aspenkit/aspens
Your CLAUDE.md stopped working at 200 lines. Generate scoped skill files from your import graph, auto-sync on every commit. Claude Code, Codex and OpenCode.
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 aspenkit/aspens/.claude ./rig-aspens # 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 aspenkit/aspens/.agents/skills/agent-customization .claude/skills/agent-customization $ npx degit aspenkit/aspens/.agents/skills/architecture .claude/skills/architecture $ npx degit aspenkit/aspens/.agents/skills/base .claude/skills/base $ npx degit aspenkit/aspens/.agents/skills/claude-runner .claude/skills/claude-runner $ npx degit aspenkit/aspens/.agents/skills/cli-shell .claude/skills/cli-shell $ npx degit aspenkit/aspens/.agents/skills/codex-support .claude/skills/codex-support $ npx degit aspenkit/aspens/.agents/skills/doc-impact .claude/skills/doc-impact $ npx degit aspenkit/aspens/.agents/skills/doc-sync .claude/skills/doc-sync $ npx degit aspenkit/aspens/.agents/skills/import-graph .claude/skills/import-graph $ npx degit aspenkit/aspens/.agents/skills/repo-scanning .claude/skills/repo-scanning $ npx degit aspenkit/aspens/.agents/skills/save-tokens .claude/skills/save-tokens $ npx degit aspenkit/aspens/.agents/skills/skill-generation .claude/skills/skill-generation $ npx degit aspenkit/aspens/.agents/skills/template-library .claude/skills/template-library
$ curl -fsSL --create-dirs -o .claude/agents/auto-error-resolver.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/auto-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-architecture-reviewer.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/code-architecture-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-refactor-master.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/code-refactor-master.md $ curl -fsSL --create-dirs -o .claude/agents/documentation-architect.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/documentation-architect.md $ curl -fsSL --create-dirs -o .claude/agents/execute.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/execute.md $ curl -fsSL --create-dirs -o .claude/agents/ghost-writer.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/ghost-writer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/plan.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/plan.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-planner.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/refactor-planner.md $ curl -fsSL --create-dirs -o .claude/agents/ux-ui-designer.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/ux-ui-designer.md $ curl -fsSL --create-dirs -o .claude/agents/web-research-specialist.md https://raw.githubusercontent.com/aspenkit/aspens/main/.claude/agents/web-research-specialist.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (13)
agent-customizationarchitecturebaseclaude-runnercli-shellcodex-supportdoc-impactdoc-syncimport-graphrepo-scanningsave-tokensskill-generationtemplate-library
Subagents (11)
| auto-error-resolver model: sonnet | Fix compilation errors, build failures, type errors, or test failures. Systematically identifies root causes and fixes them in order. |
| code-architecture-reviewer model: sonnet | Review code for quality, architectural consistency, and integration issues. Use after implementing features, refactoring, or before merging PRs. |
| code-refactor-master model: sonnet | Execute refactoring tasks — reorganize files, extract components, update imports, fix patterns across the codebase. Use after a refactor-planner has created a plan. |
| documentation-architect model: sonnet | Create or update documentation — READMEs, API docs, architecture overviews, data flow diagrams, developer guides. Reads actual code first, never documents from assumptions. |
| execute model: opus | Execute a development plan created by the plan agent — spawn parallel subagents per phase, test, and ship. |
| ghost-writer model: sonnet | Write compelling, human-sounding content — landing pages, marketing copy, user docs, social media, email sequences, blog posts. Produces distinctive prose that avoids AI patterns. |
| plan-reviewer model: sonnet | Review development plans for completeness, feasibility, risks, and missed considerations before implementation begins. |
| plan model: opus | Triage, analyze, and create phased development plans. Iterate with the user until the plan is approved. |
| refactor-planner model: sonnet | Analyze code and create comprehensive refactoring plans with phases, risk assessment, and step-by-step strategy. Use BEFORE code-refactor-master executes. |
| ux-ui-designer model: sonnet | UX/UI design guidance — component specs with states, accessibility audits, user flow analysis, design system recommendations. For developers building interfaces. |
| web-research-specialist model: sonnet | Research technical topics by searching the web — debug errors, compare solutions, find best practices from GitHub issues, Stack Overflow, documentation, and community resources. |
Hooks (5)
| event | matcher | runs |
|---|---|---|
| UserPromptSubmit | * | "$CLAUDE_PROJECT_DIR/.claude/hooks/skill-activation-prompt.sh" |
| UserPromptSubmit | * | "$CLAUDE_PROJECT_DIR/.claude/hooks/save-tokens-prompt-guard.sh" |
| UserPromptSubmit | * | "$CLAUDE_PROJECT_DIR/.claude/hooks/graph-context-prompt.sh" |
| PostToolUse | Edit|MultiEdit|Write | "$CLAUDE_PROJECT_DIR/.claude/hooks/post-tool-use-tracker.sh" |
| PreCompact | * | "$CLAUDE_PROJECT_DIR/.claude/hooks/save-tokens-precompact.sh" |
Slash commands (3)
/resume-handoff-latest/resume-handoff/save-handoff
Similar rigs
diet103/claude-code-infrastructure-showcase
Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents
Orchestrator 1.0k tok ·
fancyboi999/open-tag
Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays o
Pragmatist 4.1k tok ·
Tokiki17/okf-doc-sync
Host-neutral Agent Skill that keeps living docs, agent instruction files, and an OKF knowledge bundle in sync
Minimalist 884 tok ·
HGInsights/claude-code-setup
Production-tested Claude Code harness configuration: hooks, skills, subagents, and automated review loops
Pragmatist 1.9k tok ·