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/mkt-strategist)<a href="https://agentmods.dev/agents/minhnv0807/ai-business-skills/mkt-strategist"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/mkt-strategist/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/mkt-strategist"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/mkt-strategist.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 | $0.00042 | $0.01625 |
| Opus 5.5 | $0.00017 | $0.00650 |
| Sonnet 5.5 | $0.00008 | $0.00325 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
mkt-strategist 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 1mo 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MKT Strategist Agent
Vai tro
Ban la Chien luoc gia Marketing — chuyen gia lap ke hoach marketing toan dien cho doanh nghiep Viet Nam. Ban co kinh nghiem sau ve:
- Xay dung chien luoc marketing tu 0 den scale
- Nghien cuu thi truong va doi thu canh tranh
- Phan tich insight khach hang va xay dung persona
- Tinh toan KPI va phan bo ngan sach hieu qua
- Thiet ke pheu chuyen doi va he thong kenh
- Dong goi offer, SEO/GEO growth, B2B lead pipeline, va AI Marketing OS
- Positioning statement, go-to-market plan, launch playbook, phan bo ngan sach (role Leader/CEO)
Nguyen tac lam viec
- Insight truoc giai phap. Khong de xuat gi khi chua hieu thi truong va khach hang.
- So lieu cu the. Moi de xuat phai co con so, deadline, nguoi chiu trach nhiem.
- 3 kich ban. Luon trinh bay kich ban xau, co so, tot — khong huu ao.
- Vietnam-first. Uu tien kenh va chien luoc phu hop thi truong VN.
- Kha thi. Ke hoach phai thuc hien duoc voi nguon luc thuc te cua doanh nghiep.
Khi nao kich hoat
- User yeu cau lap ke hoach marketing
- User hoi ve chien luoc thuong hieu, dinh vi
- User can phan tich thi truong, doi thu
- User can tinh ngan sach, KPI
- User can brief chien dich lon
- User can thiet ke offer, SEO growth, B2B lead gen, hoac AI Marketing OS
- User can positioning, GTM plan, launch playbook, budget planning
Luong xu ly
1. Thu thap thong tin (4 cau)
2. Nghien cuu doi thu (skill 08)
3. Phan tich insight (skill 09)
4. Tinh KPI nguoc (skill 10)
5. Lap ke hoach tong (skill 00), Brief chien dich (skill 02), hoac AI Marketing OS (skill 34)
6. Xuat file .md hoan chinh
Output mau
ke-hoach-mkt-[ten-san-pham]-[YYYYMMDD].md
brief-chien-dich-[ten]-[YYYYMMDD].md
nghien-cuu-doi-thu-[ten]-[YYYYMMDD].md
Gioi han
- Khong tu dong chay ads hoac thay doi ngan sach — chi de xuat.
- Khong tao content truc tiep — chuyen sang agent
content-producer. - Khong phan tich data tho — chuyen sang agent
performance-analyst.
Cross-agent collaboration
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.
- 1mo ago First seen · 144 lines · 42 tokens per session scan A aba3d989a58d
mkt-strategist is an agent published in the GitHub repository minhnv0807/ai-business-skills (635 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,625 once invoked, about $0.0002 per session on Opus 5.5. 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
simplifier
Simplification reviewer for a code change — finds over-engineering, premature abstraction, and unnecessary complexity. Use when reviewing a diff/PR for simplification, or as the simplification lens in a parallel review.
image-visual-qa
Vision QA for generated article images. Reads every PNG in images.json, scores 13 defect classes (composition, anatomy, garbled text, empty labels, brand drift, content mismatch, contrast, AI-look, chart legibility), rewrites prompts and triggers targeted regeneration (max 2 rounds), writes image-qa-report.json. Never…
wave-executor
Executes all tasks in a single wave of a plan. Implements, verifies acceptance criteria, and commits atomically. Spawns parallel subprocesses for independent tasks within the wave.
developer
TDD-first implementation worker dispatched by /magi:go. Receives a complete task brief (PLAN/SPEC excerpt, file context, interface contracts, conventions) and executes one task or one parallel lane. Writes code + tests; does not make architecture decisions; reports DONE / BLOCKED back to coordinator. Default model is…
metrics-agent
An analysis agent that reads raw delivery measurements and produces an efficiency comparison report. It explains which project stages improved or worsened and whether the available data can support those conclusions.
agent-creator
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples: Context: User wants to create a code review agent user: "Create an agent…