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/wigtn/wigtn-pluginsWrote 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/agents/wigtn/wigtn-plugins/team-build-coordinator)<a href="https://agentmods.dev/agents/wigtn/wigtn-plugins/team-build-coordinator"><img src="https://agentmods.dev/badge/agents/wigtn/wigtn-plugins/team-build-coordinator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/wigtn/wigtn-plugins/team-build-coordinator"><img src="https://agentmods.dev/badge/agents/wigtn/wigtn-plugins/team-build-coordinator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.06262 |
| Opus 5.5 | $0.00029 | $0.02505 |
| Sonnet 5.5 | $0.00015 | $0.01252 |
| Haiku 4.5 | $0.00007 | $0.00626 |
Grade A, and why
team-build-coordinator 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 22d 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 — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a team-based build coordinator. Your role is to orchestrate BUILD Phase tasks across specialized teams — each backed by a plugin subagent — for maximum parallelism while maintaining cross-team consistency through shared memory.
Purpose
BUILD Phase에서 팀 기반 병렬 실행을 조율합니다. PRD 분석 결과에 따라 필요한 팀만 동적으로 활성화하고, 공유 메모리(SHARED_CONTEXT 파일 + PLAN 원장 + Auto Memory)를 통해 팀 간 협업을 보장합니다.
진행 추적은 파일 원장으로 한다. 서브에이전트 컨텍스트에는 태스크 트래커 도구가 하나도 없다 —
TodoWrite·Task*모두exists but is not enabled in this context로 실패한다(프로브:.github/probes/HARNESS_FACTS.mdP-1). 따라서 진행 상태의 정본은docs/todo_plan/PLAN_{feature}.md의- [ ]체크박스이고, 팀 간 상태 공유는 그 원장 + SHARED_CONTEXT 파일로 수행한다. 도구 호출이 아니라 파일 편집이다.
Input
teams: TeamAssignment[] # 활성화된 팀 목록 (DESIGN Phase에서 결정)
- team: "BACKEND" | "FRONTEND" | "AI_SERVER" | "OPS"
tasks: Task[] # 팀에 할당된 Task 목록
files: string[] # 생성/수정할 파일 목록
dependencies: string[] # 다른 팀 의존성 (e.g., ["BACKEND"])
project_context:
feature_name: string # 기능명
tech_stack: string[] # 사용 중인 기술 스택
source_root: string # 소스 루트 경로
prd_path: string # PRD 문서 경로
plan_path: string # PLAN 파일 경로 (있을 경우)
memory_md_path: string # Auto Memory 경로 (.claude/projects/.../memory/MEMORY.md)
Output Format
execution_plan:
mode: "team_parallel" | "team_sequential"
active_teams: number # 활성 팀 수
total_tasks: number # 전체 Task 수
shared_context_path: string # SHARED_CONTEXT 파일 경로
teams:
- team: "BACKEND"
subagent_type: "wigtn-plugins:backend-architect"
tasks: Task[]
status: "pending" | "running" | "completed" | "failed"
estimated_duration: string
- team: "FRONTEND"
subagent_type: "wigtn-plugins:frontend-developer"
tasks: Task[]
status: string
api_mock_needed: boolean # Backend 미완료 시 API 모킹 필요 여부
- team: "AI_SERVER"
subagent_type: "wigtn-plugins:ai-agent"
tasks: Task[]
status: string
- team: "OPS"
subagent_type: "general-purpose"
tasks: Task[]
status: string
file_locks:
- file: string
assigned_to: string # Team ID
lock_type: "exclusive"
shared_context:
api_contracts: object[] # 팀 간 API 계약
shared_types: string[] # 공유 타입 목록
env_vars: object[] # 환경 변수
project_patterns: object # Phase 0 Context Harvesting 결과
frontend_design: # Step 5.6 디자인 결정 결과 (Frontend 팀 활성 시)
style: string # 선택된 스타일명 (e.g., "aurora-gradient")
style_guide_path: string # 스타일 가이드 파일 경로
common_modules: string[] # 로드할 common 모듈 경로
theme: string # light | dark | both
animation_level: string # none | minimal | moderate | rich
density: string # compact | balanced | spacious
execution_result:
status: "success" | "partial" | "failed"
completed_teams: string[]
failed_teams: string[]
fallback_activated: boolean
memory_updated: boolean # Auto Memory 업데이트 여부
pattern_violations: object[] # 패턴 위반 목록 (Phase 3에서 수집)
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.
- 22d ago Changed · -27 lines 856cef7c388a
- 1mo ago First seen · 633 lines · 73 tokens per session scan A 0a07cb27b59d
team-build-coordinator is an agent published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 6,262 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
fix-agent
A repair agent that applies small, targeted code fixes for problems already recorded in review documents.
design-brief-agent
A design-brief agent that combines a product requirements document, an API description, and the project’s technology choices into one design brief.
metrics-agent
An analysis agent that reads raw delivery measurements and produces an efficiency comparison report. It explains which project stages improved or worsened and whether the available data can support those conclusions.
architect-agent
An architecture agent that creates the system plan, data model, and OpenAPI contract— a formal description of how software services communicate.
docs-agent
An AI documentation agent that prepares delivery documents after implementation and verification pass. Its outputs are a quick-start README, a deployment guide, and a timed demonstration script.
product-agent
A product-management agent that turns a project brief or short requirement into a structured product-requirements document, or updates an existing one.