setup
Setup
Bootstrap the agent working system for a new project.
Why This System
Without this system, every agent starts from zero. Mistakes you make, successors will repeat. What you learn, successors must relearn.
With this system:
- Experience accumulates, patterns emerge
- Successors stand on your shoulders
- Each agent goes further than the last
This isn't optional "best practice"—it's the infrastructure that enables agent teams to evolve.
What You Need to Do
1. Create CLAUDE.md
Base it on lidessen/moniro/CLAUDE.md.
Keep these sections as-is (core working method):
- Opening block (
FIRST/ALWAYS/LAST) Who You Are(entire section)Methodology(entire section)Remember(closing section)
Replace these sections (project-specific):
Vision→ describe this project's purposeStructure→ describe this project's directory layout
Remove or adapt these sections (optional):
Skill Collaboration→ keep if using skills, remove if notSkill Core Methods→ keep if using skills, remove if notContributing→ adapt to this project's contribution guidelines
2. Create .memory/ Structure
mkdir -p .memory/{notes,decisions,todos}
| Directory | Purpose |
|---|---|
| notes/ | Learnings, reflections, discoveries |
| decisions/ | Important decisions and their rationale |
| todos/ | Tasks that span sessions |
3. Write First Transmission Document
Create .memory/notes/to-those-who-come-after.md.
Reference lidessen/moniro/.memory/notes/2026-01-31-to-those-who-come-after.md for structure, but write your own content:
- What this project does
- What you (first agent) established
- Advice for those who follow
- A lineage table to track who contributed
Adapt to Context
The above is the required framework. On top of this, adapt based on project needs:
- Tech stack conventions: e.g., "Frontend components go in src/components/"
- Workflow conventions: e.g., "PRs require two reviewers"
- Team conventions: e.g., "Major decisions need human confirmation"
Add these to the appropriate sections in CLAUDE.md.
Checklist
After setup, verify:
- CLAUDE.md exists with
Who You Are,Methodology, andRemembersections - Opening block has
FIRST/ALWAYS/LASTreminders - .memory/ directory structure created
- to-those-who-come-after.md written
- Vision and Structure filled in for this project
Reference
Source: lidessen/moniro
For the origin and evolution of this system, see that repository's .memory/notes/ directory.
More from lidessen/skills
memory
Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "todo", or session handoff.
82design-driven
Design-driven development methodology — the design/ directory is the single source of architectural truth; read it before coding, stay within its boundaries, and update it first when the system's shape changes. Use whenever starting development on this project, or when the user asks to create/update architecture docs, add a feature that may cross existing boundaries, refactor system structure, or understand the codebase architecture. Triggers on "design first", "update the design", "does this change the architecture", "write a design for", "what's the current design", or onboarding to a codebase's shape. Args — `/design-driven init` to configure a project, `bootstrap` to generate design from existing code, `audit` to reconcile design/ against current code.
20housekeeping
Manages project housekeeping including documentation organization, dependency management, directory structure, code cleanup, technical debt tracking, and infrastructure configuration. Use when organizing documentation, cleaning up dependencies, reorganizing folders, removing dead code, addressing tech debt, or maintaining project structure.
18harness
Agent harness architecture — structure a project's agent context across layers for effective AI-assisted development. Covers CLAUDE.md, skills, design docs, hooks, and all artifacts that shape how an agent understands and operates in a codebase. Use when setting up or improving agent configuration, when agent context feels bloated or disorganized, when onboarding a project for AI-assisted development, or when the agent keeps losing architectural awareness mid-task. Triggers on "set up claude", "improve CLAUDE.md", "agent keeps forgetting", "context is too long", "harness setup", "organize agent context", "how should I structure my prompts". Args — `/harness audit` to evaluate an existing project's context architecture, `init` to set up harness from scratch.
17validation
Unified validation orchestration for code quality, consistency, and project health. Auto-triggers on code changes, PR creation, or explicit validation requests. Coordinates refining, housekeeping, and custom validators into cohesive pipelines. Use for "validate", "check", "verify", "验证", "检查", or when quality assurance is needed.
17orientation
Orients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when entering unfamiliar territory, or when asking "what can you do" or "where do I start".
16