~ / rigs / orynvn / claude-workspace-setup

orynvn/claude-workspace-setup

A project template for Claude Code CLI — opinionated, token-efficient, and built for multi-agent workflows.

↗ GitHub ★ 0 no license updated 5mo ago personal setup Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~22.3k tokens
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github
$ npx degit orynvn/claude-workspace-setup/.claude ./rig-claude-workspace-setup  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/orynvn/claude-workspace-setup/main/.claude/agents/analyst.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/orynvn/claude-workspace-setup/main/.claude/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/orynvn/claude-workspace-setup/main/.claude/agents/implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/orynvn/claude-workspace-setup/main/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/quick.md https://raw.githubusercontent.com/orynvn/claude-workspace-setup/main/.claude/agents/quick.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/orynvn/claude-workspace-setup/main/.claude/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/security.md https://raw.githubusercontent.com/orynvn/claude-workspace-setup/main/.claude/agents/security.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash .claude/hooks/pre-bash.sh \"$CLAUDE_TOOL_INPUT\""
          }
        ]
      }
    ]
  }
}

MCP servers (2)

serversourceest. tokens
error-learning local / custom 2.5k
GitHub MCP · "github"
env: GITHUB_PERSONAL_ACCESS_TOKEN
npm 18.0k

Subagents (7)

analyst
model: claude-sonnet-4-6
Analyzes user requirements (Vietnamese/English), detects intent, creates structured plans in .context/plans/, and handles task status commands (list, run, done).
debugger
model: claude-sonnet-4-5
Diagnoses bugs and CI failures. Follows RCA → Fix Plan → Fix → Log workflow. Uses Error Learning MCP and GitHub MCP when available.
implementer
model: claude-sonnet-4-5
Writes code from a task breakdown. Follows stack conventions from CLAUDE.md. Does not plan or test.
planner
model: claude-sonnet-4-5
Analyzes requirements and outputs a task breakdown. Read-only — does not write code.
quick
model: claude-haiku-4-5
Solo executor for simple tasks — no planning, no tests, direct execution. Use for docs, translations, config edits, single-file changes, renames, and cleanup.
reviewer
model: claude-sonnet-4-5
Reviews code for logic, security, and conventions. Reports findings — does not fix.
security
model: claude-sonnet-4-5
OWASP Top 10 security audit. Reports findings — does not fix code.

Hooks (3)

eventmatcherruns
PreToolUseBashbash .claude/hooks/pre-bash.sh "$CLAUDE_TOOL_INPUT"
PostToolUseEdit|Write|MultiEditbash .claude/hooks/post-edit.sh "$CLAUDE_TOOL_INPUT"
Stop*bash .claude/hooks/session-stop.sh

Slash commands (4)

/do/plan/ship/todo

Similar rigs

copied ✓