dpthinh910/ai-agent-timmy
AI agent skills, Claude Code config, and Antigravity configuration - consolidated workspace for intelligent coding workflows
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 dpthinh910/ai-agent-timmy/.claude ./rig-ai-agent-timmy # 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 dpthinh910/ai-agent-timmy/.claude/skills/agent-eval .claude/skills/agent-eval $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/agent-harness-construction .claude/skills/agent-harness-construction $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/agentic-engineering .claude/skills/agentic-engineering $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/ai-first-engineering .claude/skills/ai-first-engineering $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/ai-regression-testing .claude/skills/ai-regression-testing $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/autonomous-loops .claude/skills/autonomous-loops $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/claude-api .claude/skills/claude-api $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/claude-devfleet .claude/skills/claude-devfleet $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/context-budget .claude/skills/context-budget $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/continuous-agent-loop .claude/skills/continuous-agent-loop $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/continuous-learning-v2 .claude/skills/continuous-learning-v2 $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/continuous-learning .claude/skills/continuous-learning $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/cost-aware-llm-pipeline .claude/skills/cost-aware-llm-pipeline $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/data-scraper-agent .claude/skills/data-scraper-agent $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/deep-research .claude/skills/deep-research $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/enterprise-agent-ops .claude/skills/enterprise-agent-ops $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/eval-harness .claude/skills/eval-harness $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/exa-search .claude/skills/exa-search $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/iterative-retrieval .claude/skills/iterative-retrieval $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/market-research .claude/skills/market-research $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/mcp-server-patterns .claude/skills/mcp-server-patterns $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/nanoclaw-repl .claude/skills/nanoclaw-repl $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/prompt-optimizer .claude/skills/prompt-optimizer $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/regex-vs-llm-structured-text .claude/skills/regex-vs-llm-structured-text $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/search-first .claude/skills/search-first $ npx degit dpthinh910/ai-agent-timmy/.claude/skills/verification-loop .claude/skills/verification-loop
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs-lookup.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.claude/agents/docs-lookup.md $ curl -fsSL --create-dirs -o .claude/agents/harness-optimizer.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.claude/agents/harness-optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/loop-operator.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.claude/agents/loop-operator.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/dpthinh910/ai-agent-timmy/main/.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 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 (26)
agent-evalagent-harness-constructionagentic-engineeringai-first-engineeringai-regression-testingautonomous-loopsclaude-apiclaude-devfleetcontext-budgetcontinuous-agent-loopcontinuous-learning-v2continuous-learningcost-aware-llm-pipelinedata-scraper-agentdeep-researchenterprise-agent-opseval-harnessexa-searchiterative-retrievalmarket-researchmcp-server-patternsnanoclaw-replprompt-optimizerregex-vs-llm-structured-textsearch-firstverification-loop
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 |
| 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. |
| 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 |
| harness-optimizer model: sonnet | Analyze and improve the local agent harness configuration for reliability, cost, and throughput. |
| loop-operator model: sonnet | Operate autonomous agent loops, monitor progress, and intervene safely when loops stall. |
| 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 |
| 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 |
| 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. |
Hooks (12)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | bash -lc 'input=$(cat); root="${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}"; if [ -f "$root/scripts/hooks/run-with-flags.js" ]; then printf "%s" "$input" | node "$root/scripts/hooks/run-with-flags.js" "session:star |
| PreCompact | * | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "pre:compact" "scripts/hooks/pre-compact.js" "standard,strict" |
| PostToolUse | Edit|Write|MultiEdit | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "post:edit:console-warn" "scripts/hooks/post-edit-console-warn.js" "standard,strict" |
| PostToolUse | Edit | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "post:edit:format" "scripts/hooks/post-edit-format.js" "standard,strict" |
| PostToolUse | Edit | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "post:edit:typecheck" "scripts/hooks/post-edit-typecheck.js" "standard,strict" |
| PostToolUse | Edit|Write|MultiEdit | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "post:quality-gate" "scripts/hooks/quality-gate.js" "standard,strict" |
| PostToolUse | * | bash "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags-shell.sh" "post:observe" "skills/continuous-learning-v2/hooks/observe.sh" "standard,strict" |
| Stop | * | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "stop:check-console-log" "scripts/hooks/check-console-log.js" "standard,strict" |
| Stop | * | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "stop:session-end" "scripts/hooks/session-end.js" "minimal,standard,strict" |
| Stop | * | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "stop:evaluate-session" "scripts/hooks/evaluate-session.js" "minimal,standard,strict" |
| Stop | * | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "stop:cost-tracker" "scripts/hooks/cost-tracker.js" "minimal,standard,strict" |
| SessionEnd | * | node "${CLAUDE_PLUGIN_ROOT:-$HOME/Developer/Projects/everything-claude-code}/scripts/hooks/run-with-flags.js" "session:end:marker" "scripts/hooks/session-end-marker.js" "minimal,standard,strict" |
Slash commands (14)
/checkpoint/eval/evolve/instinct-export/instinct-import/instinct-status/learn-eval/learn/multi-execute/multi-plan/multi-workflow/orchestrate/plan/verify
Similar rigs
eugenezhangco-spec/foreman
A 14-agent engineering team for Claude Code. Plans before it builds, reviews before it ships, and never says 'it works' without proof.
Skill Collector 8.5k tok ·
OrdinaryUsr/claude-code-config
Claude Code dotfiles — custom agents, coding rules, and reusable skills for automated development
Fort Knox 20.6k tok ·
thethomaster/Claude_developer_team
Ready-to-clone Claude Code developer team template. 14 named specialist agents (Atlas, Newton, Red, Iris, Cipher + 9 more), onboarding via /init, automated hooks, and a plan-first workflow. Claude acts as manager — agents do the specialist
Orchestrator 5.4k tok ·
loulanyue/awesome-claude-notes
Community-maintained distribution of reusable AI coding agents, commands, skills, hooks, and cross-harness workflows.
MCP Hoarder 45.4k tok ·