project-inception

project-inception is a skill for Claude Code from bunhine0452/Ocul-PM. It costs 85 tokens per session (1,863 once invoked), scanned A, original, MIT.

A planning workflow for starting a project or a new feature area tracked by ocul-pm. It researches possible technology choices, agrees on a specification with the user, and creates planning documents including completion criteria.

In plain words
What is it for?
Use it at the start of a tracked project or feature area to research the stack, define the problem and boundaries, settle the specification, and create an EVALS.md file and detailed plan.
Why use it?
It turns an idea into documents that the project's planning and review tools can use. It also prevents important choices and success conditions from being invented without discussion or research.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the oculpm plugin — 5 skills, 5 commands shipped together

Good fit Use it at the start of a tracked project or feature area to research the stack, define the problem and boundaries, settle the specification, and create an EVALS.md file and detailed plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bunhine0452/ocul-pm/project-inception
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.

Any agent
npx skills add bunhine0452/Ocul-PM --skill project-inception
Clone the repo
git clone --depth 1 https://github.com/bunhine0452/Ocul-PM

Made for: Claude Code.

Or install oculpm, the plugin that ships this one along with the rest of its 5 skills, 5 commands.

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.

agentmods badge for project-inception

README.md
[![agentmods](https://agentmods.dev/badge/skills/bunhine0452/ocul-pm/project-inception/github.svg)](https://agentmods.dev/skills/bunhine0452/ocul-pm/project-inception)
Your own site
<a href="https://agentmods.dev/skills/bunhine0452/ocul-pm/project-inception"><img src="https://agentmods.dev/badge/skills/bunhine0452/ocul-pm/project-inception/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.

agentmods 80×15 button for project-inception

Your own site · 80×15
<a href="https://agentmods.dev/skills/bunhine0452/ocul-pm/project-inception"><img src="https://agentmods.dev/badge/skills/bunhine0452/ocul-pm/project-inception.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,863 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01863
Opus 5 $0.00043 $0.00932
Sonnet 5 $0.00017 $0.00373
Haiku 4.5 $0.00009 $0.00186

Measured 10d ago against content hash c18a1507ef2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

project-inception 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 10d 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.

plugin/oculpm/skills/project-inception/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

project-inception — 아이디어를 설계 산출물로

새 프로젝트(또는 새 기능 영역)를 시작할 때, 아이디어를 ocul-pm 파일 체계에 그대로 물리는 4종 산출물로 바꿉니다. 성공 기준은 문서를 "만드는 것"이 아니라 — 기존 도구가 무수정으로 소비하는 것입니다 (discussion→플래너 승격, EVALS→회고 추이, rules→에이전트 자동 로드).

STAGE 0 — 문제 파악 (리서치 방향을 정할 만큼만)

.oculpm/ 이 없는 새 저장소라면 먼저 사용자에게 "이 프로젝트를 ocul-pm 으로 추적할까요?" 를 물어보고, 동의를 받으면 project_init 도구(confirm=true)로 초기화합니다 — 동의 없이/선제적으로 호출하지 않습니다. 도구가 없으면 ocul-pm 앱에서 프로젝트 추가를 안내하세요.

정보가 부족한 채 계획을 지어내지 마세요. 단, 여기서는 리서치의 방향을 정하는 데 필요한 최소만 묻습니다 — 문제(누구의 어떤 문제), 완성의 정의(첫 데모 한 장면), 비목표, 플랫폼·강한 제약(기한·오프라인·보안). 아이디어에 이미 담긴 것은 다시 묻지 않습니다. 답을 받아 .oculpm/agents/discussion-spec.md 규격대로 .oculpm/discussion/<slug>/discussion.md 를 만들고 ## 문제 정의 를 채웁니다.

STAGE 1 — 환경 탐색 (웹 리서치)

사용자에게 더 묻기 전에, 웹 검색(WebSearch/WebFetch)으로 환경을 직접 조사합니다. 문제에 맞는 후보 스택 2~3개에 대해:

  • 현재 안정 버전과 권장 조합 (프레임워크 + 빌드 도구 + 테스트 러너)
  • 공식 스캐폴드 명령·battle-tested 보일러플레이트
  • 해당 도메인의 표준 라이브러리·베스트 프랙티스·흔한 함정
  • 필요한 개발 환경 (런타임 버전, 패키지 매니저, 필수 CLI)

조사 결과를 discussion 의 ### 방안 {#opt-id} 후보안에 버전·출처와 함께 기록합니다. 기억 속 버전을 단정하지 말 것 — 검색으로 확인한 것만 적습니다.

