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/prdnpx skills add kimsanguine/hplan --skill prdgit 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/prd)<a href="https://agentmods.dev/skills/kimsanguine/hplan/prd"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/prd.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 | $0.00145 | $0.10132 |
| Opus 5 | $0.00072 | $0.05066 |
| Sonnet 5 | $0.00029 | $0.02026 |
| Haiku 4.5 | $0.00015 | $0.01013 |
Grade B, and why
prd 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 4d 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."` How it starts
The opening of the file, as written. The whole thing — 830 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context (auto-injected)
프로젝트 메모리:
!cat .claude/MEMORY.md 2>/dev/null || echo "프로젝트 메모리 없음."
현재 이슈 (Linear/GitHub):
!linear issue list --mine --status "In Progress" --limit 5 2>/dev/null || gh issue list --limit 5 --json number,title --jq '.[] | "#\(.number) \(.title)"' 2>/dev/null || echo "이슈 트래커 연결 없음."
Unified PRD Template — 15 Sections
Core Goal
- 고객(인간) 대상 제품과 그 안의 LLM 에이전트 사양을 단일 PRD 15-section으로 통합
- "사람·문제·결정"이 상단 (1-6), "에이전트·실행 사양"이 중단 (7-11), "지표·가설·실패"가 하단 (12-14)
- 1인 빌더 60일 사이클 + 5명 사랑 검증 + Live URL 도착까지 같은 PRD를 매번 갱신
Trigger Gate
Use This Skill When
- 새 SaaS·버티컬 앱·1인 빌더 제품의 정식 사양 문서화 (PRD v0.1)
- 5명 사랑 검증 직전 PRD v0.2~v0.3 갱신
- 도메인 특화 제품 (법률·교육·의료) — 사용자 페르소나·JTBD가 핵심
- 내부용 LLM 에이전트 spec — Section 1·3에 페르소나 = 내부 사용자, Section 7-11에 에이전트 상세
- 투자자·파트너·외부 엔지니어에게 제품 사양 공식 전달
- PRD §11 Output Spec 작성 후 UI 변형 4개를 비교해 설계 방향을 결정할 때 →
--mode design-shotgun - §6 Now/Next/Later를 시각적 로드맵으로 변환하거나 백로그를 RICE로 우선순위화할 때 →
--mode roadmap [generate|rice|prioritize]
Route to Other Skills When
- 배포 전 QA 라운드 →
deliver/qa-checklist --mode adversarial(PRD §15 QA Pool + PERSONA_SPECS 기반 동적 에이전트 구성) - ICP·beachhead 정의 →
discover/customer-reach로 라우팅 후 Section 1에 주입 - JTBD·Switch Interview →
discover/customer-reach로 라우팅 후 Section 2에 주입 - 결정 옵션 매트릭스 →
discover/assumptions --mode build-or-buy(6축) +architect/orchestration(4패턴) +discover/hitl(5레벨) → Section 4 - 제외사항 자동 인용 →
hplan/exclusions레지스트리 fuzzy match → Section 5 - MVP 비용 시뮬레이션 →
discover/cost-sim(lognormal p50/p90) → Section 6 - Instruction 7요소 상세 설계 →
deliver/agent-setup→ Section 7 보강 - OKR 정의 →
operate/metrics-design --step okr(dual-axis) → Section 12 - 가설 분해 →
discover/assumptions(4축) → Section 13 - 신뢰성·SLO →
operate/reliability→ Section 14 - Multi-ecosystem export →
hplan/handoff(Spec-Kit / Kiro / GStack / Claude Code) - 사용자 인터페이스가 있는 LLM 에이전트 (UI/UX 강제) →
deliver/respect --mode brief(RESPECT.md 디자인 시그니처) → Section 11 출력 사양 보강 - design-shotgun 변형 선택 후 TC 자동 생성 →
deliver/qa-checklist
What ships with it
7 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.
- 4d ago First seen · 830 lines · 145 tokens per session scan B f3d6dc5c9090
prd is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 19d ago), licensed MIT. It adds 145 tokens to every session and 10,132 once invoked, about $0.0007 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…
orchestrate
Agent-driven workflow orchestration (v1 report-only). Use when: declaring an intent (audit/research/feature shape) and wanting a planner agent to derive the skill workflow, preview it, and run read-only fanout with fail-closed no-change verification. Not for: executing mutating steps (v1 emits them as…
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 MCP. 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.