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.
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 OsamaA140/agent-trials/agents ./rig-agent-trials/agents $ npx degit OsamaA140/agent-trials/commands ./rig-agent-trials/commands $ npx degit OsamaA140/agent-trials/skills ./rig-agent-trials/skills $ npx degit OsamaA140/agent-trials/hooks ./rig-agent-trials/hooks
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 OsamaA140/agent-trials/skills/backend-patterns .claude/skills/backend-patterns $ npx degit OsamaA140/agent-trials/skills/clickhouse-io .claude/skills/clickhouse-io $ npx degit OsamaA140/agent-trials/skills/coding-standards .claude/skills/coding-standards $ npx degit OsamaA140/agent-trials/skills/continuous-learning .claude/skills/continuous-learning $ npx degit OsamaA140/agent-trials/skills/eval-harness .claude/skills/eval-harness $ npx degit OsamaA140/agent-trials/skills/frontend-patterns .claude/skills/frontend-patterns $ npx degit OsamaA140/agent-trials/skills/project-guidelines-example .claude/skills/project-guidelines-example $ npx degit OsamaA140/agent-trials/skills/security-review .claude/skills/security-review $ npx degit OsamaA140/agent-trials/skills/strategic-compact .claude/skills/strategic-compact $ npx degit OsamaA140/agent-trials/skills/tdd-workflow .claude/skills/tdd-workflow $ npx degit OsamaA140/agent-trials/skills/verification-loop .claude/skills/verification-loop
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/OsamaA140/agent-trials/main/agents/tdd-guide.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (11)
backend-patternsclickhouse-iocoding-standardscontinuous-learningeval-harnessfrontend-patternsproject-guidelines-examplesecurity-reviewstrategic-compacttdd-workflowverification-loop
Subagents (9)
| 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-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: sonnet | Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides. |
| e2e-runner model: sonnet | End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, vide |
| 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 |
| 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: opus | 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 |
| 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 (15)
/build-fix/checkpoint/code-review/e2e/eval/learn/orchestrate/plan/refactor-clean/setup-pm/tdd/test-coverage/update-codemaps/update-docs/verify
Similar rigs
WorldFlowAI/everything-claude-code
Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development
Orchestrator 1.5k tok ·
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 ·
cloudnative-co/claude-code-starter-kit
One-command setup of a complete Claude Code development environment with interactive wizard
Orchestrator 8.4k 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 ·