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.
npx agentmods add skills/kimsanguine/hplan/strategynpx skills add kimsanguine/hplan --skill strategygit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/skills/kimsanguine/hplan/strategy)<a href="https://agentmods.dev/skills/kimsanguine/hplan/strategy"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/strategy.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.02393 |
| Opus 5 | $0.00029 | $0.01196 |
| Sonnet 5 | $0.00012 | $0.00479 |
| Haiku 4.5 | $0.00006 | $0.00239 |
Grade A, and why
strategy 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy — 비즈니스 모델 · 경쟁 해자 · 성장 루프 통합 설계
Running for: $ARGUMENTS
Core Goal
- 가치 창출(사용자 절감액/개선도)과 가치 포획(수익 모델) 사이의 균형을 설정하여 지속 가능한 비즈니스 구조 설계
- 모델 성능이 commodity화되는 시장에서 데이터·워크플로우·네트워크 차원의 경쟁 우위를 설계하여 방어선 구축
- 에이전트 사용 데이터가 자동으로 제품을 개선하는 성장 루프를 설계하여 시간이 지날수록 경쟁 격차가 벌어지는 구조 구축
비즈니스 모델 (biz-model)
수익 모델 선택 기준
| 모델 | 언제 적합한가 | 리스크 |
|---|---|---|
| Per-execution | 출력 단위가 명확할 때 | 사용량 불안 |
| Tiered subscription | 예측 가능한 사용 패턴 | 과/저 프로비저닝 |
| Outcome-based | 성과를 직접 측정할 수 있을 때 | 귀인 어려움 |
| Seat-based + usage | 팀 도구, 사용 강도 편차 큼 | 복잡성 |
| Freemium | 네트워크 효과·바이럴 가능성 | 전환율 |
가치 창출 분석 체크리스트
- Time Saved: [시간/주] × [시급] = [$/주]
- Error Reduction: [오류율 전] → [후] × [오류당 비용]
- New Capability: 기존에 불가능했던 것
- Scale Factor: 1인이 N인 분량을 처리 가능
단위 경제 (Unit Economics)
CPE(Cost Per Execution) = 총비용 ÷ 실행 횟수
목표 Gross Margin > 70% (SaaS 기준)
고객당 월 수익: $___
고객당 월 비용:
- LLM API: $___
- 인프라: $___
- 지원: $___
- CAC 분할상환: $___
가치 포획 원칙: 생성 가치의 10~20% 청구. 경쟁 대안(사람 처리, 아웃소싱)을 가격 상한 기준으로.
비용 구조 실패 신호: CPE가 목표 이윤율 초과 → API 최적화(모델 라우팅), 배치 처리, 또는 가격 인상 검토.
경쟁 해자 (moat)
6가지 Moat 유형 평가 (1~5점)
| Moat 유형 | 설명 | 점수 | 근거 |
|---|---|---|---|
| Data Flywheel | 사용 → 데이터 → 제품 개선 → 더 많은 사용 | /5 | |
| Workflow Lock-in | 사용자 일상 프로세스에 깊이 통합 | /5 | |
| Network Effects | 사용자 증가 → 모든 사용자 가치 증가 | /5 | |
| Switching Cost | 경쟁사로 이동하는 데 드는 비용/고통 | /5 | |
| Proprietary Knowledge | 독점 도메인 전문성 | /5 | |
| Speed/UX Moat | 대안 대비 10배 나은 경험 | /5 |
Copy-Time 18개월 미만이면 진정한 moat이 아님 — 보강 또는 전환 필요.
Maturity Stage
Stage 1 (Pre-PMF): moat 없음 → Copy-Time 3~6개월
Stage 2 (Growth): 단일/이중 moat 형성 → Copy-Time 12~18개월
Stage 3 (Expansion): 3+ moat 시너지 → Copy-Time 24~36개월
Stage 4 (Dominance): Core Power 극강 → Copy-Time 36~60개월+
Moat 조합 전략
Enterprise → Workflow Lock-in + Switching Cost 우선 (통합 깊이)
SMB → Speed/UX + Data Flywheel 우선 (빠른 가치 체감)
Platform → Network Effects + Data 우선 (양면 시장)
False Moat 제거 체크리스트
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 First seen · 234 lines · 58 tokens per session scan A efeff7163f7d
strategy is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 20d ago), licensed MIT. It adds 58 tokens to every session and 2,393 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.
Other skills, from other repositories
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
feature-dev
Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.
jira
Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).
precommit
Pre-commit checks — lint:fix -> build -> test.