c9 | 4,595 B | A | view · diff |
| git:20260613.bb5ed3b | 2026-06-13 | bb5ed3b | 3,742 B | A | view · diff |
| git:20260422.c75d972 | 2026-04-22 | c75d972 | 3,870 B | A | view · diff |
| git:20260409.94468e3 | 2026-04-09 | 94468e3 | 3,949 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4632 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
this-hw/claude-code-kit · 4 stars · license MIT · pushed 2026-09-09 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hrntsuphmbslec4u GET https://markdownregistry.com/api/v1/resolve?ref=this-hw/claude-code-kit/agent-teams GET https://markdownregistry.com/api/v1/blob/d163151731572af61529831b13c59ef2c16ef8e89e6e5061f22b6820cde3d58b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from this-hw/claude-code-kit
Every file in this-hw/claude-code-kit