agent-teams

A guide for coordinating many independent coding tasks at the same time. It points large jobs toward a native workflow called ultracode and describes Agent Teams as a fallback.

In plain words
What is it for?
Use it to split large changes, such as implementation, tests, documentation, or refactoring, into parallel pieces.
Why use it?
It helps decide when parallel work is useful and when tasks should remain sequential because one depends on another.

Skill for Claude CodeCodex

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 skills/this-hw/claude-code-kit/agent-teams
Any agent
npx skills add This-HW/claude-code-kit --skill agent-teams
Clone the repo
git clone --depth 1 https://github.com/This-HW/claude-code-kit

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 940 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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00940
Opus 5 $0.00017 $0.00470
Sonnet 5 $0.00007 $0.00188
Haiku 4.5 $0.00003 $0.00094

Measured 2d ago against content hash 419dbe09b355, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-teams 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 2d 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.

plugins/common/skills/agent-teams/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Teams / 대규모 병렬 처리 스킬

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

⚠️ ultracode사용자 대화형 트리거 전용입니다 — 스킬/비대화형에서 프로그래밍 호출이 불가합니다(2026.6 기준). 따라서 auto-dev는 Large 작업을 감지하면 청크로 분할해 안내하고, 실제 대규모 병렬은 사용자가 ultracode로 시작합니다.

auto-dev와의 연계

auto-dev가 Work size: Large를 만나면:

  1. 독립 청크로 분할 (blockedBy 기반)
  2. 청크가 소수면 → 스킬 주도 병렬 dispatch
  3. 청크가 다수(10+)면 → 사용자에게 ultracode 트리거 안내

역할 배분 가이드 (병렬 구성 참고)

작업 유형 병렬 구성 (Teammates/에이전트)
기능 구현 implement-code, write-tests, sync-docs
리팩토링 plan-refactor, implement-code, verify-code
다관점 리뷰 /multi-perspective-review 사용 권장

권장 병렬 수: 3-8개 (그 이상은 ultracode에 위임).


레거시: 실험적 Agent Teams (선택)

CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 환경에서 TeamCreate + Task(team_name=...) 조합이 여전히 동작할 수 있으나, 네이티브 ultracode로 대체되었습니다. 신규 작업은 ultracode를 사용하세요. 이 경로는 하위호환을 위해서만 남아 있습니다.


multi-perspective-review와의 관계

상황 사용
다관점 리뷰 /multi-perspective-review
대규모 기능/리팩토링 ultracode (네이티브) 또는 auto-dev 청크 분할

참조

문서 위치
오케스트레이션 모델 CLAUDE.md → Orchestration Model
auto-dev 파이프라인 plugins/common/skills/auto-dev/SKILL.md
MPR 스킬 plugins/common/skills/multi-perspective-review/SKILL.md

Read the full file on GitHub · 95 lines

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.

  1. 2d ago First seen · 95 lines · 35 tokens per session scan A 419dbe09b355

Subscribe to this mod's changes

agent-teams is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 940 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.

Related

Other skills, from other repositories

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens