srepollock/dotfiles
Personal dotfiles. Used for quick system builds and startups.
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Quality 25/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit srepollock/dotfiles/.claude ./rig-dotfiles # 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 srepollock/dotfiles/.claude/skills/ast-refactorer .claude/skills/ast-refactorer $ npx degit srepollock/dotfiles/.claude/skills/changelog-generator .claude/skills/changelog-generator $ npx degit srepollock/dotfiles/.claude/skills/compact-safe .claude/skills/compact-safe $ npx degit srepollock/dotfiles/.claude/skills/factory .claude/skills/factory $ npx degit srepollock/dotfiles/.claude/skills/grill-me .claude/skills/grill-me $ npx degit srepollock/dotfiles/.claude/skills/issue .claude/skills/issue $ npx degit srepollock/dotfiles/.claude/skills/mock-server-factory .claude/skills/mock-server-factory $ npx degit srepollock/dotfiles/.claude/skills/pr .claude/skills/pr $ npx degit srepollock/dotfiles/.claude/skills/rc .claude/skills/rc $ npx degit srepollock/dotfiles/.claude/skills/roadmap-generator .claude/skills/roadmap-generator $ npx degit srepollock/dotfiles/.claude/skills/sandbox-manager .claude/skills/sandbox-manager $ npx degit srepollock/dotfiles/.claude/skills/security-review .claude/skills/security-review $ npx degit srepollock/dotfiles/.claude/skills/security-scanner .claude/skills/security-scanner $ npx degit srepollock/dotfiles/.claude/skills/ship-changes .claude/skills/ship-changes $ npx degit srepollock/dotfiles/.claude/skills/start-day .claude/skills/start-day $ npx degit srepollock/dotfiles/.claude/skills/telemetry-analyzer .claude/skills/telemetry-analyzer $ npx degit srepollock/dotfiles/.claude/skills/to-issues .claude/skills/to-issues $ npx degit srepollock/dotfiles/.claude/skills/to-prd .claude/skills/to-prd $ npx degit srepollock/dotfiles/.claude/skills/tribunal .claude/skills/tribunal $ npx degit srepollock/dotfiles/.claude/skills/update-version .claude/skills/update-version $ npx degit srepollock/dotfiles/.claude/skills/workspace-indexer .claude/skills/workspace-indexer
$ curl -fsSL --create-dirs -o .claude/agents/api-documenter.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/api-documenter.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/bug-fixer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/bug-fixer.md $ curl -fsSL --create-dirs -o .claude/agents/dependency-updater.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/dependency-updater.md $ curl -fsSL --create-dirs -o .claude/agents/factory-approver.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/factory-approver.md $ curl -fsSL --create-dirs -o .claude/agents/factory-builder.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/factory-builder.md $ curl -fsSL --create-dirs -o .claude/agents/factory-review-code.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/factory-review-code.md $ curl -fsSL --create-dirs -o .claude/agents/factory-review-security.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/factory-review-security.md $ curl -fsSL --create-dirs -o .claude/agents/factory-review-ui.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/factory-review-ui.md $ curl -fsSL --create-dirs -o .claude/agents/factory-review-ux.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/factory-review-ux.md $ curl -fsSL --create-dirs -o .claude/agents/factory-spec-writer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/factory-spec-writer.md $ curl -fsSL --create-dirs -o .claude/agents/feature-builder.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/feature-builder.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-specialist.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/frontend-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/implementation-planner.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/implementation-planner.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/integration-specialist.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/integration-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/performance-analyzer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/performance-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-architect.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/plan-architect.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/pr-description-generator.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/pr-description-generator.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-specialist.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/test-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/thorough-reviewer.md https://raw.githubusercontent.com/srepollock/dotfiles/trunk/.claude/agents/thorough-reviewer.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": [
