Kastalien-Research/thoughtbox-dot-claude
Thoughtbox's standard Claude Code setup.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude ./rig-thoughtbox-dot-claude # 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 Kastalien-Research/thoughtbox-dot-claude/.claude/skills/docker .claude/skills/docker $ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude/skills/effect-ts .claude/skills/effect-ts $ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude/skills/mcp-builder .claude/skills/mcp-builder $ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude/skills/mcp-client-builder .claude/skills/mcp-client-builder $ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude/skills/memory-system-expert .claude/skills/memory-system-expert $ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude/skills/skill-creator .claude/skills/skill-creator $ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude/skills/template-skill .claude/skills/template-skill $ npx degit Kastalien-Research/thoughtbox-dot-claude/.claude/skills/zod4 .claude/skills/zod4
$ curl -fsSL --create-dirs -o .claude/agents/fact-checking-agent.md https://raw.githubusercontent.com/Kastalien-Research/thoughtbox-dot-claude/main/.claude/agents/fact-checking-agent.md $ curl -fsSL --create-dirs -o .claude/agents/meta-agent.md https://raw.githubusercontent.com/Kastalien-Research/thoughtbox-dot-claude/main/.claude/agents/meta-agent.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 (8)
Docker Patternseffect-tsmcp-buildermcp-client-buildermemory-system-expertskill-creatortemplate-skillzod4
Subagents (2)
| fact-checking-agent model: sonnet | Use proactively to verify claims in documentation against sources of truth (codebase, web data, or research). Identifies claims, locates verification sources, validates accuracy, and corrects mismatch |
| meta-agent model: opus | Generates a new, complete Claude Code sub-agent configuration file from a user's description. Use this to create new agents. Use this Proactively when the user asks you to create a new sub agent. |
Slash commands (74)
/analysis/context-aware-review/analysis/evolution-tracker/analysis/knowledge-graph/analysis/recover-parallel/analysis/time-machine/clear-thought/think-create/clear-thought/think-debug/clear-thought/think-decide/clear-thought/think-research/clear-thought/think-solve/clear-thought/think-strategy/debugging/distributed-debug/debugging/systematic-debug/debugging/temporal-debug/development/implement-spec/development/implementation-variants/development/parallel-executor/development/spec-to-test/exploration/parallel-explorer/loops/authoring/code-generation/loops/authoring/documentation/loops/authoring/spec-drafting/loops/exploration/codebase-discovery/loops/exploration/domain-research/loops/exploration/problem-space/loops/meta/composition-patterns/loops/meta/loop-interface/loops/orchestration/dependency-resolver/loops/orchestration/queue-processor/loops/orchestration/spiral-detector/loops/refinement/code-quality/loops/refinement/consistency-check/loops/refinement/requirement-quality/loops/verification/acceptance-gate/loops/verification/fact-checking/loops/verification/integration-test/memory/add-quick/memory/search/memory/start/meta/capture-learning/meta/code-review-game/meta/complexity-navigator/meta/dgm-evolve/meta/feature-discovery/meta/learning-accelerator/meta/refactoring-game/meta/ulysses-protocol/meta/virgil-protocol/orchestration/adaptive-workflow/orchestration/meta-orchestrator/orchestration/swarm-intelligence/research/docs-researcher/startup/metaclaude/startup/metacursor/startup/prime/synthesis/knowledge-fusion/synthesis/pattern-synthesizer/synthesis/synthesis-dgm/synthesis/wisdom-distillation/toolscontext/context7/toolscontext/exa/toolscontext/firecrawl/utils/post-edit-workflow/workflows/claude-code-native-workflow/workflows/fact-check-docs/workflows/fact-check-standalone/workflows/mcp-battle-orchestrator/workflows/mcp-chain/workflows/mcp-orchestrate/workflows/mcp-recipe/workflows/mcp-workflow/workflows/spec-designer/workflows/spec-orchestrator/workflows/spec-validator
Similar rigs
codeclawd/fable-mode
Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillation (FABLE_CODE.md), measured playbook, verification hooks, and design/MCP/test skills. "Fable 5 Lit
Pragmatist 566 tok ·
PleasePrompto/ductor
Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, webhooks, Docker sandboxing.
Minimalist 1.9k tok ·
Abdullah-967/my-claudec0de-setup-2026
Transform Claude Code into a professional autonomous agent. This setup includes structured context handoffs, a features.json tracking system, and built-in workflows for synchronization and semantic commits.
Pragmatist 750 tok ·
dukcode/claude-dotfiles
Personal configuration files for Claude Code — skills, hooks, and settings.claude-config
Minimalist 155 tok ·