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/build-loopnpx skills add kimsanguine/hplan --skill build-loopgit 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/build-loop)<a href="https://agentmods.dev/skills/kimsanguine/hplan/build-loop"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/build-loop.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 | $0.00073 | $0.01326 |
| Opus 5 | $0.00036 | $0.00663 |
| Sonnet 5 | $0.00015 | $0.00265 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
build-loop 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 3d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
- "/build" 한 번으로 발견 → 리서치 → 설계 → PRD → 태스크 분해 → 팀 구현을 한 루프에서 완성한다.
- 단계 간 hand-off 마찰 0건 — 각 단계의 산출물이 다음 단계의 입력으로 직결.
- 하네스 + 병렬 팀 + Ralph Loop 자율 모드를 자동 결합.
전체 루프 (6 단계)
1. Discover (discover/opp-tree, assumptions (--mode build-or-buy 포함))
2. Research (web/internal research, competitor 분석)
3. Design (architect/orchestration (Hierarchical pattern 포함), memory-arch)
4. PRD (deliver/prd + mermaid 정합성 게이트)
5. Decompose (deliver/conductor — 작업 분해 + worktree)
6. Implement (deliver/conductor — 자율 모드 + 검증)
각 단계는 hplan 기존 스킬을 직렬 호출한다. 단계 간 산출물은 표준 경로에 저장.
Trigger Gate
Use This Skill When
- 사용자가
/build또는 "발견부터 구현까지" 요청 - 아이디어가 PRD/스펙으로 정리되지 않은 초기 상태
- 단계 간 결정을 사용자가 매번 내리기보다 자동 진행을 원할 때
- 4명+ 팀 + 자율 모드를 사용한 큰 스코프 작업
Route to Other Skills When
- 이미 PRD 있으면 → 5단계부터 시작 →
deliver/conductor - 빌드 게이트 통과 안 한 상태면 →
hplan/evidence-rubric먼저 - 한 단계만 필요하면 해당 스킬 직접 호출
Boundary Checks
- 빌드 게이트(
hplan/evidence-rubric) 미통과 시 자동 중단 — Stage 0 우선 - 자율 모드 진입 시 사용자 명시 승인 필요 ("ralph loop로 진행" 등)
Instructions
You are running build-loop for: $ARGUMENTS
Step 1 — Discover
discover/opp-tree로 기회 정의discover/assumptions로 리스크 가정 추출discover/assumptions --mode build-or-buy로 자체 빌드 정당성 확인
Step 2 — Research
- 도메인 문서 / 경쟁사 / 기존 유사 시도 조사
- 산출물:
research/<idea>.md
Step 3 — Design
architect/orchestration(Hierarchical pattern 포함)으로 역할 설계 및 조율 패턴architect/memory-arch로 메모리 계층
Step 4 — PRD
deliver/prd로 7섹션 PRD- mermaid workflow + userflow 두 다이어그램 의무
scripts/validate-mermaid.py로 정합성 검증 (P0-1 게이트)
Step 5 — Decompose
deliver/conductor로 작업 분해- 독립 작업 ≥2면 worktree 격리
Step 6 — Implement
deliver/conductor로 하네스 구성- 자율 모드 승인 받았으면 Ralph Loop 활성
- 백업 + dry-run + pending_inputs 표준
Failure Handling
| 실패 상황 | 감지 | 대응 |
|---|---|---|
| 빌드 게이트 미통과 | hplan checkpoint != approved | 즉시 중단 → /evidence-rubric 안내 |
| PRD mermaid 정합성 실패 | validate-mermaid.py exit≠0 | Step 4 재실행, missing requirements 보강 |
| 작업 분해 시 파일 충돌 | conductor Step 2 fail | 직렬 처리로 fallback |
| 자율 모드 미승인인데 진입 | "ralph loop" 키워드 부재 | 사용자 확인 필요 → 단계별 컨펌 모드 |
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.
- 3d ago First seen · 134 lines · 73 tokens per session scan A 27be4d2b11cc
build-loop is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 18d ago), licensed MIT. It adds 73 tokens to every session and 1,326 once invoked, about $0.0004 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
user-story-generator
Transforms requirements into user stories with Given/When/Then acceptance criteria ready for sprint planning and Jira. Use when user needs to write user stories, create Jira tickets, define acceptance criteria, or says "user stories", "acceptance criteria", "sprint backlog", "Jira tickets", "as a user I want"…
ambiguity-resolver
Structures a brief HANDED DOWN by a stakeholder (boss, exec, another team) into a one-page problem statement with scope boundaries and a named decision owner. Use when the PM says "мне спустили задачу", "I've been asked to look into Y", "руководство хочет X", "CEO попросил разобраться" — a request the PM didn't…
contract-testing-flywheel
Generate a structured onboarding backlog — in Jira, GitHub Issues/Projects, Azure DevOps, or as a manual markdown export — that drives a development team from zero to publishing both consumer and provider contract tests. Use when the user invokes /contract-testing-flywheel or asks to "kick off contract testing for a…
setup-initiative
Guides the PM through an initiative alignment checklist — metric, baseline, target, stakeholders, success/kill criteria. Use before a gate, when the PM says "setup initiative", "set the target", "define success criteria", "align on goals", or when the coverage map shows Frame incomplete. NOT a prerequisite for…
obsidian-kanban
Create and maintain Obsidian Kanban boards stored in Markdown, with a GTD-friendly workflow for capturing tasks, adding cards, organizing lists, and maintaining task details such as inline tags, Kanban date and time tokens, linked-note priority metadata, and subtasks. Use when working with Obsidian Kanban board files…
product-discovery
File-first orchestrator for product discovery and spec frameworks. Frames the problem with a Discovery Lead, Product Analyst, or System Architect role. Spawns parallel framework agents (Double Diamond, How Might We, Jobs to Be Done, user stories with INVEST, EARS for AI-coder specs, Gherkin), synthesizes into a PRD or…