A setup wizard for installing and configuring a project work harness. It asks where the harness files and documentation should live, then creates missing files and adds selected guidance.

Use it to configure harness settings, create phase and documentation scaffolding, and choose how CLAUDE.md guidance is stored.

It provides project-specific setup while protecting existing files from accidental replacement. It also handles whether shared guidance belongs globally or inside the project.

setup — Skill for Claude Code and Codex by seungdeok: A setup wizard for installing and configuring a project…

Install

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.

agentmods

npx agentmods add skills/seungdeok/harness-starter/setup

Any agent

npx skills add seungdeok/harness-starter --skill setup

Clone the repo

git clone --depth 1 https://github.com/seungdeok/harness-starter

Made for: Claude Code, Codex.

Or install harness, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/seungdeok/harness-starter/setup.svg)](https://agentmods.dev/skills/seungdeok/harness-starter/setup)

Your own site

<a href="https://agentmods.dev/skills/seungdeok/harness-starter/setup"><img src="https://agentmods.dev/badge/skills/seungdeok/harness-starter/setup.svg" alt="Measured on agentmods" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,956 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00138	$0.05956
Opus 5	$0.00069	$0.02978
Sonnet 5	$0.00028	$0.01191
Haiku 4.5	$0.00014	$0.00596

Measured 3d ago against content hash 03ef99c55e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

test -f .gitignore && grep -qxF '.claude/worktrees/' .gitignore && echo 동일 || echo 없음

skills/setup/SKILL.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

setup — harness 설치 마법사

plugin 은 설치 시점에 스크립트를 못 돌리므로, 이 스킬이 프로젝트별 초기화를 대신해요. 결과물: .claude/settings.local.json 의 env.HARNESS_*(설정) + scope 에 따른 파일 scaffold.

절대 규칙: 기존 파일을 덮어쓰지 않아요. CLAUDE.md 는 append 만, scaffold 는 없는 파일만 생성. 유일한 예외는 프로젝트 scope 의 scripts/pipeline.py 예요 — 이건 plugin 번들의 복사본이라 갱신 대상이고, 확인을 받은 뒤에만 덮어써요 (§4 참고).

1. 질문 (AskUserQuestion, 필수)

세 가지를 한 번에 물어요:

scope — 하네스 파일을 어디에 둘지
- 글로벌 (기본): pipeline.py 는 plugin 번들(글로벌 캐시)을 그대로 사용. 프로젝트에는 phase 파일(phases/)만 생겨서 worktree 와 함께 움직여요. 프로젝트에 복사되는 코드 없음.
- 프로젝트: pipeline.py·docs 템플릿·CLAUDE.md 섹션을 모두 프로젝트 내부에 복사/생성. 사내 레포처럼 모든 것을 레포 안에 커밋해야 할 때.
docs 경로 — PRD/ADR/ARCHITECTURE 와 solutions(교훈 노트)를 둘 경로. 기본 docs. 사용자가 자유 입력으로 바꿀 수 있어요 (예: documents, docs/harness).
CLAUDE.md 처리 — 두 조각을 어디에 둘지 (조각은 §5 참고)
- A = 행동 가이드라인(1~6장) — 프로젝트와 무관한 내용이라 글로벌에 둬도 돼요
- B = ## Project Docs (@import 블록) — 프로젝트 상대경로예요
선택지:
- 둘 다 프로젝트 CLAUDE.md 에 (기본)
- A 는 글로벌(~/.claude/CLAUDE.md) · B 는 프로젝트 — 여러 레포에서 가이드라인을 공유할 때
- 건너뛰기
B 를 글로벌에 두는 선택지는 없어요. @ 는 파일 위치 기준 상대경로라 글로벌에선 절대경로로만 가능한데, 그러면 모든 프로젝트 세션에 특정 레포의 문서가 실려요. 질문에 이 한 줄을 함께 보여줘요.

2. 사전 스캔 (쓰기 전 필수)

§1 의 답변이 나오면, 파일을 하나도 건드리기 전에 대상 전체를 훑어 상태를 보여줘요. 재실행(플러그인 업데이트 후)에서 무엇이 그대로 남고 무엇이 바뀌는지 미리 알 수 있어야 해요.

이 표를 고치면 §3·§4·§5 의 해당 절차도 함께 갱신해요 — 판정 근거는 이 표에만 있어요.

scope 에 해당하는 행만 보여줘요.

대상	scope	판정 방법	상태
`.claude/settings.local.json` 의 `env.HARNESS_*`	공통	파일의 `env` 값 vs 이번 답변	없음/동일/다름
`.gitignore` 의 `.claude/worktrees/`	공통	`grep -qxF` (줄 단위)	없음/동일
`.gitignore` 의 `.claude/settings.local.json`	공통	`grep -qxF` (줄 단위)	없음/동일
`scripts/pipeline.py`	프로젝트	헤더 SHA vs 번들 SHA (§4-1)	없음/동일/다름/판정불가
`<docs>/` 템플릿 6종	프로젝트 (글로벌은 원할 때만)	파일 존재 여부만	없음/있음
`harness:guidelines` 마커 (조각 A)	§1 에서 추가하기로 했을 때	프로젝트 `CLAUDE.md` 와 `~/.claude/CLAUDE.md` 둘 다	없음/다름
`harness:docs` 마커 (조각 B)	§1 에서 추가하기로 했을 때	프로젝트 `CLAUDE.md` 만 (B 는 글로벌 불가)	없음/다름

Read the full file on GitHub · 330 lines

Files

What ships with it

8 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.

Changes

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 · 330 lines · 138 tokens per session scan B 03ef99c55e18

Subscribe to this mod's changes

setup is a skill published in the GitHub repository seungdeok/harness-starter (2 stars, last pushed 17d ago), licensed MIT. It adds 138 tokens to every session and 5,956 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

setup