"Bash(rm -rf /*)",
"Bash(sudo rm:*)",
"Bash(dd:*)",
"Read(**/.env)",
"Read(**/.env.local)",
"Read(**/.env.*.local)",
"Read(~/.ssh/**)",
"Read(~/.claude/.credentials.json)",
"Read(~/.claude/settings.local.json)",
"Edit(**/.env)",
"Edit(**/.env.local)",
"Edit(**/.env.*.local)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "python3 $HOME/.claude/hooks/block-sensitive-writes.py"
}
]
}
]
}
} Skills (21)
ast-refactorerchangelog-generatorcompact-safefactorygrill-meissuemock-server-factoryprrcroadmap-generatorsandbox-managersecurity-reviewsecurity-scannership-changesstart-daytelemetry-analyzerto-issuesto-prdtribunalupdate-versionworkspace-indexer
Subagents (26)
| api-documenter model: haiku | Use when API endpoints (REST, GraphQL) need documenting or an existing OpenAPI spec or docs/api.md needs updating to match the code; not for prose guides or code changes. |
| Architect model: inherit | Use when a design or change needs a structural review for pattern fit, coupling, modularity and scalability, or a tie-break between conflicting designs; not for writing plans or code. |
| Bug-Fixer model: sonnet | Use when a defect, failing test or regression needs root-cause diagnosis and a minimal surgical fix; not for new features or planned multi-file changes (use Feature-Builder or Implementer). |
| dependency-updater model: sonnet | Safely updates project dependencies. Use when packages are outdated, security advisories exist, or before major releases. Updates incrementally with testing between steps, not all at once. |
| factory-approver model: opus | Used only by the /factory orchestrator after all reviews pass, to decide APPROVE (auto-merge) or ESCALATE (needs a human) and write JOB_DIR/decision.md. Not for general use. |
| factory-builder model: opus | Used only by the /factory orchestrator to implement JOB_DIR/spec.md on a feature branch worktree, write tests per acceptance criterion, commit, and write JOB_DIR/build.md; resumed each review round. N |
| factory-review-code model: sonnet | Used only by the /factory orchestrator to review a factory job's code quality and acceptance-criteria test coverage and write ROUND_DIR/review-code.md. Not for general use. |
| factory-review-security model: opus | Used only by the /factory orchestrator to security-review a factory job's branch diff and write ROUND_DIR/review-security.md. Not for general use. |
| factory-review-ui model: sonnet | Used only by the /factory orchestrator to review a factory job's visual UI design and write ROUND_DIR/review-ui.md. Not for general use. |
| factory-review-ux model: sonnet | Used only by the /factory orchestrator to review a factory job's user experience (end users, CLI users, API consumers) and write ROUND_DIR/review-ux.md. Not for general use. |
| factory-spec-writer model: opus | Used only by the /factory orchestrator to turn a feature request into JOB_DIR/spec.md with testable acceptance criteria. Not for general use. |
| Feature-Builder model: sonnet | Use when a new feature or capability needs end-to-end implementation from requirements, including scaffolding, logic and docstrings; not for executing a pre-written TODO list (use Implementer) or fixi |
| Frontend-Specialist model: sonnet | Use when building or changing UI components, client state management, accessibility (ARIA, semantic HTML) or responsive layout; not for backend, API or infrastructure work. |
| Implementation-Planner model: sonnet | Use when an architected plan needs converting into a granular, file-level TodoWrite checklist an Implementer can follow linearly; not for designing the plan itself (use Planner or Plan Architect). |
| Implementer model: sonnet | Use when a well-specified change from a written plan or TODO list needs executing exactly as scoped; not for design decisions, open-ended features (Feature-Builder) or debugging (Bug-Fixer). |
| Integration-Specialist model: inherit | Use when work touches external service connections, webhooks, third-party API contracts, or retry, timeout and circuit-breaker resilience; not for purely internal logic. |
| Orchestrator model: inherit | Use when a request is complex and multi-stage, needing several sub-agents (plan, implement, review) coordinated and their outputs synthesized; not for single-agent tasks or producing a plan only. |
| Performance-Analyzer model: inherit | Use when code is slow or resource-heavy and needs algorithmic complexity analysis, profiling or bottleneck hunting; not for general code review or functional bugs. |
