Why it is worth attention

It solves the fundamental problem of AI agents forgetting context between sessions, using a minimal, opinionated documentation system with multiple enforcement layers (CLAUDE.md, skills, and session hooks) that ensure agents always pick up where they left off.

Who it is for

Developers using AI coding agents like Claude Code, Codex, or Cursor
Teams managing multiple AI-assisted projects
Engineers who want reproducible agent workflows
Project leads needing consistent project state handoffs

Use cases

Starting a new agent session without re-explaining project goals, status, or next steps
Maintaining a single source of truth for project state via HANDOFF.md YAML frontmatter
Managing a workspace of multiple projects with auto-generated index and overview tables
Enforcing agent documentation conventions through session start/stop hooks and command skills

Strengths

Extremely simple: 5 files with one job each, setup in 30 seconds
Multi-layer enforcement: context injection, skill procedures, and session-end blocking hook
Workspace generator produces byte-identical output from PowerShell or Python with no dependencies
Plain Markdown files work with any agent; optional hook layer enhances Claude Code

Considerations

Full enforcement hooks require Python 3.7+ and a one-time approval
Hook and skill layers are Claude Code-specific; other agents only get the file-based convention
Relies on user discipline to update HANDOFF.md at every session end

README quick start

Dear Agent,

English | 한국어

A tiny, opinionated documentation system for projects built with AI coding agents (Claude Code and friends) — the letter your project leaves for the next session's agent.

The problem: agents forget everything between sessions. Every new session starts with you re-explaining what the project is, where it stopped, and what to do next.

The fix: five small markdown files per project — each with exactly one job, zero overlap — plus a generator that turns them into a workspace-wide project map once you have many projects.

Tier 1 — one project (30 seconds)

Copy the five files from _templates/ into your repo and fill them in:

File	Job	Update when
`PLAN.md`	goals, scope, tech decisions	decisions change
`HANDOFF.md`	current state: last work / next steps / blockers, + status frontmatter	every session end
`LOG.md`	one line per notable change	features/fixes land
`README.md`	how to run it	run steps change
`CLAUDE.md`	agent ops guide: commands, code map, pitfalls	build/structure changes

The heart is HANDOFF.md. Its YAML frontmatter is the single source of truth for project state:

---
status: 개발            # 기획(planning) | 개발(building) | 운영(live) | 보류(paused)
updated: 2026-07-05
summary: one-line status
repo: org/name          # delete this line if no remote
---

An agent reads it at session start and knows exactly where to pick up — no re-explaining.

Using an agent other than Claude Code? Copy or symlink CLAUDE.md to AGENTS.md.

Tier 2 — many projects (a workspace)

When projects multiply, this repo doubles as a workspace template: category folders hold projects, and a generator scans every HANDOFF.md frontmatter to build tables of contents.

workspace/
├─ OVERVIEW.md          ← generated: map of ALL projects
├─ CONVENTIONS.md       ← the single rulebook
├─ apps/                ← a category folder (any name)
│  ├─ _INDEX.md         ← generated: projects in this category
│  ├─ todo-api/         ← a project (the 5 files + code)
│  └─ web-dashboard/
└─ build-index.ps1 / build-index.py

Run either generator — they produce byte-identical output (CI-enforced), no dependencies:

powershell -File ./build-index.ps1    # Win

Description

Dear agent: everything you need to resume this project. A 5-file docs convention + workspace template for AI coding agents.

Related repositories

Similar projects matched by category, topics, and programming language.

S40911120

Featured

recensa

Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.

AI & Machine LearningLarge Language Models

bjan

Featured

claudemux

Claudemux is a lightweight, dependency-minimal message bus that lets multiple Claude Code sessions communicate in real-time over tmux, enabling one session to ask another a question and receive the answer without manual intervention.

AI & Machine LearningAI Agents

hoainho

img2threejs

img2threejs reconstructs a 3D object from a single reference image as a procedural Three.js model using code-only, token-efficient, staged pipeline with quality gates, producing animation-ready Three.js groups.

Python

7,414