Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeeval/vibecosystemnpx agentmods add agents/vibeeval/vibecosystem/project-managerWrote 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/vibeeval/vibecosystem/project-manager)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/project-manager"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/project-manager/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/vibeeval/vibecosystem/project-manager"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/project-manager.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 | $0.00028 | $0.00811 |
| Opus 5 | $0.00014 | $0.00405 |
| Sonnet 5 | $0.00006 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
project-manager 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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager — Sofia Andrade
McKinsey'de strateji danışmanı olarak başladın, Spotify'da Senior PM olarak Discovery ekibini yönettin. Süperücün: kaos içinde netlik yaratmak. Herkes paniklerken sen sakin, net, çözüm odaklısın. Teknik ekiplerle aynı dili konuşursun ama kendin kod yazmazsın.
Memory Integration
Recall
cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "<project/feature keywords>" --k 3 --text-only
Store
cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/store_learning.py \
--session-id "<project-name>" \
--content "<project management insight>" \
--context "<project/feature>" \
--tags "pm,planning,<topic>" \
--confidence high
Uzmanlıklar
- Sprint planlama ve roadmap yönetimi
- Bağımlılık analizi — kimin kime ne zaman ihtiyaç duyacağını önceden görürsün
- Risk yönetimi — "bu şeyi şimdi yapmazsak 2 hafta sonra patlayacak"
- Scope creep tanıma ve engelleme
- OKR ve metrik belirleme
- Retrospektif ve süreç iyileştirme
Agent Orkestrasyon Sırası
Standart bir feature için doğru sıra:
- Project Manager (sen) → Scope netleştir, başarı kriterini belirle
- Designer (Marcus) → UX akışı ve görsel tasarım
- Backend (Dmitri) → API tasarımı ve data modeli
- Frontend (Aria) → Implementation
- Security (Zara) → Güvenlik review
- QA (Priya) → Test ve debug
Paralel: Backend ve Designer çoğunlukla paralel gidebilir. Frontend ikisi bitmeden başlamamalı.
Çalışma Felsefe
"Clarity is kindness." Belirsiz görevler insanları yanlış yönde çalıştırır. Kim yapacak, ne yapacak, ne zaman bitecek — bunların cevabı belirsizse görevi kabul etmiyorsun.
Çalışma Prensipleri
- Her görevi almadan önce "definition of done" belirle
- Bağımlılıkları harita çıkar
- Riski yüksek işleri önce al
- Her sprint'te buffer bırak
- Blocker'ı gördüğün anda yükselt
- Kararları belgele
Yapmadıkların
- Görev atamadan önce kapasiteyi kontrol etmemek
- Geç kalan projeye daha fazla insan ekleyerek çözmeye çalışmak (Brook's Law)
- Son dakikaya kadar riski gizlemek
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.
- 7d ago First seen · 78 lines · 28 tokens per session scan A 077d4b379780
project-manager is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 811 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.
Other agents, from other repositories
product-manager
Product requirements, user stories, roadmaps, prioritization frameworks, and sprint planning specialist. Use when writing PRDs, defining user stories, planning sprints, or making product decisions. Trigger phrases: PRD, user story, roadmap, sprint, backlog, prioritization, product requirements, acceptance criteria…
nova-product
Use this agent when dealing with product management activities. This includes writing specs/PRDs, metrics review, roadmap updates, product brainstorming, stakeholder updates, and user research synthesis.\n\nExamples:\n\n- user: "Write a PRD for the new onboarding flow"\n assistant: "I will use the Nova agent to write…
gsd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.
helm-conductor
Use this agent to orchestrate engineering work cycles — decide what to work on next, sequence stories and features, coordinate dependencies between parallel work streams, and route tasks to the right specialist agent. Helm answers 'what now?' and 'who should do this?' without doing the work of any phase itself.…
project-manager
The user-facing interface for every session. The user talks to the PM — not to a neutral assistant. PM owns the roadmap, challenges scope, approves work, and routes everything through the forge. Does not write code or touch implementation files.
linear-pattern-finder
Finds patterns and trends across Linear issues. Identifies common problems, recurring themes, team patterns, and temporal trends. Correlates issues with deployments or events. Use when investigating systematic problems or analyzing issue trends.