STAGE 2 — 대화로 최적 사양 확정

리서치 근거를 들고 사용자와 대화해 사양을 함께 확정합니다. 질문은 기능 나열이 아니라 제품 렌즈로 팝니다 — 누가 쓰는가, 어떤 가치 가설인가, 안 만들면 사용자는 뭘 하는가(비사용 대안), 성공을 무엇으로 알아보는가. 남은 미결(선호 언어·프레임워크, 규모, 비용 허용치, 기존 자산)을 리서치가 뒷받침하는 객관식으로 한 번에 묻습니다 — "무엇을 쓸까요?"가 아니라 "A(버전·근거) vs B(버전·근거), 이 상황엔 A 추천"처럼. 모호한 답은 재질문하고, 추측으로 메꾸지 않습니다. 사용자가 방안을 고르면 ## 결론 을 쓰고 status 를 resolved 로. 증거 게이트: 결론·계획의 모든 주장에는 근거(조사 출처·사용자 답변·측정)를 병기합니다 — 근거 없는 수식어("빠르고 확장 가능한")는 쓰지 않습니다.

STAGE 3 — 계획 (plan_create, 3-depth 로 매우 자세히)

결론을 3-depth 계획으로: plan_create MCP 도구로 phases(마일스톤) → items(작업) → children(하위 작업, 1단계)을 만듭니다. 구현이 이 계획을 따라가므로 자세할수록 좋습니다 — 리프는 반나절 이하 단위의 "검증 가능한 동사구"("로그인"이 아니라 "이메일 로그인 happy-path 가 동작한다"), 구현 순서대로 배열하고, 리프마다 확인 방법을 항목 문구에 담습니다 — 실행할 명령(테스트/빌드) 또는 재현 시나리오가 문구에서 읽혀야 /oculpm:next 가 완료 기준으로 씁니다. Phase 1 의 첫 항목은 "리서치에서 확정한 버전으로 환경 구성·스캐폴드". 도구가 없으면 AGENTS.md §4 의 폴백 규격으로 직접 작성.

STAGE 4 — 완료 정의 (EVALS.md)

프로젝트 루트에 EVALS.md 를 만듭니다: 결론의 "완성의 정의"를 실행/재현 가능한 평가 항목(체크리스트/시나리오)으로 옮기고, 맨 아래에 기록 표를 둡니다:

Read the full file on GitHub · 65 lines

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.

  1. 10d ago First seen · 65 lines · 85 tokens per session scan A c18a1507ef2b

Subscribe to this mod's changes

project-inception is a skill published in the GitHub repository bunhine0452/Ocul-PM (7 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 1,863 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.

Related

Other skills, from other repositories

agentbro-pr-merge

Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.

shirenchuang/agentbro · 38 tokens

linear

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

rojim666/SztuCode · 27 tokens

product-strategy

A product-planning guide for evaluating requirements, users, scope, priorities, roadmaps, and success measures. It ties proposals to user problems, business value, boundaries, and signals that can be checked.

devcodex-labs/devcodex · 68 tokens

pm-long-horizon-planning

Audit long, complex, and potentially inconsistent PM taskbooks and compile them into one self-contained, semantically validated Product Brief with a requirement ledger, WP dependency graph, budgets, absolute schedule, gates, tests, experiment evidence, risks, recovery, and stop conditions. Use for long-horizon or…

joinwell52-AI/CodeFlowMu-open · 136 tokens

pm-product-requirements

Turn vague ADMIN requests, chat feedback, screenshots, and workflow complaints into scoped CodeFlowMu product requirements. Use when PM needs PRD-style clarification, user stories, goals, non-goals, constraints, risks, or task input while preserving FCoP boundaries.

joinwell52-AI/CodeFlowMu-open · 59 tokens

pm-acceptance-criteria

Convert "done" into checkable CodeFlowMu acceptance criteria. Use before PM dispatch, PM review, QA verification, or ADMIN closure to define functional, file, behavior, evidence, and forbidden-item checks.

joinwell52-AI/CodeFlowMu-open · 49 tokens