zhongli369/ai-workbench
Adaptive AI software engineering workspace for Claude Code — lightweight by default, powerful when needed.
field: Developer tools workflow: PR / code reviewSecurity reviewPlanning & specsRefactoringTesting & TDD
stack: Python
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 zhongli369/ai-workbench/workbench/.claude ./rig-ai-workbench # 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 zhongli369/ai-workbench/workbench/.claude/skills/benchmark .claude/skills/benchmark $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/codebase-onboarding .claude/skills/codebase-onboarding $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/coding-standards .claude/skills/coding-standards $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/context-budget .claude/skills/context-budget $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/continuous-learning-v2 .claude/skills/continuous-learning-v2 $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/cost-tracking .claude/skills/cost-tracking $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/deep-research .claude/skills/deep-research $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/ecc-guide .claude/skills/ecc-guide $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/error-handling .claude/skills/error-handling $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/eval-harness .claude/skills/eval-harness $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/experience-capture .claude/skills/experience-capture $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/failure-oracle .claude/skills/failure-oracle $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/frontend-patterns .claude/skills/frontend-patterns $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/gateguard .claude/skills/gateguard $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/git-workflow .claude/skills/git-workflow $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/github-ops .claude/skills/github-ops $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/hookify-rules .claude/skills/hookify-rules $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/iterative-retrieval .claude/skills/iterative-retrieval $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/parallel-execution-optimizer .claude/skills/parallel-execution-optimizer $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/plan-orchestrate .claude/skills/plan-orchestrate $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/prompt-optimizer .claude/skills/prompt-optimizer $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/python-patterns .claude/skills/python-patterns $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/python-testing .claude/skills/python-testing $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/repo-scan .claude/skills/repo-scan $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/rules-distill .claude/skills/rules-distill $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/safety-guard .claude/skills/safety-guard $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/search-first .claude/skills/search-first $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/security-review .claude/skills/security-review $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/tdd-workflow .claude/skills/tdd-workflow $ npx degit zhongli369/ai-workbench/workbench/.claude/skills/workbench .claude/skills/workbench
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-explorer.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/code-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/docs-lookup.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/docs-lookup.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/harness-optimizer.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/harness-optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-optimizer.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/performance-optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/pr-test-analyzer.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/pr-test-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/python-reviewer.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/python-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/silent-failure-hunter.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/silent-failure-hunter.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/zhongli369/ai-workbench/main/workbench/.claude/agents/tdd-guide.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (30)
benchmarkcodebase-onboardingcoding-standardscontext-budgetcontinuous-learning-v2cost-trackingdeep-researchecc-guideerror-handlingeval-harnessexperience-capturefailure-oraclefrontend-patternsgateguardgit-workflowgithub-opshookify-rulesiterative-retrievalparallel-execution-optimizerplan-orchestrateprompt-optimizerpython-patternspython-testingrepo-scanrules-distillsafety-guardsearch-firstsecurity-reviewtdd-workflowworkbench
Subagents (16)
| 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-error-resolver model: sonnet | Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the |
| code-explorer model: sonnet | Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, and documenting dependencies to inform new development. |
| 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. |
| docs-lookup model: sonnet | When the user asks how to use a library, framework, or API or needs up-to-date code examples, use Context7 MCP to fetch current documentation and return answers with examples. Invoke for docs/API/setu |
| e2e-runner model: sonnet | End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines fl |
| harness-optimizer model: sonnet | Analyze and improve the local agent harness configuration for reliability, cost, and throughput. |
| performance-optimizer model: sonnet | Performance analysis and optimization specialist. Use PROACTIVELY for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks, |
| planner model: opus | Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for p |
| pr-test-analyzer model: sonnet | Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention. |
| python-reviewer model: sonnet | Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects. |
| refactor-cleaner model: sonnet | Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely r |
| 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 |
| silent-failure-hunter model: sonnet | Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation. |
| tdd-guide model: sonnet | Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage. |
Slash commands (14)
/build-fix/checkpoint/code-review/cost-report/feature-dev/harness-audit/learn/plan/promote/python-review/quality-gate/security-scan/test-coverage/update-docs
Similar rigs
ndhananj/codex-agent-setup
A set up agent frameworks based on "affaan/everything-claude-code"
Orchestrator 2.2k tok · · Q3
WorldFlowAI/everything-claude-code
Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development
Orchestrator 1.5k tok · · Q3
HABUBUSS/everything-claude-code
Discover production-ready Claude Code configs: agents, skills, hooks, commands, rules, and MCP setups from an Anthropic hackathon winner.
Orchestrator 1.5k tok · · Q3
OsamaA140/agent-trials
Prove an agent does its job before you trust it: employee templates, deterministic pass^k trials, zero-token safety hooks, token-lean Claude Code config.
Orchestrator 1.5k tok · · Q3