giovanebribeiro/claude-setup
My configurations, scripts, skills, etc. for Claude Code
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit giovanebribeiro/claude-setup/agents ./rig-claude-setup/agents $ npx degit giovanebribeiro/claude-setup/commands ./rig-claude-setup/commands $ npx degit giovanebribeiro/claude-setup/skills ./rig-claude-setup/skills
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.
$ npx degit giovanebribeiro/claude-setup/skills/client-context .claude/skills/client-context $ npx degit giovanebribeiro/claude-setup/skills/continuous-learning .claude/skills/continuous-learning $ npx degit giovanebribeiro/claude-setup/skills/jira-create-card .claude/skills/jira-create-card $ npx degit giovanebribeiro/claude-setup/skills/jira-executive-summary .claude/skills/jira-executive-summary $ npx degit giovanebribeiro/claude-setup/skills/jira-project-health .claude/skills/jira-project-health $ npx degit giovanebribeiro/claude-setup/skills/jira-recent-comments .claude/skills/jira-recent-comments $ npx degit giovanebribeiro/claude-setup/skills/jira-sprint-retro .claude/skills/jira-sprint-retro $ npx degit giovanebribeiro/claude-setup/skills/learn .claude/skills/learn $ npx degit giovanebribeiro/claude-setup/skills/tracker-adapter .claude/skills/tracker-adapter
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-resolver.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/build-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/lang-reviewer.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/lang-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/manager.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/manager.md $ curl -fsSL --create-dirs -o .claude/agents/pm-assistant.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/pm-assistant.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/giovanebribeiro/claude-setup/master/agents/security-reviewer.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": "atuin hook claude-code"
}
]
},
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "serena-hooks remind --client=claude-code"
}
]
},
{
"matcher": "mcp__serena__*",
"hooks": [
{
"type": "command",
"command": "serena-hooks auto-approve --client=claude-code"
}
]
}
]
}
} Skills (9)
client-contextcontinuous-learningjira-create-cardjira-executive-summaryjira-project-healthjira-recent-commentsjira-sprint-retrolearntracker-adapter
Subagents (8)
| architect model: opus | Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions |
| build-resolver model: sonnet | Polyglot build error resolution specialist for Go, Java/Maven/Gradle, and Rust/Cargo. Auto-detects the language from build files and error output, then applies surgical fixes. Use when any build, vet, |
| code-reviewer model: sonnet | Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes. |
| doc-updater model: haiku | Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides. |
| lang-reviewer model: sonnet | Polyglot code reviewer for Go, Java, Python, and Rust. Auto-detects the project language from changed files and applies the appropriate idiomatic review — concurrency, error handling, security, and fr |
| manager model: fable | Top-level orchestrator. Use PROACTIVELY to decompose complex multi-step user requests into a plan and dispatch sub-tasks to specialized agents. Only invoke for genuinely multi-step/multi-domain tasks |
| pm-assistant | Personal project-management assistant for a client's Jira boards. Generates Epic health reports, creates/edits Epics and cards to standard, produces Director-facing executive summaries, and builds biw |
| security-reviewer model: sonnet | Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injectio |
Hooks (8)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | serena-hooks activate --client=claude-code |
| SessionEnd | * | serena-hooks cleanup --client=claude-code |
| PostToolUse | Bash | atuin hook claude-code |
| PostToolUse | Bash | ~/.claude/skills/tracker-adapter/hooks/commit-key-reminder.sh |
| PostToolUseFailure | Bash | atuin hook claude-code |
| PreToolUse | Bash | atuin hook claude-code |
| PreToolUse | * | serena-hooks remind --client=claude-code |
| PreToolUse | mcp__serena__* | serena-hooks auto-approve --client=claude-code |
Slash commands (8)
/gha/refactor-clean/skill-health/tdd/track-work/update-codemaps/update-docs/verify
Plugins (1)
rust-analyzer-lsp@claude-plugins-official
Similar rigs
peopleforrester/claude-dotfiles
Configuration layer for Claude Code: 70 skills, 15 agents, 21 rules, 14 hooks, and 4 sandboxed permission profiles, all schema-validated in CI
Fort Knox 862 tok ·
Yuutokata/claude-code-setup
🔄 One Claude Code setup for my desktop and MacBook, synced through git, with guardrails that keep secrets out.
Fort Knox 1.1k tok ·
cfrs2005/claude-init
Claude Code 中文开发套件 - 为中国开发者定制的零门槛 AI 编程环境。一键安装完整中文化体验，集成 MCP 服务器、智能上下文管理、安全扫描，支持免翻墙访问。让 AI 编程更简单。
Orchestrator 1.5k tok ·
mh2-lee/everything-claude-code
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Orchestrator 1.2k tok ·