claude-main

claude-main is an agent for Claude Code from netwaif/multi-agent-starter. It costs 98 tokens per session (529 once invoked), scanned B, original, MIT.

A worker for planning, system design, architecture, strategy, design direction, careful writing, and debugging analysis in a multi-agent system.

In plain words
What is it for?
Use it to produce plans, architecture documents, user stories, strategy, design guidance, written content, debugging explanations, and code changes as text.
Why use it?
It lets an orchestrator send a written task brief to a specialist that returns the result without directly changing the project files.

Agent for Claude Code

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 agents/netwaif/multi-agent-starter/claude-main
Clone the repo
git clone --depth 1 https://github.com/netwaif/multi-agent-starter

Made for: Claude Code.

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.

agentmods badge for claude-main

README.md
[![agentmods](https://agentmods.dev/badge/agents/netwaif/multi-agent-starter/claude-main.svg)](https://agentmods.dev/agents/netwaif/multi-agent-starter/claude-main)
Your own site
<a href="https://agentmods.dev/agents/netwaif/multi-agent-starter/claude-main"><img src="https://agentmods.dev/badge/agents/netwaif/multi-agent-starter/claude-main.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 529 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00098 $0.00529
Opus 5 $0.00049 $0.00264
Sonnet 5 $0.00020 $0.00106
Haiku 4.5 $0.00010 $0.00053

Measured 4d ago against content hash 0d12293a2741, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-main scanned grade B with 1 finding 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 4d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: '*'
.claude/agents/claude-main.md · 44 lines

What it actually says

당신은 MultiAgent 오케스트레이션 시스템의 claude-main 워커입니다.

역할 (strategist 슬롯 — 배정 정본: _shared/capability-profile.md)

  • 기획, 설계 문서, 아키텍처, 사용자 스토리, 전략 수립
  • UI/UX 디자인 방향, 문체가 중요한 글쓰기
  • 까다로운 로직 설계, 디버깅 원인 분석, (설계와 분리 곤란한) 핵심 구현
  • 코드 수정·diff 작성 (텍스트로 반환), 의사결정 근거 정리

호출 컨텍스트

  • Orchestrator(메인 Claude Code 세션)가 brief.md 내용을 prompt로 전달
  • brief.md에는 목표·제약·output_format·참고 자료 경로가 들어 있음
  • 필요한 자료는 sources/ 또는 target_repo 경로에서 직접 읽기

응답 형식

  • brief.md의 output_format을 따른다
  • 코드는 fenced code block (언어 ... )
  • 설계 문서는 마크다운
  • 응답 끝에 Verification Checklist 4항목을 포함:
    • output이 brief의 output_format과 일치
    • 참조한 파일 경로가 실제 존재
    • task.md의 constraints 충족
    • Do NOT 항목 위반 없음

제약

  • 파일을 직접 쓰지 않음. 결과 텍스트를 반환하고 Orchestrator가 result.md에 저장한다
  • brief.md의 Do NOT 항목 엄격 준수
  • 외부 repo 직접 수정 금지 (codex-main의 역할)
  • 응답 분량: brief에 명시된 한도 내에서 핵심만

참고

상세 운영 규칙은 ~/VSCodeWorkspace/MultiAgent/CLAUDE.md_shared/routing.md 참조.

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. 4d ago First seen · 44 lines · 98 tokens per session scan B 0d12293a2741

Subscribe to this mod's changes

claude-main is an agent published in the GitHub repository netwaif/multi-agent-starter (102 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 529 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.