agentrigs
+ submit rig
~ / rigs / eugeek / claude-config-tdd

eugeek/claude-config-tdd

Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment

↗ GitHub ★ 2 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
~5.8k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Protects secrets · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add chrome-devtools -- npx -y @executeautomation/mcp-chrome-devtools
$ claude mcp add context7 -e CONTEXT7_<redacted> -- npx -y @upstash/mcp-context7
$ npx degit eugeek/claude-config-tdd/agents ./rig-claude-config-tdd/agents
$ npx degit eugeek/claude-config-tdd/commands ./rig-claude-config-tdd/commands

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 chrome-devtools -- npx -y @executeautomation/mcp-chrome-devtools
$ claude mcp add context7 -e CONTEXT7_<redacted> -- npx -y @upstash/mcp-context7
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/eugeek/claude-config-tdd/main/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/backend.md https://raw.githubusercontent.com/eugeek/claude-config-tdd/main/agents/backend.md
$ curl -fsSL --create-dirs -o .claude/agents/frontend.md https://raw.githubusercontent.com/eugeek/claude-config-tdd/main/agents/frontend.md
$ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/eugeek/claude-config-tdd/main/agents/qa.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/eugeek/claude-config-tdd/main/agents/reviewer.md

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

{
  "permissions": {
    "deny": [
      "Bash(git add *)",
      "Bash(git commit *)",
      "Bash(git push *)",
      "Bash(git pull *)",
      "Bash(git merge *)",
      "Bash(git rebase *)",
      "Bash(git reset *)",
      "Bash(git stash *)",
      "Bash(git clone *)",
      "Bash(rtk git add *)",
      "Bash(rtk git commit *)",
      "Bash(rtk git push *)",
      "Bash(rtk git pull *)",
      "Bash(rtk git merge *)",
      "Bash(rtk git rebase *)",
      "Bash(rtk git reset *)",
      "Bash(rtk git stash *)",
      "Bash(rtk git clone *)",
      "Bash(sudo *)",
      "Bash(rm *)",
      "Read(**/.env)",
      "Read(.env)",
      "Write(**/.env)",
      "Write(.env)",
      "Edit(**/.env)",
      "Edit(.env)"
    ]
  }
}

MCP servers (2)

serversourceest. tokens
@executeautomation/mcp-chrome-devtools · "chrome-devtools" npm 2.5k
@upstash/mcp-context7 · "context7"
env: CONTEXT7_API_KEY
 npm 2.5k

Subagents (5)

architect
model: opus
Software architecture - system design, module structure, scalability, patterns. Use in plan mode for complex tasks.
backend
model: sonnet
Backend development - REST/GraphQL API, database, auth, server logic, data processing
frontend
model: sonnet
Frontend development specialist - React, TypeScript, performance, UX
qa
model: sonnet
QA specialist - comprehensive test coverage for all scenarios
reviewer
model: sonnet
Code reviewer - fresh perspective, finds unnecessary comments, enforces DRY and best practices

Slash commands (4)

/fix/review/test-new/test

Permissions

deny (26)
Bash(git add *)
Bash(git commit *)
Bash(git push *)
Bash(git pull *)
Bash(git merge *)
Bash(git rebase *)
Bash(git reset *)
Bash(git stash *)
Bash(git clone *)
Bash(rtk git add *)
Bash(rtk git commit *)
Bash(rtk git push *)
Bash(rtk git pull *)
Bash(rtk git merge *)
Bash(rtk git rebase *)
Bash(rtk git reset *)
Bash(rtk git stash *)
Bash(rtk git clone *)
Bash(sudo *)
Bash(rm *)
Read(**/.env)
Read(.env)
Write(**/.env)
Write(.env)
Edit(**/.env)
Edit(.env)
ask (0)
—
allow (34)
Bash(npm *)
Bash(yarn *)
Bash(pnpm *)
Bash(bun *)
Bash(npx *)
Bash(ls *)
Bash(cat *)
Bash(grep *)
Bash(find *)
Bash(tree *)
Bash(pwd)
Bash(echo *)
Bash(which *)
Bash(git status)
Bash(git log *)
Bash(git diff *)
Bash(git show *)
Bash(git branch)
Bash(git remote -v)
Bash(vitest *)
Bash(jest *)
Bash(pytest *)
Bash(python -m pytest *)
Bash(python -m mypy *)
Bash(tsc *)
Bash(mypy *)
Bash(ruff *)
Bash(eslint *)
Bash(biome *)
Bash(flake8 *)
Read(**/*)
Read(.env.example)
Write(.env.example)
Edit(.env.example)

Similar rigs

YounusHussain9/claude-agent-workspace
Multi-repo workspace for Claude Code: plain-language requests, specialist AI agents, approval gates and safety hooks.
★ 0 project Claude Code 3 skills 6 agents 3 hooks today
Fort Knox 2.0k tok ·
IntuitivePhella/AI-PhellOS
Portable AI development workflow template and CLI for spec-driven, test-aware software delivery with Codex, Claude Code, and other coding agents.
★ 2 project Claude CodeCodex 8 agents 4mo ago
Orchestrator 3.1k tok ·
ThinhHoang1/claude-code-agent-team
An AI dev team for Claude Code agent teams: 8 role agents, a HANDOFF protocol and 3 hook quality gates — with the TeammateIdle infinite-loop bug fixed and regression-tested.
★ 0 project Claude Code 8 agents 3 hooks 1d ago
Orchestrator 1.6k tok ·
itshig/AGENTS-template
Drop-in AGENTS.md template for Claude Code, Cursor, Codex, and other AI agents — with .agents/ for rules, personas, and workflows.
★ 1 collection Claude CodeCodexGemini CLI 5 agents 1mo ago
Orchestrator 3.0k tok ·
copied ✓