optiquity/optiquity-ai-agent-config-pack
Versioned AI agent team managed project orchestration system for Claude Code, Codex, and Gemini. Focused on software development projects with extensive support for Apple platforms, Python, and others, the system can be extended to support
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Protects secrets · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details
Copy this rig
# review before running: this installs third-party code
$ npx degit optiquity/optiquity-ai-agent-config-pack/.claude ./rig-optiquity-ai-agent-config-pack # 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.
$ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/architecture-review .claude/skills/architecture-review $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/boundary-investigation .claude/skills/boundary-investigation $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/commit-discipline .claude/skills/commit-discipline $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/dashboard-render .claude/skills/dashboard-render $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/dependency-intake .claude/skills/dependency-intake $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/documentation .claude/skills/documentation $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/implementation-report .claude/skills/implementation-report $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-dashboard .claude/skills/pack-dashboard $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-help .claude/skills/pack-help $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-intervention-mode .claude/skills/pack-intervention-mode $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-isolation-mode .claude/skills/pack-isolation-mode $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-refresh .claude/skills/pack-refresh $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-review-mode .claude/skills/pack-review-mode $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-startup .claude/skills/pack-startup $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/pack-status .claude/skills/pack-status $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/planning .claude/skills/planning $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/review .claude/skills/review $ npx degit optiquity/optiquity-ai-agent-config-pack/.agents/skills/verification-harness .claude/skills/verification-harness $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/api-design .claude/skills/api-design $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/apple-architecture-core .claude/skills/apple-architecture-core $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/apple-swiftdata-patterns .claude/skills/apple-swiftdata-patterns $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/audit-methodology .claude/skills/audit-methodology $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/c-language .claude/skills/c-language $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/cpp-language .claude/skills/cpp-language $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/debugging .claude/skills/debugging $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/dependency-python .claude/skills/dependency-python $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/dependency-swift .claude/skills/dependency-swift $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/deployment-apple .claude/skills/deployment-apple $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/deployment-python .claude/skills/deployment-python $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/error-handling .claude/skills/error-handling $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/grpc-patterns .claude/skills/grpc-patterns $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/implementation .claude/skills/implementation $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/ios-architecture .claude/skills/ios-architecture $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/macos-architecture .claude/skills/macos-architecture $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/objc-language .claude/skills/objc-language $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/pm-dashboard .claude/skills/pm-dashboard $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/pm-groupings .claude/skills/pm-groupings $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/pm-help .claude/skills/pm-help $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/pm-intervention-mode .claude/skills/pm-intervention-mode $ npx degit optiquity/optiquity-ai-agent-config-pack/project-template/skills/pm-isolation-mode .claude/skills/pm-isolation-mode
$ curl -fsSL --create-dirs -o .claude/agents/pack-architect.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/.claude/agents/pack-architect.md $ curl -fsSL --create-dirs -o .claude/agents/pack-coder.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/.claude/agents/pack-coder.md $ curl -fsSL --create-dirs -o .claude/agents/pack-docs-researcher.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/.claude/agents/pack-docs-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/pack-planner.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/.claude/agents/pack-planner.md $ curl -fsSL --create-dirs -o .claude/agents/pack-reviewer.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/.claude/agents/pack-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/auditor-architecture.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor-architecture.md $ curl -fsSL --create-dirs -o .claude/agents/auditor-code.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor-code.md $ curl -fsSL --create-dirs -o .claude/agents/auditor-docs.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor-docs.md $ curl -fsSL --create-dirs -o .claude/agents/auditor-ops.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor-ops.md $ curl -fsSL --create-dirs -o .claude/agents/auditor-security.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor-security.md $ curl -fsSL --create-dirs -o .claude/agents/auditor-tests.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor-tests.md $ curl -fsSL --create-dirs -o .claude/agents/auditor-ui.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor-ui.md $ curl -fsSL --create-dirs -o .claude/agents/auditor.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/auditor.md $ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/docs-researcher.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/docs-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/grpc-schema.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/grpc-schema.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/repo-ops.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/repo-ops.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/optiquity/optiquity-ai-agent-config-pack/main/project-template/.claude/agents/tester.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": [
"Read(./.env)",
"Read(./.env.*)",
