From 3c97060606c02950bd3280181f7c9e5126385690 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Wed, 29 Jul 2026 07:12:25 +0000 Subject: [PATCH] Add AGENTS.md and CLAUDE.md for Cursor/Claude project rules Introduce a single source of truth for agent guidance during the planning-docs phase: document authority, tentative Q1-Q7 handling, v1 scope guards, safety invariants, and next PoC priorities. Co-authored-by: okuma --- AGENTS.md | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ CLAUDE.md | 15 ++++++++ README.md | 5 +++ 3 files changed, 123 insertions(+) create mode 100644 AGENTS.md create mode 100644 CLAUDE.md diff --git a/AGENTS.md b/AGENTS.md new file mode 100644 index 0000000..f61748c --- /dev/null +++ b/AGENTS.md @@ -0,0 +1,103 @@ +# Project Instructions — hikikomori / 분신 (가칭) + +This repository is currently a **planning-docs repo** for an AI-twin messenger +("나를 대신해 남과 대화하는 AI 분신"). There is no application code yet. + +Canonical docs live under `docs/`. Prefer linking to them over copying content +into prompts or new files. + +## Document authority + +When documents disagree, follow this order: + +1. [`docs/decision-log.md`](docs/decision-log.md) — working assumptions for Q1~Q7 +2. [`docs/vision.md`](docs/vision.md) / [`docs/PRD.md`](docs/PRD.md) / [`docs/tech-design.md`](docs/tech-design.md) +3. [`docs/roadmap.md`](docs/roadmap.md) / [`docs/risk-log.md`](docs/risk-log.md) +4. [`docs/PLANNING.md`](docs/PLANNING.md) — process guide +5. [`docs/idea-meeting-2026-06-29.html`](docs/idea-meeting-2026-06-29.html) — historical meeting source only + +Notes: + +- Q1~Q7 in `decision-log.md` are **제안 (tentative)**, not final meeting + decisions. Do not silently reverse them. If a change is required, update + `decision-log.md` and all derived docs in the same change. +- `PLANNING.md` §2 may still show empty checkboxes (`☐`). That is stale + template state — prefer `decision-log.md` for current working answers. +- Stale wording such as “OS 레이어 → 자체 앱” is wrong. The working order is + **자체 앱 클로즈드 베타 first → OS 레이어 later** (`decision-log.md` Q7). + +## Product identity (v1 working assumptions) + +- Name (working): **분신** +- One-liner: ChatGPT talks *with* me; 분신 talks *as* me *to others* +- Target: consumer individuals first (not B2B) +- Delivery: self-owned messenger, closed beta +- Autonomy for v1: **L0~L2 only** +- MVP scenarios: **읽씹 종결** + **단톡 따라잡기** +- Platform: Android first + +## Hard scope guards (do not expand without an explicit decision-log update) + +Out of v1 scope: + +- L3 full away-mode auto-reply +- L4 twin-to-twin negotiation / appointment auto-finalization +- OS-layer bridging over KakaoTalk / Instagram / etc. +- B2B / workspace products +- Server-side full conversation analytics that violate on-device-first + +Do not design or implement Phase 2+ work before Phase 1 gates are validated +(`docs/roadmap.md`). + +## Absolute safety invariants + +These apply at every autonomy level and must not be weakened for convenience: + +- Money, appointment confirmation, and emotional/sensitive topics always + escalate to the human. When uncertain, escalate (fail-safe). +- Twin-authored messages must be visually distinct (badge / `sender_mode`). +- Honest identity answers: if asked “본인이야 분신이야?”, answer as twin. +- Peer veto: if the other person rejects the twin, disable auto-reply for that + conversation immediately. +- Every automatic action needs post-hoc notification + one-tap undo. + +## Privacy & architecture principles + +- Tone/style learning: **on-device first**. Do not default to uploading raw chat + history to servers. +- Autonomy / escalation engine: **client-side** so safety is not blocked by + server latency or outage. +- Draft generation: on-device first, server LLM fallback with minimal context. +- Relay/storage server is allowed; it is not a license for full cloud analysis. + +## Process rules + +Follow `docs/PLANNING.md`: decide → narrow → validate → specify. + +Current next priorities (do not invent a full stack first): + +1. PoC #1 — on-device tone realism +2. PoC #3 — impersonation / trust acceptance (badge, veto UX) +3. Clickable prototype (badge + veto) +4. Small user interviews +5. Meeting review to promote Q1~Q7 from 제안 → 확정 + +Do not invent frameworks, folder layouts, or CI conventions until real code +exists. When code work starts, prefer Android-first changes aligned with +`docs/tech-design.md` and keep L0~L2 + safety invariants intact. + +## Documentation conventions + +- Planning docs are written in **Korean**. +- Keep decisions traceable with links to `decision-log.md` Q# and related files. +- Preserve `idea-meeting-2026-06-29.html` as historical source material; do not + treat it as the live decision record. +- When status changes, keep `PLANNING.md` §8, `roadmap.md`, and `risk-log.md` + in sync. +- Prefer updating existing docs over creating parallel overlapping docs. + +## Communication with agents + +- Read the relevant docs before proposing product/tech changes. +- Call out whether a suggestion is inside v1 scope or a future-phase idea. +- If requirements are ambiguous, ask before expanding scope. diff --git a/CLAUDE.md b/CLAUDE.md new file mode 100644 index 0000000..b91be9a --- /dev/null +++ b/CLAUDE.md @@ -0,0 +1,15 @@ +# Claude Code — hikikomori / 분신 + +Follow the project instructions in [@AGENTS.md](./AGENTS.md). + +Quick context: + +- This repo is planning docs only (no app code yet). +- Working product name: **분신** (tentative). +- Source of working decisions: `docs/decision-log.md` (status: 제안). +- v1 scope: self-app closed beta, L0~L2, 읽씹 종결 + 단톡 따라잡기, Android first. +- Hard bans for v1: L3/L4, OS-layer over third-party messengers, B2B. +- Never weaken escalation, twin badge, peer veto, or undo. + +Before changing product or technical direction, read `AGENTS.md` and the +relevant files under `docs/`. diff --git a/README.md b/README.md index 7b45bda..d500e05 100644 --- a/README.md +++ b/README.md @@ -13,6 +13,11 @@ - 리스크 로그: [`docs/risk-log.md`](./docs/risk-log.md) - 로드맵: [`docs/roadmap.md`](./docs/roadmap.md) +## AI 에이전트 규칙 + +- Cursor / 공통: [`AGENTS.md`](./AGENTS.md) +- Claude Code 진입점: [`CLAUDE.md`](./CLAUDE.md) + ## 현재 단계 아이디어 발산 → 컨셉 심화 → 기획 문서 세트(Vision/PRD/기술설계/리스크/로드맵) 초안 작성까지 완료.