| Plan Architect model: inherit | Use when a plan must be generated and architecturally validated end-to-end, returning a Validated or Blocked verdict with risks; not for a quick roadmap (Planner) or per-file TODO breakdown (Implement |
| Planner model: inherit | Use when a feature, bug fix or refactor needs a phased plan with tasks, risks and validation steps before coding; not for architectural validation (Plan Architect) or writing code. |
| PR Description Generator model: haiku | Use when a pull request description is needed from the current branch diff and commit log against the base branch; not for reviewing code or creating the PR. |
| Reviewer model: inherit | Use proactively after code changes for a routine review of standards, performance, basic security and async correctness; not for deep multi-angle review of complex changes (Thorough Reviewer) or diff- |
| security-reviewer model: fable | Diff-scoped security review. Operates only on the changed-file set for a given git range and emits a fixed findings table. Covers secrets, injection, and authz. |
| Test Specialist model: fable | Improves code quality by designing and writing comprehensive tests. |
| test-writer model: sonnet | Use when tests need writing for new or untested code, matching the project's framework and conventions, covering edge cases and regressions; not for modifying production code. |
| Thorough Reviewer model: inherit | Use proactively after large or risky changes for a final multi-angle review covering correctness, security, performance and architecture; not for routine small diffs (use Reviewer). |
Hooks (7)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Edit|Write | python3 $HOME/.claude/hooks/block-sensitive-writes.py |
| PostToolUse | Bash | $HOME/.claude/hooks/log-bash-command.sh |
| PostToolUse | Edit|Write | $HOME/.claude/hooks/prettier-format.sh |
| Notification | permission_prompt | $HOME/.claude/hooks/notify.sh 'Permission requested — check your terminal' |
| Notification | idle_prompt | $HOME/.claude/hooks/notify.sh 'Claude is waiting for your input' |
| SessionStart | * | $HOME/.claude/hooks/dotfiles-drift-notice.sh |
| SessionStart | * | echo 'Reminder: use conventional commits. Prefer bun over npm. /compact before stepping away.' |
Slash commands (3)
/commit/history/secrev
Plugins (16)
commit-commands@claude-plugins-officialcode-review@claude-plugins-officialhookify@claude-plugins-officialfeature-dev@claude-plugins-officialfrontend-design@claude-plugins-officialsuperpowers@claude-plugins-officialskill-creator@claude-plugins-officialgithub@claude-plugins-officialsecurity-guidance@claude-plugins-officialcontext7@claude-plugins-officialpr-review-toolkit@claude-plugins-officialdocument-skills@anthropic-agent-skillsexample-skills@anthropic-agent-skillsui-ux-pro-max@ui-ux-pro-max-skillcc-plugin-you-should-know@builtindrive-brain@drive-brain
Permissions
deny (12)
Bash(rm -rf /*)
Bash(sudo rm:*)
Bash(dd:*)
Read(**/.env)
Read(**/.env.local)
Read(**/.env.*.local)
Read(~/.ssh/**)
Read(~/.claude/.credentials.json)
Read(~/.claude/settings.local.json)
Edit(**/.env)
Edit(**/.env.local)
Edit(**/.env.*.local)
ask (0)
—
allow (61)
Bash(git:*)
Bash(npm:*)
Bash(npx:*)
Bash(node:*)
Bash(yarn:*)
Bash(pnpm:*)
Bash(bun:*)
Bash(bunx:*)
Bash(python:*)
Bash(python3:*)
Bash(pip:*)
Bash(pip3:*)
Bash(cargo:*)
Bash(rustc:*)
Bash(go:*)
Bash(docker:*)
Bash(docker-compose:*)
Bash(gh:*)
Bash(ls:*)
Bash(cat:*)
Bash(echo:*)
Bash(which:*)
Bash(pwd:*)
Bash(whoami:*)
Bash(env:*)
Bash(mkdir:*)
Bash(cp:*)
Bash(mv:*)
Bash(touch:*)
Bash(chmod:*)
Bash(curl:*)
Bash(jq:*)
Bash(make:*)
Bash(grep:*)
Bash(find:*)
Bash(sed:*)
Bash(awk:*)
Bash(sort:*)
Bash(uniq:*)
Bash(wc:*)
Bash(head:*)
Bash(tail:*)
Bash(diff:*)
Bash(tar:*)
Bash(zip:*)
Bash(unzip:*)
Bash(npm run:*)
Bash(npm --version:*)
Bash(node --version:*)
Bash(git add:*)
Bash(git status:*)
Bash(git fetch:*)
Bash(git checkout:*)
Bash(git grep:*)
Bash(git log:*)
Bash(git ls-tree:*)
Bash(source:*)
Bash(npx tsc:*)
Bash(yarn run:*)
Bash(pip install:*)
Similar rigs
ameya-vichare/claude-sdd-starter
A platform-agnostic Claude Code setup for engineering teams, using an interactive setup wizard that tailors everything to your project and provides a spec-driven feature development workflow.
Orchestrator 2.3k tok · · Q3
kevingo710/dota2App
React Native app built and verified by a team of AI agents: deterministic gate, evals, hybrid Claude/local routing, live Neo4j agent graph
Fort Knox 3.9k tok · · Q60
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
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 · · Q0