UtmostCreator/app-configs
Dotfiles for NixOS, macOS, Linux and WSL: Nix flakes, Home Manager, chezmoi, mise and Homebrew, configuring bash, zsh, fish, tmux, Neovim, VS Code, Git and SSH, with a one-command bootstrap and rollback.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~8.9k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add codebase-memory-mcp -e CBM_ALLOWED_ROOT=YOUR_CBM_ALLOWED_ROOT -- codebase-memory-mcp $ npx degit UtmostCreator/app-configs/.claude ./rig-app-configs # 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.
$ claude mcp add codebase-memory-mcp -e CBM_ALLOWED_ROOT=YOUR_CBM_ALLOWED_ROOT -- codebase-memory-mcp $ npx degit UtmostCreator/app-configs/.agents/skills/agent-definition-review .claude/skills/agent-definition-review $ npx degit UtmostCreator/app-configs/.agents/skills/audit-agent-fleet .claude/skills/audit-agent-fleet $ npx degit UtmostCreator/app-configs/.agents/skills/autopilot .claude/skills/autopilot $ npx degit UtmostCreator/app-configs/.agents/skills/bug-reproduction-and-fix .claude/skills/bug-reproduction-and-fix $ npx degit UtmostCreator/app-configs/.agents/skills/change-reporting .claude/skills/change-reporting $ npx degit UtmostCreator/app-configs/.agents/skills/change-traceability .claude/skills/change-traceability $ npx degit UtmostCreator/app-configs/.agents/skills/characterization-testing .claude/skills/characterization-testing $ npx degit UtmostCreator/app-configs/.agents/skills/check-agent-request-fit .claude/skills/check-agent-request-fit $ npx degit UtmostCreator/app-configs/.agents/skills/clarification .claude/skills/clarification $ npx degit UtmostCreator/app-configs/.agents/skills/config-change-safety .claude/skills/config-change-safety $ npx degit UtmostCreator/app-configs/.agents/skills/contract-boundaries .claude/skills/contract-boundaries $ npx degit UtmostCreator/app-configs/.agents/skills/dependency-upgrade .claude/skills/dependency-upgrade $ npx degit UtmostCreator/app-configs/.agents/skills/design-agent-runtime-guardrails .claude/skills/design-agent-runtime-guardrails $ npx degit UtmostCreator/app-configs/.agents/skills/detect-tech-stack .claude/skills/detect-tech-stack $ npx degit UtmostCreator/app-configs/.agents/skills/docs-sync .claude/skills/docs-sync $ npx degit UtmostCreator/app-configs/.agents/skills/feature-planning .claude/skills/feature-planning $ npx degit UtmostCreator/app-configs/.agents/skills/glyphbrace-post-install-setup .claude/skills/glyphbrace-post-install-setup $ npx degit UtmostCreator/app-configs/.agents/skills/human-handoff .claude/skills/human-handoff $ npx degit UtmostCreator/app-configs/.agents/skills/infra-risk-audit .claude/skills/infra-risk-audit $ npx degit UtmostCreator/app-configs/.agents/skills/mentor-mode .claude/skills/mentor-mode $ npx degit UtmostCreator/app-configs/.agents/skills/project-context .claude/skills/project-context $ npx degit UtmostCreator/app-configs/.agents/skills/release-safety .claude/skills/release-safety $ npx degit UtmostCreator/app-configs/.agents/skills/repo-investigation .claude/skills/repo-investigation $ npx degit UtmostCreator/app-configs/.agents/skills/repo-search .claude/skills/repo-search $ npx degit UtmostCreator/app-configs/.agents/skills/review-diff .claude/skills/review-diff $ npx degit UtmostCreator/app-configs/.agents/skills/runtime-evidence .claude/skills/runtime-evidence $ npx degit UtmostCreator/app-configs/.agents/skills/safe-refactor .claude/skills/safe-refactor $ npx degit UtmostCreator/app-configs/.agents/skills/script-inventory .claude/skills/script-inventory $ npx degit UtmostCreator/app-configs/.agents/skills/select-repo-commands .claude/skills/select-repo-commands $ npx degit UtmostCreator/app-configs/.agents/skills/technical-change-planning .claude/skills/technical-change-planning $ npx degit UtmostCreator/app-configs/.agents/skills/test-quality-audit .claude/skills/test-quality-audit $ npx degit UtmostCreator/app-configs/.agents/skills/verify-change .claude/skills/verify-change $ npx degit UtmostCreator/app-configs/.agents/skills/verify-ui-change .claude/skills/verify-ui-change $ npx degit UtmostCreator/app-configs/.agents/skills/workflow-drift-audit .claude/skills/workflow-drift-audit
$ curl -fsSL --create-dirs -o .claude/agents/agent-definition-reviewer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/agent-definition-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/agent-factory.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/agent-factory.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/configuration-maintainer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/configuration-maintainer.md $ curl -fsSL --create-dirs -o .claude/agents/fleet-assessor.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/fleet-assessor.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/local-maintainer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/local-maintainer.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/phoenix-analyzer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/phoenix-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-writer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/plan-writer.md $ curl -fsSL --create-dirs -o .claude/agents/release-auditor.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/release-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/super-implementer.md https://raw.githubusercontent.com/UtmostCreator/app-configs/main/.claude/agents/super-implementer.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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| codebase-memory-mcp env: CBM_ALLOWED_ROOT | binary | 2.5k |
