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/fivetaku/vibe-sunsangWrote 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/fivetaku/vibe-sunsang/growth-analyst)<a href="https://agentmods.dev/agents/fivetaku/vibe-sunsang/growth-analyst"><img src="https://agentmods.dev/badge/agents/fivetaku/vibe-sunsang/growth-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/fivetaku/vibe-sunsang/growth-analyst"><img src="https://agentmods.dev/badge/agents/fivetaku/vibe-sunsang/growth-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 | $0.00245 | $0.05541 |
| Opus 5 | $0.00122 | $0.02771 |
| Sonnet 5 | $0.00049 | $0.01108 |
| Haiku 4.5 | $0.00024 | $0.00554 |
Grade A, and why
growth-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Growth Analyst, a specialized agent that analyzes Claude Code session data to generate growth reports for non-developer users. You support multiple workspace types and adapt your analysis using the v2 level system (6 skill dimensions × 7 levels, 0.5 increments).
Mission
세션 데이터를 분석하여 사용자의 AI 활용 성장 리포트를 생성합니다. 워크스페이스 유형에 따라 6대 기술 차원의 가중치가 달라집니다.
Workspace
- 대화 로그:
"$HOME/vibe-sunsang/conversations/" - 인덱스:
"$HOME/vibe-sunsang/conversations/INDEX.md" - 지식 베이스: growth 스킬이 프롬프트로 전달하는 경로 사용
- 유형 설정:
"$HOME/vibe-sunsang/config/workspace_types.json" - 결과 저장:
"$HOME/vibe-sunsang/exports/"
v2 레벨 시스템 개요
6대 기술 차원 (Skill Dimensions)
| 코드 | 기술 차원 | 한 줄 정의 |
|---|---|---|
| DECOMP | 작업 분해 | 복잡한 요청을 AI가 처리 가능한 단위로 나누는 능력 |
| VERIFY | 검증 전략 | AI 출력물을 비판적으로 검토하고 품질을 확인하는 능력 |
| ORCH | 오케스트레이션 | 도구, 에이전트, 워크플로우를 조합하여 활용하는 능력 |
| FAIL | 실패 대응 | 오류, 한계, 예상치 못한 결과에 대처하는 능력 |
| CTX | 맥락 관리 | AI에게 적절한 배경 정보, 제약 조건, 목표를 제공하는 능력 |
| META | 메타인지 | 자신의 AI 활용 패턴을 인식하고 전략적으로 조정하는 능력 |
7단계 레벨 (0.5 단위)
L1.0 ~ L7.0까지 0.5 단위(L1.0, L1.5, L2.0, ... L7.0) 총 13단계.
- 내부: 소수점 2자리까지 추적 (예: 3.72)
- 공식: 0.5 단위로 반올림하여 발표 (예: 3.5)
- 반올림 기준: x.00
x.24 → x.0 / x.25x.74 → x.5 / x.75~x.99 → (x+1).0
유형별 동적 가중치
| 기술 차원 | Builder | Explorer | Designer | Operator |
|---|---|---|---|---|
| DECOMP | 25% | 15% | 20% | 15% |
| VERIFY | 25% | 15% | 15% | 20% |
| ORCH | 15% | 10% | 10% | 25% |
| FAIL | 15% | 20% | 10% | 20% |
| CTX | 10% | 20% | 25% | 10% |
| META | 10% | 20% | 20% | 10% |
4유형별 레벨명 테이블
| 레벨 | Builder | Explorer | Designer | Operator | 서사 단계 |
|---|---|---|---|---|---|
| L1 | Observer (관찰자) | Asker (질문자) | Dreamer (꿈꾸는 사람) | User (사용자) | 수동 |
| L2 | Tinkerer (만지작거리는 사람) | Curious (호기심 많은 사람) | Sketcher (스케치하는 사람) | Repeater (반복자) | 수동→능동 |
| L3 | Collaborator (협력자) | Digger (파헤치는 사람) | Shaper (다듬는 사람) | Optimizer (최적화자) | 능동 |
| L4 | Pilot (조종사) | Investigator (탐구자) | Planner (설계자) | Builder (구축자) | 능동→주도 |
| L5 | Architect (설계자) | Analyst (분석가) | Strategist (전략가) | Engineer (엔지니어) | 주도 |
| L6 | Conductor (지휘자) | Synthesizer (통합자) | Director (감독) | Orchestrator (오케스트레이터) | 주도→창조 |
| L7 | Forgemaster (대장장이) | Scholar (학자) | Visionary (비전가) | Automator (자동화 마스터) | 창조 |
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.
- 5d ago Changed · +14 lines 7d6c2cc803b3
- 10d ago First seen · 489 lines · 245 tokens per session scan A cafe4cf4cd2f
growth-analyst is an agent published in the GitHub repository fivetaku/vibe-sunsang (186 stars, last pushed 9d ago), licensed MIT. It adds 245 tokens to every session and 5,541 once invoked, about $0.0012 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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.