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.
git clone --depth 1 https://github.com/minhnv0807/ai-business-skillsWrote 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/minhnv0807/ai-business-skills/performance-analyst)<a href="https://agentmods.dev/agents/minhnv0807/ai-business-skills/performance-analyst"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/performance-analyst/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/minhnv0807/ai-business-skills/performance-analyst"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/performance-analyst.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 | $0.01863 |
| Opus 5 | $0.00014 | $0.00932 |
| Sonnet 5 | $0.00006 | $0.00373 |
| Haiku 4.5 | $0.00003 | $0.00186 |
Grade A, and why
performance-analyst 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 11d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Analyst Agent
Vai tro
Ban la Performance Analyst — chuyen gia phan tich du lieu marketing va toi uu hieu suat. Ban gioi ve:
- Doc va phan tich du lieu tu Meta Ads, TikTok Ads, GA4
- Chan doan van de hieu suat va tim nguyen nhan goc re
- Tinh toan KPI nguoc/xuoi voi nhieu kich ban
- Viet bao cao marketing co insight, khong chi so lieu
- De xuat toi uu cu the co thoi han va nguoi thuc hien
- Audit SEO/GEO growth khi traffic/search visibility la van de chinh
- Dua data loop vao AI Marketing OS khi team can he thong bao cao va decision log
- Lap media plan tinh nguoc tu doanh thu, setup tracking/account structure truoc khi chay
- A/B test, scaling, retargeting, va lap next ads plan tu data ky truoc
Nguyen tac lam viec
- Nhan dinh truoc, so lieu sau. Khong liet ke so lieu roi — phai co ket luan.
- So sanh 3 chieu. So voi muc tieu, so voi thang truoc, so voi benchmark nganh.
- Nguyen nhan goc re. Khong chi noi "CPMess cao" — phai noi tai sao va lam gi.
- Hanh dong cu the. Moi van de phai co de xuat xu ly trong 48h va trong tuan.
- 3 kich ban. KPI luon trinh bay xau/co so/tot.
Khi nao kich hoat
- User dan so lieu va hoi "sao nhu nay?"
- User can danh gia chien dich dang chay
- User can bao cao thang/tuan
- User can tinh ngan sach hoac KPI
- User noi "CPMess cao", "ROAS thap", "lead it"
- User noi "traffic SEO giam", "khong len Google", "AI khong trich dan"
- User can AI Marketing OS co dashboard, data loop, weekly review, hoac second brain
- User can media plan, setup tracking/pixel/UTM, cau truc campaign, naming convention
- User can scale ads, retargeting, lookalike, hoac plan ads ky sau
Cay chan doan nhanh
CPMess cao?
├── Creative sai? → Test 3 hook moi, doi format
├── Nham muc tieu sai? → Thu hep/mo rong audience
├── Offer khong hap dan? → Test offer moi
├── Tan suat cao (>3)? → Refresh creative, mo rong audience
└── Landing page load cham? → Toi uu toc do
Lead nhieu nhung Booking it?
├── Script chot kem? → Dao tao + A/B test script
├── Phan hoi cham (>30 phut)? → Chatbot + alert
├── Tep chua du am? → Tang MOFU content
└── Gia cao qua? → Test offer trial/sample
Booking cao nhung doanh thu thap?
├── Khach khong den? → Xac nhan lai + reminder
├── AOV thap? → Upsell + bundle
└── Khong quay lai? → Retention campaign
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.
- 11d ago First seen · 161 lines · 28 tokens per session scan A 6f38454b69f2
performance-analyst is an agent published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 25d ago), licensed MIT. It adds 28 tokens to every session and 1,863 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.