Skills (34)
agent-definition-reviewaudit-agent-fleetautopilotbug-reproduction-and-fixchange-reportingchange-traceabilitycharacterization-testingcheck-agent-request-fitclarificationconfig-change-safetycontract-boundariesdependency-upgradedesign-agent-runtime-guardrailsdetect-tech-stackdocs-syncfeature-planningglyphbrace-post-install-setuphuman-handoffinfra-risk-auditmentor-modeproject-contextrelease-safetyrepo-investigationrepo-searchreview-diffruntime-evidencesafe-refactorscript-inventoryselect-repo-commandstechnical-change-planningtest-quality-auditverify-changeverify-ui-changeworkflow-drift-audit
Subagents (14)
| agent-definition-reviewer model: sonnet | Use to audit one agent instruction file for format fit, role and tool fit, contradictions, next-step advice and token economy. Returns a 0-100 score, exact fixes and a proposed assessment. One file pe |
| agent-factory model: sonnet | Use to propose a new agent or materially revise an existing agent definition. Check reuse, prepare a draft, validate request fit and design guardrails. Normally return the draft without writing files; |
| architect model: opus | Use when a change needs scoping or design before implementation: ownership, contracts and boundaries, adapter strategy, risk, acceptance criteria and a plan. It reads the repository and returns a desi |
| configuration-maintainer model: sonnet | Use for scoped changes to deployment and runtime configuration, including container and compose files, service definitions, runtime flags and environment templates. Preserve unrelated behaviour and ve |
| fleet-assessor model: sonnet | Use to assess every installed agent file, one at a time, and rank the results 0-100 with fix priorities. Reviews all agents, not one file. Does not edit definitions. |
| implementer model: sonnet | Use to implement one bounded change, such as a bug fix, a feature or a refactor, with focused verification and the project's own conventions. May update multiple ordinary source files within the agree |
| local-maintainer model: sonnet | Use only when the user explicitly asks for a change to the project's own agent setup and tooling: agent and skill files, instruction files, generated catalogs, or local provider and tool configuration |
| orchestrator model: opus | Use only when the user asks to coordinate a multi-step task across this project's installed agents, such as research, design, implementation and review. It plans the stages, delegates each one and che |
| phoenix-analyzer model: sonnet | Use to analyse AI agent workflows recorded in Arize Phoenix, for one project or all of them: delegation chains, routing decisions, false completion claims, tool, cost and performance signals, and miss |
| plan-writer model: haiku | Use to write a finished design's plan to a Markdown file, or to update an existing plan file with progress that was reported and evidenced. It edits only the plan file; it does not design, implement o |
| release-auditor model: opus | Use before releasing a medium or high risk change, or one that touches a public surface, to audit rollout, rollback, migration, observability and install safety. It reads the change and the evidence o |
| researcher model: sonnet | Use for read-only investigation when scope, ownership, usage, contracts, tests, generated files or current changes must be established before planning, implementing or reviewing. It reports evidence; |
| reviewer model: opus | Use to independently assess a change set or technical design decision for correctness, regressions, contract fit, duplication and missing verification. May run focused checks in authorised isolated te |
| super-implementer model: opus | Use only when the user explicitly requests a bounded change beyond an ordinary implementation slice: generator or template sources and their generated outputs, build/toolchain scripts, or inseparable |
Similar rigs
homeofe/improvements
Portable, LLM-agnostic framework for multi-model AI workflows: model routing, structured agent handoff (AAHP), and a phased agent pipeline. MIT.
Orchestrator 1.4k tok · · Q24
IntuitivePhella/AI-PhellOS
Portable AI development workflow template and CLI for spec-driven, test-aware software delivery with Codex, Claude Code, and other coding agents.
Orchestrator 3.1k tok · · Q31
Fili999/ai-hub
One hub for your AI coding agents, skills and workflows: write them once, install them into Claude Code, Codex, Antigravity CLI and local models. Free, open source, runs on your computer.
Minimalist 903 tok · · Q8
yuroka-studio/nightshift-agents
Scheduled Claude Code agents that take one task from a backlog, open a PR with real test evidence, and never merge or deploy on their own.
Fort Knox 1.0k tok · · Q61