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 agent-setupgit 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/agent-setup)<a href="https://agentmods.dev/skills/kimsanguine/hplan/agent-setup"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/agent-setup/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/agent-setup"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/agent-setup.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 | $0.00087 | $0.03365 |
| Opus 5.5 | $0.00035 | $0.01346 |
| Sonnet 5.5 | $0.00017 | $0.00673 |
| Haiku 4.5 | $0.00009 | $0.00336 |
Grade B, and why
agent-setup 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 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.
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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
두 영역을 단일 인터페이스로 통합한다:
| focus | 책임 | 출력 |
|---|---|---|
--focus instructions |
System Prompt + 7요소 + tool list + memory_config 완전 명세 | 즉시 배포 가능한 완전 Instruction 세트 |
--focus claude-md |
프로젝트 스캔 → CLAUDE.md / AGENTS.md 생성·개선 | 프로젝트 메모리 파일 (9룰 구조 적용) |
--focus both |
인스트럭션 먼저, 그 결과를 CLAUDE.md/AGENTS.md에 반영 | 통합 에이전트 환경 세팅 |
기본값:
--focus both— 새 에이전트 세팅에는 둘 다 필요하다.
Trigger Gate
Use This Skill When
- 새 에이전트 환경 전체 세팅 →
--focus both - 에이전트 System Prompt + 7요소만 설계 →
--focus instructions - 프로젝트 CLAUDE.md / AGENTS.md 생성·개선만 →
--focus claude-md - 기존 인스트럭션 최적화·디버깅 →
--focus instructions --level draft - 팀원 온보딩을 위한 프로젝트 컨텍스트 공유 →
--focus claude-md
Route to Other Skills When
- 컨텍스트 윈도우 예산 계획 →
deliver/prdSection 9 (메모리 설계) - PRD 공식 문서화 →
deliver/prd - 에이전트 설계 구현 전 4축 검증 →
deliver/conductor(Spec Compliance 게이트)
Boundary Checks
--focus미명시 →both기본값 진입 + 사용자 안내- Anti-Goals 없으면 instructions/both 모두 경고 (Anti-Goals는 에이전트 설계 필수)
- Tool 목록에 사용 조건 없으면 경고 (도구 남용 방지)
- CLAUDE.md는 프로젝트 레벨 컨텍스트 문서이지 에이전트 Instruction이 아님
Inputs
| 입력 | 출처 | 처리 |
|---|---|---|
--focus |
$ARGUMENTS |
instructions/claude-md/both 분기 |
--level draft|full |
$ARGUMENTS (instructions focus에만 적용) |
draft: PM 관점 초안, full: 완전 명세 |
| target | $ARGUMENTS (옵션 이후 나머지) |
에이전트명, 목적, 또는 프로젝트 경로 |
.claude/MEMORY.md |
프로젝트 루트 (있을 때) | 프로젝트 컨텍스트 자동 참조 |
agents/*/INSTRUCTION.md |
프로젝트 루트 (있을 때) | 기존 에이전트 인스트럭션 자동 참조 |
Instructions
You are setting up the agent environment with arguments: $ARGUMENTS
공통 Step 0 — focus 파싱
args = parse("$ARGUMENTS")
focus = args.get("--focus", "both") # 기본값: both
level = args.get("--level", "full") # instructions focus 시 기본값: full
target = args remainder after options
focus 미명시 시:
"--focus 미명시 —
--focus both기본값으로 진입합니다. 사용 가능:--focus instructions|claude-md|both"
focus: instructions
instructions의 역할: System Prompt + 7요소 + tool list + memory_config 완전 명세. "신입 직원 온보딩 문서" 수준.
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 · 324 lines · 87 tokens per session scan B 29327bb3c21d
agent-setup is a skill published in the GitHub repository kimsanguine/hplan (3 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 3,365 once invoked, about $0.0003 per session on Opus 5.5. 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
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 — no skill 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.
tech-spec
Tech spec generation and review. Use when: designing features, writing specs, spec review. Not for: requirements analysis (use req-analyze), implementation (use feature-dev), architecture advice (use codex-architect). Output: numbered tech spec document.