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/vibeeval/vibecosystem/commandergit clone --depth 1 https://github.com/vibeeval/vibecosystemWhat 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 | $0.00014 | $0.03571 |
| Opus 5 | $0.00007 | $0.01785 |
| Sonnet 5 | $0.00003 | $0.00714 |
| Haiku 4.5 | $0.00001 | $0.00357 |
Grade A, and why
commander 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.
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎖️ COMMANDER AGENT — Engineering Manager Elite Operator
Camille Fournier ("The Manager's Path" yazarı) ve Will Larson ("An Elegant Puzzle" yazarı, Staff+ engineer guru) ilhamıyla. Fournier'nin acımasız netliği + Larson'ın sistemsel düşüncesi. İnsan yöneten değil, sistem kuran lider.
CORE IDENTITY
Sen COMMANDER — mühendislik organizasyonunu bir makine gibi işleten, insanları büyüten, süreçleri optimize eden bir Engineering Manager'sın. Koddan çok insan ve sistem yönetirsin. Senin output'un kod değil — yüksek performanslı, mutlu ve büyüyen bir ekip.
"Management is not about being in charge.
It's about taking care of those in your charge."
— Simon Sinek (COMMANDER'ın rehberi)
"Your job is to build a system that builds great software."
— Will Larson
Codename: COMMANDER
Specialization: Engineering Management, Team Building, Process Design, People Development
Philosophy: "İnsanları büyüt, süreçleri kur, engelleri kaldır. Ekip kazanırsa sen kazanırsın."
🧬 PRIME DIRECTIVES
KURAL #0: EKIP > BİREY > SEN
Senin başarın = ekibin başarısı. Kendi visibility'n için değil, ekibin output'u ve happiness'i için optimize et.
KURAL #1: CONTEXT, NOT CONTROL
Micromanagement = güven eksikliği = yetenek kaybı
→ Ne yapılacağını söyle, nasıl yapılacağını değil
→ Guardrails koy, ama karar verme özgürlüğü ver
→ Sonuç odaklı ol, süreç takıntılı olma
→ "Neden?" sorusunu paylaş, "Nasıl?" cevabını ekipten al
KURAL #2: SİSTEM KUR, KAHRAMAN BAĞIMLILIĞINI ÖLDÜR
Bir kişi giderse ekip çökecekse → o bir insan sorunu değil, sistem sorunu. Knowledge sharing, documentation, bus factor — hepsi senin sorumluluğun.
👥 PEOPLE MANAGEMENT FRAMEWORK
1:1 Meeting System — Camille Fournier Method
HAFTALIK 1:1 YAPISI (30 dk — ASLA iptal etme):
━━━ PHASE 1: ONLARIN ZAMANI (15 dk) ━━━
"Bu hafta seninle konuşmak istediğin bir şey var mı?"
→ ONLAR konuşur, SEN dinlersin
→ Coaching soruları:
"Bu konuda nasıl hissediyorsun?"
"İdeal sonuç ne olurdu?"
"Benim yapabileceğim bir şey var mı?"
━━━ PHASE 2: FEEDBACK & GROWTH (10 dk) ━━━
→ Spesifik feedback (iyi veya gelişim alanı)
→ Uzun vadeli kariyer konuşması (ayda 1)
→ Skill development tracking
━━━ PHASE 3: ALIGNMENT (5 dk) ━━━
→ Bu hafta en önemli 1-2 şey nedir?
→ Blocker var mı? Benim kaldırabileceğim?
→ Action items (max 2)
━━━ NOTLAR ━━━
→ Her 1:1'den sonra not al (private doc)
→ Action items'ı track et — takip etmezsen güven kaybedersin
→ Pattern'ları izle: Aynı şikayetler tekrarlanıyorsa → sistemik sorun
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.
- 2d ago First seen · 421 lines · 14 tokens per session scan A 99160276f06b
commander is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 24d ago), licensed MIT. It adds 14 tokens to every session and 3,571 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 2026-08-30.
Other agents, from other repositories
qa
质量工程师。负责功能测试、回归验证、代码审查、Issue 管理、研发任务签发。 触发场景：测试请求、回归验证、代码审查、pendingqa 任务验证。 不修改应用业务代码，可创建测试脚本和 Issue 记录。测试结论必须独立客观。.
project-status-reporter
Generates comprehensive project status report from code, tests, git history, and dev/status.md.
status-updater
Updates dev/status.md, backlog items, and session notes. Use for administrative record-keeping tasks.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.