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 skills add kimsanguine/hplan --skill cost-simgit 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/cost-sim)<a href="https://agentmods.dev/skills/kimsanguine/hplan/cost-sim"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/cost-sim.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 | $0.00063 | $0.03075 |
| Opus 5 | $0.00032 | $0.01537 |
| Sonnet 5 | $0.00013 | $0.00615 |
| Haiku 4.5 | $0.00006 | $0.00308 |
Grade B, and why
cost-sim scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`cat .claude/MEMORY.md 2>/dev/null || echo "프로젝트 메모리 없음 — .claude/MEMORY.md를 생성하면 자동 참조됩니다."` How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
- 에이전트 운영 비용을 사전에 시뮬레이션하여 비용 폭탄을 방지한다.
- 토큰/API/외부 서비스 비용을 통합 모델링한다.
- 스케일 시나리오(1→10→100→1,000명)별 비용 곡선을 예측한다.
Trigger Gate
Use This Skill When
- 에이전트 타당성 평가 시 월간 비용을 추정해야 할 때
- build-or-buy 판단의 비용 축 근거가 필요할 때
- 에이전트 KPI에 비용 상한을 설정해야 할 때
- "이거 비용 얼마 들어?" 류의 질문이 나올 때
Route to Other Skills When
- 비용이 아닌 모델 성능/품질 기준이면 →
architect/orchestration --pattern router - 비용 추적/최적화(이미 운영 중)면 →
operate/ops-review - 비용이 과다해서 직접 구축 vs 외부 솔루션을 비교한다면 →
discover/assumptions --mode build-or-buy - 결정론적 p50/p90 마진 + free-user abuse 시뮬레이션 수치가 필요할 때 →
cogs-sentinel(hplan plugin)
Boundary Checks
- 이 스킬은 사전 시뮬레이션 전용이다. 실 비용 추적/모니터링은
operate/ops-review범위. - 모델 가격은 2026-03 기준이며 빠르게 변동함을 항상 명시한다.
- 추정치를 확정 수치로 표현하지 않는다 — 범위(range)로 제시.
Agent Cost Model
에이전트 비용은 일반 SaaS와 완전히 다른 구조입니다.
| 일반 SaaS | 에이전트 |
|---|---|
| 고정 인프라 비용 | 사용량 비례 비용 |
| 서버 × 시간 | 토큰 × 호출 수 × 모델 단가 |
| 예측 가능 | 사용 패턴에 따라 변동 |
| 스케일 시 점진 증가 | 스케일 시 비용 폭발 가능 |
가장 흔한 실수: MVP에서 $5/월이었던 비용이, 사용자 100명에서 $500/월로 폭증.
비용 구조 3요소
요소 1 — 토큰 비용 (Token Cost)
Input Cost = 입력 토큰 수 × 모델별 입력 단가
Output Cost = 출력 토큰 수 × 모델별 출력 단가
Total Token Cost = (Input + Output) × 호출 횟수
모델별 단가 (2026-03 기준, 1M 토큰당):
| 모델 | 입력 | 출력 | 특징 |
|---|---|---|---|
| Claude Haiku | $0.25 | $1.25 | 비용 효율, 단순 작업 |
| Claude Sonnet | $3.00 | $15.00 | 균형, 대부분의 작업 |
| Claude Opus | $15.00 | $75.00 | 최고 품질, 복잡한 판단 |
| GPT-4o | $2.50 | $10.00 | 범용 |
| GPT-4o-mini | $0.15 | $0.60 | 저비용 대안 |
⚠️ 모델 가격은 빠르게 변동합니다. 실제 계획 시 최신 가격 확인 필수.
요소 2 — 호출 빈도 (Call Frequency)
일간 호출 수 = 트리거 횟수 × 에이전트당 평균 API 호출 수
월간 호출 수 = 일간 × 30
에이전트 유형별 일반적 호출 패턴:
| 유형 | 트리거 빈도 | 회당 API 호출 | 월간 호출 |
|---|---|---|---|
| Cron Agent (1일 1회) | 30/월 | 2~5 | 60~150 |
| Monitor Agent (1시간) | 720/월 | 1~3 | 720~2,160 |
| On-demand Agent | 사용자 의존 | 3~10 | 변동 |
| Orchestrator | 하위 에이전트 수 의존 | 10~50 | 높음 |
요소 3 — 외부 API 비용 (External API Cost)
에이전트가 사용하는 외부 서비스 비용:
| 서비스 | 무료 티어 | 유료 단가 |
|---|---|---|
| Brave Search API | 2,000 쿼리/월 | $3/1,000 쿼리 |
| Google Search API | 100 쿼리/일 | $5/1,000 쿼리 |
| Telegram Bot API | 무제한 | 무료 |
| Notion API | 무제한 (개인) | 무료 |
| SendGrid | 100/일 | $0.001/이메일 |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 308 lines · 63 tokens per session scan B 52378c2b635c
cost-sim is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 63 tokens to every session and 3,075 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
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…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
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.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.