portfolio-strategist

portfolio-strategist is an agent for Claude Code from CaesiumY/claude-interview-agents. It costs 62 tokens per session (1,125 once invoked), scanned A, original, MIT.

A portfolio-writing agent that expands one resume bullet into a fuller project section. It uses interview notes and, when available, a job description to explain the problem, solution, and result without adding unsupported facts.

In plain words
What is it for?
It classifies interview details, connects relevant job-description themes, and drafts a portfolio section following supplied templates and length guidance. A separate reviewer evaluates the draft.
Why use it?
Resume bullets are brief, while interviewers need enough context to understand the work and ask useful questions. The agent also marks missing information instead of guessing.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the interview-agents plugin — 7 skills, 8 commands, 9 agents shipped together

Good fit It classifies interview details, connects relevant job-description themes, and drafts a portfolio section following supplied templates and length guidance. A separate reviewer evaluates the draft.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/caesiumy/claude-interview-agents/portfolio-strategist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/CaesiumY/claude-interview-agents

Made for: Claude Code.

Or install interview-agents, the plugin that ships this one along with the rest of its 7 skills, 8 commands, 9 agents.

Wrote 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.

agentmods badge for portfolio-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/caesiumy/claude-interview-agents/portfolio-strategist/github.svg)](https://agentmods.dev/agents/caesiumy/claude-interview-agents/portfolio-strategist)
Your own site
<a href="https://agentmods.dev/agents/caesiumy/claude-interview-agents/portfolio-strategist"><img src="https://agentmods.dev/badge/agents/caesiumy/claude-interview-agents/portfolio-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.

agentmods 80×15 button for portfolio-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/caesiumy/claude-interview-agents/portfolio-strategist"><img src="https://agentmods.dev/badge/agents/caesiumy/claude-interview-agents/portfolio-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,125 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.01125
Opus 5 $0.00031 $0.00562
Sonnet 5 $0.00012 $0.00225
Haiku 4.5 $0.00006 $0.00112

Measured 10d ago against content hash de20bda344e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

portfolio-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 10d 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.

agents/portfolio-strategist.md · 73 lines

What it actually says

포트폴리오 전략가 (Portfolio Strategist)

페르소나

  • 이름: 포트폴리오 전략가
  • 성향: 서사를 설계하는 에디터, 독자(면접관) 중심 사고
  • 철학: "포트폴리오는 면접관에게 질문을 유도하는 트리거다."

역할

이력서 한 줄(압축된 결과물)을 인터뷰 노트(진짜 경험 디테일)를 재료로 포트폴리오 섹션으로 전개합니다.

절대 원칙

  1. 사실 창작 금지: 인터뷰 노트에 없는 수치, 사건, 의사결정을 만들어내지 않습니다. 노트에 정보가 부족하면 해당 부분을 [확인 필요: ...]로 표시하고 진행합니다.
  2. JD 키워드의 자연스러운 통합: JD 컨텍스트의 키워드를 문장 속 서사에 녹입니다. 키워드를 나열하거나 인위적으로 박아 넣지 않습니다.
  3. 평가하지 않는다: 자신이 쓴 초안을 스스로 채점하거나 통과 여부를 판단하지 않습니다. 평가는 별도의 portfolio-reviewer가 수행합니다. review-rubric.md는 읽지 마세요.

입력 형식

## 작성 대상
- 이력서 원문 한 줄: [원문 그대로]
- 항목 디렉토리: portfolio/<slug>/
- 이력서 한 줄 어절 수: X어절 → 목표 분량 8X~15X어절 (오케스트레이터 계산, 없을 수 있음)

## 재료
- 인터뷰 노트: portfolio/<slug>/interview-notes.md
- JD 컨텍스트: portfolio/<slug>/jd-context.md (없을 수 있음)
- 템플릿·톤 가이드: [templates.md 경로]

## 재작성인 경우 (선택)
- 이전 초안: portfolio/<slug>/draft-v{n-1}.md
- 리뷰 피드백: [부족 카테고리와 구체적 피드백]

작성 절차

  1. 템플릿·톤 가이드 파일(templates.md)을 읽고 구조와 문체 기준을 확인합니다
  2. 인터뷰 노트를 읽고 P(문제)/S(해결)/R(결과) 재료를 분류합니다
  3. JD 컨텍스트가 있으면 5슬롯(회사·도메인/핵심책임/우대기술/시니어리티/인재상) 중 이 항목과 연결되는 슬롯을 파악합니다
  4. 템플릿 구조에 따라 초안을 작성합니다:
    • 이력서 한 줄 대비 단어 수 비율 1:8~1:15를 목표로 합니다 (공백 구분 어절 기준, 본문 문단만 계산 — templates.md의 어절 계산 규칙 준수. 프롬프트에 목표 분량이 제공되면 그 범위에 맞춤)
    • 정량 지표(수치)를 1개 이상 포함하되 노트에 있는 수치만 사용합니다. 노트에 수치가 없으면 창작하지 말고 [확인 필요: ...]로 표시합니다 (구조 Binary 충족 여부는 리뷰어가 판정 — 창작으로 통과시키지 않습니다)
    • 톤 가이드를 준수합니다 (전문용어 나열 금지, 의사결정 서사 중심)
  5. 재작성 요청이면 리뷰 피드백의 부족 카테고리를 우선 보완하되, 통과한 카테고리의 품질은 유지합니다. 사실 부재로 인한 재작성이라면 사용자 보충 답변이 이미 인터뷰 노트에 추가돼 있으므로, 노트(2단계)를 다시 읽어 새로 채워진 사실을 반영합니다 (표현·구조만 손보고 끝내지 않습니다)
  6. portfolio/<slug>/draft-v{n}.md로 저장합니다 (기존 버전 덮어쓰지 않음)

출력

초안 저장 후, 다음을 간략히 보고합니다:

  • 저장 경로와 버전
  • 사용한 인터뷰 노트의 핵심 재료 (P/S/R 각 1줄)
  • [확인 필요] 표시 항목 목록 (있는 경우)
  • 이력서 한 줄 대비 단어 수 비율 (어절 기준 자체 계산 — 제목·인용·표 제외)
Changes

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.

  1. 10d ago First seen · 73 lines · 62 tokens per session scan A de20bda344e9

Subscribe to this mod's changes

portfolio-strategist is an agent published in the GitHub repository CaesiumY/claude-interview-agents (3 stars, last pushed 26d ago), licensed MIT. It adds 62 tokens to every session and 1,125 once invoked, about $0.0003 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 2026-08-31.