GitHub - vggg/agent-project-bootstrap: Scaffold a multi-agent Claude Code project with vault, librarian, and worker agents. · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
vggg
agent-project-bootstrap
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>2 Commits<br>2 Commits
.claude-plugin
.claude-plugin
skills/agent-project-bootstrap
skills/agent-project-bootstrap
CHANGELOG.md
CHANGELOG.md
CLAUDE.md
CLAUDE.md
CONTRIBUTING.md
CONTRIBUTING.md
LICENSE
LICENSE
README.md
README.md
View all files
Repository files navigation
agent-project-bootstrap
A Claude Code plugin that scaffolds a multi-agent project setup from templates. It generates the Obsidian vault structure for a librarian agent (Iris), the COORDINATION.md that governs cross-agent protocol, and the workspace CLAUDE.md files for up to four worker agents: two developers, an analyst, and a designer. All files use {{placeholder}} tokens you fill once; nothing is hardcoded to a specific project.
When it's useful
You're running multiple Claude Code sessions in parallel on the same long-lived project
You want a knowledge layer (research findings, decisions, reconciliation log) that lives separate from the codebase
You're a solo or near-solo developer who coordinates with several specialist agents rather than a human team
You've used multi-agent Claude Code before and want a repeatable starting point instead of rebuilding config files from scratch each time
When it's overkill
One-shot or throwaway tasks (a single agent session is simpler)
Projects where you don't need persistent memory across sessions
Team setups where human engineers handle coordination and you only need one agent at a time
What gets generated
Vault structure (Obsidian, git-tracked):
CLAUDE.md # project brief (open threads, key decisions)<br>COORDINATION.md # cross-agent protocol (handoffs, ADRs, dev log, branching)">_meta/<br>CONVENTIONS.md # tool hierarchy + wikilinks rules<br>PERSONAS/<br>IRIS.md # librarian role definition<br>DAVE.md # dev agent 1<br>KRIS.md # dev agent 2 (optional)<br>VERA.md # analyst<br>IVY.md # designer<br>CLAUDE.md # Iris session guide<br>projects//<br>CLAUDE.md # project brief (open threads, key decisions)<br>COORDINATION.md # cross-agent protocol (handoffs, ADRs, dev log, branching)
Workspace files (one per agent, checked into their respective repos or directories):
workspaces/<br>dev/CLAUDE.md # engineering guide (used by both dev agents)<br>analyst/CLAUDE.md # analyst session guide<br>designer/CLAUDE.md # designer session guide
Installation
/plugin install https://github.com/vggg/agent-project-bootstrap
The /plugin install command syntax may evolve as Claude Code matures. If the above fails, check the Claude Code docs for the current install command format.
Usage
After installation, tell Claude something like:
"Use the agent-project-bootstrap skill to set up a new project."
Claude will ask for your project name, vault path, workspace base directory, GitHub repo, live URL, and tech stack, then emit all files with placeholders substituted. The emit process is documented in skills/agent-project-bootstrap/SKILL.md for reference.
Customisation
The templates use archetype names for agents (Iris, Dave, Kris, Vera, Ivy). These are just names — rename them to whatever fits your working style. The structural patterns (three-tier write ownership, handoff protocol, COORDINATION.md as single source for cross-agent rules) are what carry the value, not the names themselves.
The dev-2 slot (Kris) is explicitly optional. Single-developer projects skip it.
Acknowledgements
This skill codifies a multi-agent coordination pattern developed through real iteration on a software project. The goal is to make the setup repeatable without requiring each new project to rediscover the same structural decisions.
MIT License · vggg
About
Scaffold a multi-agent Claude Code project with vault, librarian, and worker agents.
Resources
Readme
License
MIT...