"Read(./secrets/**)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Agent",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/scripts/hooks/modes-enforce.py"
},
{
"type": "command",
"command": "python3 $CLAUDE_PROJECT_DIR/scripts/pm-modes-enforce.py"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/scripts/hooks/modes-commit-gate.py"
},
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/scripts/hooks/deletion-boundary.py"
},
{
"type": "command",
"command": "python3 $CLAUDE_PROJECT_DIR/scripts/pm-modes-commit-gate.py"
},
{
"type": "command",
"command": "python3 $CLAUDE_PROJECT_DIR/scripts/pm-deletion-boundary.py"
}
]
}
]
}
} Skills (58)
architecture-reviewboundary-investigationcommit-disciplinedashboard-renderdependency-intakedocumentationimplementation-reportpack-dashboardpack-helppack-intervention-modepack-isolation-modepack-refreshpack-review-modepack-startuppack-statusplanningreviewverification-harnessapi-designapple-architecture-coreapple-swiftdata-patternsaudit-methodologyc-languagecpp-languagedebuggingdependency-pythondependency-swiftdeployment-appledeployment-pythonerror-handlinggrpc-patternsimplementationios-architecturemacos-architectureobjc-languagepm-dashboardpm-groupingspm-helppm-intervention-modepm-isolation-modepm-refreshpm-review-modepm-startuppm-statuspm-target-sweepprotobuf-patternspython-best-practicespython-data-architecturepython-observability-patternspython-server-architecturerepo-opsresolve-merge-conflictsrest-patternssecurity-patternsswift-best-practicesswift-concurrency-patternstestingui-test-strategy
Subagents (21)
| pack-architect | Use for pack architecture and design decisions — file structure, naming conventions, cross-tool parity, migration strategy, version planning. Read-only analysis and recommendations. |
| pack-coder | Use to execute approved implementation plans against pack source — writing/editing scripts, fixtures, configs, or agent files. Reads ARCHITECTURE/PLAN docs, makes the file changes in the injected comm |
| pack-docs-researcher | Use for verifying CLI tool features, flags, and file format requirements against official documentation before committing to design decisions. Also for evaluating tool dependencies. |
| pack-planner | Use for implementation planning — task breakdown, file dependency analysis, commit sequencing, cross-doc consistency checks, and verification strategy for pack changes. |
| pack-reviewer | Use for reviewing pack changes before commit — trinity rule compliance, stale cross-references, doc consistency, validate-pack.py alignment, and migration safety. |
| architect | Use for architecture assessment, module boundaries, dependency decisions, layer discipline, and long-term maintainability. Default for: Architecture / design (Claude Code). |
| auditor-architecture | Audit subagent for architecture compliance, design quality, and observability infrastructure — layer boundaries, LSP/SOLID, coupling, interface uniformity, observability wiring. |
| auditor-code | Audit subagent for language-specific code quality — idioms, dead code, performance anti-patterns, concurrency safety, systemic error handling. |
| auditor-docs | Audit subagent for documentation drift detection — does documentation match the actual code? Path validity, API examples, config options, setup commands, CHANGELOG accuracy. |
| auditor-ops | Audit subagent for deployment readiness, configuration management, and observability wiring. Always runs — every project deploys somewhere. |
| auditor-security | Audit subagent for security — credential exposure, injection, deserialization, log safety, AND supply chain (CVEs, license compatibility, abandoned dependencies). |
| auditor-tests | Audit subagent for test coverage and design quality — coverage gaps, isolation, determinism, missing edge cases, mocked-vs-real boundary decisions. |
| auditor-ui | Audit subagent for UI/UX compliance only — view thickness, accessibility, incomplete states, platform UI conventions. Skipped for server-only projects. |
| auditor | Use for full-codebase structural audits across multiple quality dimensions. Retrospective and periodic — run after substantial implementation, not per-phase. Read-only. |
| coder | Use for implementation, targeted refactors, bug fixes, and test updates once the task is understood. Default for: Implementation (Codex). Also handles: Debugging, Refactoring (Codex). |
| docs-researcher | Use for checking official framework, package, and tool documentation before making correctness-sensitive claims or config changes. Default for: Dependency evaluation, Documentation (Claude Code). |
| grpc-schema | Use for Proto3 schema design, field evolution, breaking-change detection, buf validation, and gRPC service contract decisions. Default for: API and schema design (Claude Code). |
| planner | Use for planning, task breakdown, migration sequencing, risk analysis, and verification strategy before non-trivial edits. Default for: Planning / task breakdown (Claude Code). Also: Architecture / de |
| repo-ops | Use for repo operations, branch-safe scripted edits, local automation, Git hygiene, and repeatable command sequences. Default for: Repo operations, Local validation (Codex). |
| reviewer | Use for review of correctness, regressions, state ownership, concurrency safety, dependency decisions, and missing tests. Default for: Code review (Claude Code). |
| tester | Use for test design, verification planning, debugging failing tests, and deciding between unit, integration, UI, and end-to-end coverage. Default for: Testing (Codex). |
Hooks (7)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Agent | $CLAUDE_PROJECT_DIR/scripts/hooks/modes-enforce.py |
| PreToolUse | Bash | $CLAUDE_PROJECT_DIR/scripts/hooks/modes-commit-gate.py |
| PreToolUse | Bash | $CLAUDE_PROJECT_DIR/scripts/hooks/deletion-boundary.py |
| PreToolUse | Agent | python3 $CLAUDE_PROJECT_DIR/scripts/pm-modes-enforce.py |
| PreToolUse | Bash | python3 $CLAUDE_PROJECT_DIR/scripts/pm-modes-commit-gate.py |
| PreToolUse | Bash | python3 $CLAUDE_PROJECT_DIR/scripts/pm-deletion-boundary.py |
| PostToolUse | Edit|Write|MultiEdit | $CLAUDE_PROJECT_DIR/scripts/agent-post-edit-check.sh |
Permissions
deny (3)
Read(./.env)
Read(./.env.*)
Read(./secrets/**)
ask (0)
—
allow (14)
Bash(xcodebuild *)
Bash(swift test *)
Bash(swift build *)
Bash(swift format *)
Bash(buf *)
Bash(uv *)
Bash(ruff *)
Bash(pyright *)
Bash(pytest *)
Bash(git status)
Bash(git diff *)
Bash(git add *)
Bash(./scripts/*)
Bash(./agent-run.sh *)
Similar rigs
juzser/blacksmith
Autonomous agent factory — loop runner, worktree engine, and a local dashboard over the event log.
Orchestrator 2.6k tok ·
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok ·
ingenierodeatascos-cyber/ai-project-template
AI-First project template for building software with orchestrated AI agents using Spec-Driven Development. Includes router, planner, implementer and reviewer workflows for structured development with Codex, Claude Code or similar AI coding
Orchestrator 196 tok ·
sHyunis/claude-code-config
Claude Code 전역 설정 패키지 - 에이전트, 커맨드, 규칙, Hook을 한 번에 설치
Orchestrator 1.1k tok ·