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 commands/studiokjm/ai-harness-template/shapeupgit clone --depth 1 https://github.com/studioKjm/ai-harness-templateWrote 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/commands/studiokjm/ai-harness-template/shapeup)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/shapeup"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/shapeup.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 | $0.00000 | $0.00965 |
| Opus 5 | $0.00000 | $0.00483 |
| Sonnet 5 | $0.00000 | $0.00193 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
shapeup 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shapeup — Shape Up Command
Pitch 작성부터 Betting Table, 사이클 Hill Chart까지 Shape Up 워크플로우를 관리합니다.
Usage
/shapeup pitch new <title> [--appetite|-a small-batch|big-batch]
/shapeup pitch list [--state|-s <state>]
/shapeup pitch show <PCH-ID>
/shapeup pitch ready <PCH-ID> # 베팅 테이블 준비 완료
/shapeup pitch not-bet <PCH-ID> # 이번 사이클 기각
/shapeup bet <PCH-ID> [--cycle|-c <cycle>] [--by|-b <who>] [--rationale|-r <reason>]
/shapeup not-bet <PCH-ID>
/shapeup hill new [--cycle|-c <cycle-id>] # Hill Chart 스냅샷 생성
/shapeup hill show <HLC-ID> # ASCII 시각화
Shape Up 핵심 개념
| 개념 | 설명 |
|---|---|
| Appetite | 이 아이디어에 얼마나 투자할지 — 먼저 결정, 추정이 아님 |
| Small Batch | 1~2주, 소규모 팀 |
| Big Batch | 6주, 사이클 전체 투입 |
| Pitch | 문제 + appetite + 해결 방향 (세부 디자인 아님) |
| Betting Table | 다음 사이클에 어떤 pitch를 build할지 결정하는 회의 |
| Circuit Breaker | appetite 초과 시 자동 종료 — 연장 없음 |
| Hill Chart | 작업 진행 상태 시각화 (불확실 → 확실) |
| Cool-down | 사이클 사이 2주 — 자유 작업, 기술 부채, 다음 shaping |
Workflow
[Cool-down: Shaping]
1. /shapeup pitch new "주문 알림 재설계" --appetite big-batch
2. # pitch YAML 편집 — Problem, Solution, Rabbit Holes, No-Gos 작성
3. /shapeup pitch ready PCH-20260501-001
[Betting Table]
4. /shapeup pitch list --state ready # 후보 목록
5. /shapeup bet PCH-20260501-001 --cycle "2026-Q2-C1" --by "CEO" --rationale "가장 높은 retention 임팩트"
6. /shapeup not-bet PCH-20260501-002 # 이번 사이클 기각 (다음에 재심)
[Building]
7. /shapeup hill new --cycle "2026-Q2-C1"
8. # hill YAML 편집 — 각 scope의 위치 기록
9. /shapeup hill show HLC-20260501-001
Pitch States
shaping → ready → bet → building → done
↘ not-bet (이번 사이클 기각, 재pitch 가능)
↘ abandoned (영구 기각)
Hill Chart 읽기
Uphill (불확실) [HILLTOP] Downhill (실행 중)
0% 25% 50% 50% 75% 100%
|------|------|------|------|------|
● "결제 UI 재설계" ← 막 시작
● "API 연동" ← 탐색 중
● "알림 발송 로직" ← 방향 확정
● "E2E 테스트" ← 마무리 중
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 · 90 lines · 0 tokens per session scan A 9b386e33a9f5
shapeup is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 965 tokens. 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 commands, from other repositories
iteration-drive
Drive the active iteration to completion — Phase 2 Autonomous Execute, Phase 3 iteration-close, Phase 4 Create PR, Phase 5 PR merge-ready loop (prefer babysit/-babysit; optional greploop when repo has it; else CI fallback) until mergeable. Not Done until Phase 5 exit checklist passes.
init
Initialise the planning seed and record the human team, roles, and escalation channels.
statuswt
You are checking the status of all active worktree task files in the project.
changeRequest
你是 AI 产品工作流编排器。用户执行此命令，发起一次需求变更请求，你需要协调 AI 产品经理和 AI 产品主管完成完整的变更流程。.
projectStatus
你是 AI 产品工作流编排器。用户执行此命令，要求你汇报当前工作流的进展状态。.
boarding
항공기 이륙 1단계 — Linear 이슈를 읽어 요구사항·코드 영향 범위 정리.