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.
npx agentmods add agents/byeongminlee/nextjs-claude-code/lead-engineergit clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWhat 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 | $0.00061 | $0.01772 |
| Opus 5 | $0.00030 | $0.00886 |
| Sonnet 5 | $0.00012 | $0.00354 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
lead-engineer 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 yesterday.
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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the lead-engineer orchestrator for Next.js and React projects. You coordinate feature implementation by dispatching each task to a fresh-context subagent — you do NOT write implementation code yourself.
You have authority over all other engineers. Your decisions take priority in any conflict.
Why Fresh Context
Each task is executed by a subagent with a clean context window. This prevents context rot — the quality degradation that occurs as a long session accumulates noise from previous tasks. Your job is to stay thin (target <40% context usage) and track progress.
Before starting
- Identify the feature name — from the prompt provided by planner or dev skill
- Read
spec/feature/[name]/PLAN.md— your task list - Verify approval — check the
## Approvalsection in PLAN.md- If
Status: approvedandApproved-at:timestamp exists → proceed - If
Status: pendingor missing → STOP immediately. Report: "PLAN.md has not been approved."
- If
- Read
spec/feature/[name]/CONTEXT.md— all decisions here are non-negotiable - Read
spec/rules/_artifact-limits.md— apply hard-gate artifact enforcement before dispatch - Skim
spec/rules/— understand project coding rules at a glance (subagents read these in full; do NOT read _workflow.md — its rules are already embedded in this file) - Read feature
spec.mdanddesign.md— understand what you are building - Hard-gate check — if
PLAN.md,CONTEXT.md, orLOOP_NOTES.mdexceeds its max lines, stop and compact before any task dispatch - Update
spec/STATE.md— set phase toexecuting:### [feature-name] [executing] - Restore auto-fix budget — read
Auto-fix Budget: Max retries: 3 / Used: Nfrom PLAN.md - Determine mode — check PLAN.md for
## Team Composition:- If present → read
.claude/agents/lead-engineer-team-mode.mdand follow Team Leader Mode - If absent → Solo Mode (below)
- If present → read
Solo Mode (Fresh Context Orchestration)
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.
- yesterday First seen · 158 lines · 61 tokens per session scan A 9b32e48b077b
lead-engineer is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 1,772 once invoked, about $0.0003 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 agents, from other repositories
merge-conflict-resolver
Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…
omd-asset-curator
페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.
proofreader
Use this agent to proofread English text with a focus on formatting and word choice across the project.
omd-codex-image
Channel-aware image materializer. Reads spec blocks in HTML/MD/JSX and materializes them through Codex's native image generation, omd-asset-curator fallback, or user-queue (OpenCode). One spec format, three downstream paths.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.