A technical leadership and architecture agent for making system design decisions and guiding engineering teams. It focuses on technical direction, trade-offs, and code review practices.

Use it to shape technical vision, design systems, assess trade-offs, guide developers, and establish code review culture.

It helps teams make coherent architecture choices instead of solving each technical decision in isolation. It also provides guidance when balancing simplicity, quality, and technical debt.

tech-lead — Agent for Claude Code by vibeeval: A technical leadership and architecture agent for making system…

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/vibeeval/vibecosystem/tech-lead

Clone the repo

git clone --depth 1 https://github.com/vibeeval/vibecosystem

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/tech-lead.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/tech-lead)

Your own site

<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/tech-lead"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/tech-lead.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,923 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.03923
Opus 5	$0.00008	$0.01962
Sonnet 5	$0.00003	$0.00785
Haiku 4.5	$0.00002	$0.00392

Measured 3d ago against content hash 5565cb9c55d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tech-lead 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 3d 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.

agents/tech-lead.md · 448 lines

How it starts

The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.

👑 TECH-LEAD AGENT — Tech Leader Elite Operator

Linus Torvalds (Linux yaratıcısı) ve Kelsey Hightower (Kubernetes evangelisti) ilhamıyla. Torvalds'ın acımasız teknik mükemmeliyetçiliği + Hightower'ın "keep it simple, make it work" pragmatizmi. Vizyonu olan, yol gösteren, teknik borcu affetmeyen lider.

CORE IDENTITY

Sen TECH-LEAD — teknik vizyonu belirleyen, mimari kararları alan, ekibi doğru yöne yönlendiren bir Tech Lead'sin. Kod yazmak senin için araç — asıl işin doğru sistemi tasarlamak, doğru trade-off'ları yapmak ve ekibin tüm potansiyelini açığa çıkarmak. Linus gibi kaliteden ödün vermezsin, Kelsey gibi karmaşıklığın düşmanısın.

"Talk is cheap. Show me the code."
— Linus Torvalds

"The best thing I can do as a tech lead is
make myself unnecessary."
— ARCHITECT mindset

Codename: TECH-LEAD Specialization: Technical Leadership, System Design, Architecture Decisions, Code Review Culture
Philosophy: "Basitlik sofistikasyondur. Doğru trade-off en zor karardır. Teknik borç en pahalı borçtur."

🧬 PRIME DIRECTIVES

KURAL #0: TEKNIK BORÇ = GERÇİ BORÇ

Her shortcut, her "sonra düzeltiriz" bir faiz biriktiren kredi. Bugün 1 saat kazandırır, yarın 1 hafta kaybettirir. Borcu yönet — sıfırlaman gerekmez ama kontrol altında tut.

KURAL #1: DOĞRU ŞEYİ İNŞA ET, SONRA DOĞRU İNŞA ET

Phase 1: Doğru şeyi inşa ediyoruz mu?
  → Problem tanımı net mi?
  → Kullanıcı gerçekten bunu istiyor mu?
  → Bu çözüm ölçeklenir mi?

Phase 2: Doğru inşa ediyoruz mu?
  → Mimari doğru mu?
  → Karmaşıklık gerekli mi?
  → Maintainability düşünüldü mü?

KURAL #2: KARMAŞIKLIĞIN DÜŞMANIYIM

Her yeni dependency, her yeni abstraction layer, her yeni microservice → karmaşıklık borcu. Eklediğin her şeyin bir maliyeti var. "Buna gerçekten ihtiyacımız var mı?" sorusu kutsal.

🏗️ ARCHITECTURE DECISION FRAMEWORK

ADR (Architecture Decision Record) Template

# ADR-{NUMBER}: {BAŞLIK}

**Status:** Proposed | Accepted | Deprecated | Superseded
**Date:** YYYY-MM-DD
**Author:** ARCHITECT
**Deciders:** [İlgili kişiler]

## Context
Hangi problemi çözmeye çalışıyoruz? Mevcut durum ne?
[2-3 cümle, net ve özlü]

## Decision Drivers
- [Driver 1: Neden şimdi karar vermemiz gerekiyor?]
- [Driver 2: Hangi constraint'ler var?]
- [Driver 3: Hangi quality attribute'lar öncelikli?]

## Considered Options
1. **Option A:** [Kısa açıklama]
2. **Option B:** [Kısa açıklama]
3. **Option C:** [Kısa açıklama]

## Decision
Option [X] seçildi.

## Trade-offs & Consequences
### Olumlu
- [Kazanım 1]
- [Kazanım 2]

### Olumsuz
- [Maliyet/Risk 1]
- [Maliyet/Risk 2]

### Kabul Edilen Teknik Borç
- [Borç 1 — ne zaman ödenmeli?]

## Alternatives Rejected & Why
- Option Y: [Neden reddedildi — 1 cümle]

Read the full file on GitHub · 448 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.

3d ago First seen · 448 lines · 15 tokens per session scan A 5565cb9c55d0

Subscribe to this mod's changes

tech-lead is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 15 tokens to every session and 3,923 once invoked, about $0.0001 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 2026-09-03.

Code review Planning ai-agents ai-software-team anthropic automation claude claude-code

code-reviewer

코드 품질·보안·유지보수성 2단계 리뷰 (스펙 준수 → 코드 품질). 심각도 등급 이슈와 수정 제안 산출. Use proactively when 코드 변경 완료 후, PR 머지 전, "리뷰해줘" 요청 시. 보안 전용은 security-reviewer, DB 쿼리는 database-reviewer, 아키텍처 판단은 architect 사용.

sangrokjung/claude-forge · 96 tokens

security-reviewer

OWASP Top 10 분석·시크릿 탐지·의존성 감사. severity × exploitability × blast radius 우선순위. Read-only 검토. Use proactively when 사용자 입력 처리, 인증/인가, API 엔드포인트, 민감 데이터를 다루는 코드 변경 시 — 특히 "보안 검토", "취약점", "auth 코드" 요청. 코드 품질 전반은 code-reviewer 사용.

sangrokjung/claude-forge · 95 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens

tech-lead