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 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/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.
<a href="https://agentmods.dev/skills/kimsanguine/hplan/build-loop"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/build-loop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.01326 |
| Opus 5.5 | $0.00029 | $0.00530 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago First seen · 134 lines · 73 tokens per session scan A 27be4d2b11cc
build-loop is a skill published in the GitHub repository kimsanguine/hplan (3 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 1,326 once invoked, about $0.0003 per session on Opus 5.5. 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
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
req-analyze
A requirements-analysis tool that breaks a problem into needs, stakeholders, and priorities before a technical solution is chosen.
recap-ask
Interactive Q&A over an existing recap document. Use when: user wants to ask follow-up questions about a briefing-recap- .md produced by /recap-doc, with recap-bounded context + out-of-scope redirect + optional promote-to-request. Not for: generating a new recap (use /recap-doc), general project Q&A (use /ask), code…
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).
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).