studioKjm/dre
The business/domain-analysis counterpart to REA — business model, pricing, financials, and marketing evidence for AI agents. BYOK, free, MCP server.
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · No YOLO mode · Sandbox or ask-first rules · details
Quality 20/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit studioKjm/dre/.claude ./rig-dre # 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.
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/contrarian.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/contrarian.md $ curl -fsSL --create-dirs -o .claude/agents/evaluator.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/evaluator.md $ curl -fsSL --create-dirs -o .claude/agents/hacker.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/hacker.md $ curl -fsSL --create-dirs -o .claude/agents/interviewer.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/interviewer.md $ curl -fsSL --create-dirs -o .claude/agents/ontologist.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/ontologist.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/seed-architect.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/seed-architect.md $ curl -fsSL --create-dirs -o .claude/agents/simplifier.md https://raw.githubusercontent.com/studioKjm/dre/master/.claude/agents/simplifier.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(DROP DATABASE *)",
"Bash(git push --force *)",
"Bash(git push -f *)",
"Bash(git reset --hard *)",
"Bash(sudo rm *)",
"Bash(chmod 777 *)",
"Bash(curl * | sh)",
"Read(./.env.production*)"
],
"ask": [
"Bash(git push *)"
]
}
} Subagents (9)
| architect | USE THIS WHEN symptoms keep recurring, layer boundaries blur, or changes ripple unexpectedly. ALWAYS invoke for structural diagnosis during /unstuck or major refactors. Finds root causes in design, no |
| contrarian | USE THIS WHEN the team reaches quick consensus, before committing to a major design decision, or during /evolve and /unstuck. Challenges assumptions with "what if we're wrong?" scenarios. Always propo |
| evaluator | USE THIS WHEN verifying implementation against a seed spec, running gates, or assessing AC compliance. ALWAYS invoke during /evaluate. Never fixes — only judges Pass/Fail with file:line evidence. Runs |
| hacker | USE THIS WHEN the official path is blocked, a deadline looms, or a temporary workaround is acceptable. ALWAYS invoke during /unstuck when standard approaches fail. Finds safe bypasses (monkey-patch, p |
| interviewer | USE PROACTIVELY whenever the user describes a new feature, vague requirement, or unclear goal. ALWAYS run BEFORE writing code or creating a seed spec. Asks Socratic questions to surface hidden assumpt |
| ontologist | USE THIS WHEN defining domain terms, extracting entities/relationships from requirements, or unifying synonyms (e.g., "user" vs "member" vs "account"). ALWAYS invoke during /seed spec generation. Extr |
| researcher | USE THIS WHEN a claim needs evidence, debugging requires history, or library/API behavior is uncertain. ALWAYS invoke before guessing — checks official docs, existing code patterns, git log/blame firs |
| seed-architect | USE THIS WHEN crystallizing interview results into an immutable specification. ALWAYS invoke during /seed. Converts conversation + ontology into structured seed YAML with zero TODO/TBD tolerance. Bloc |
| simplifier | USE THIS WHEN code feels over-engineered, scope seems to creep, or abstractions pile up. ALWAYS invoke during /evolve and /unstuck. Asks "is this needed for MVP?" on every feature. YAGNI-first — prefe |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit|Write|MultiEdit | ${CLAUDE_PROJECT_DIR}/.harness/hooks/post-edit-lint.sh |
Slash commands (13)
/decompose/evaluate/evolve/install/interview/methodology/pm/review/rollback/run/seed/trd/unstuck
Permissions
deny (9)
Bash(rm -rf /*)
Bash(DROP DATABASE *)
Bash(git push --force *)
Bash(git push -f *)
Bash(git reset --hard *)
Bash(sudo rm *)
Bash(chmod 777 *)
Bash(curl * | sh)
Read(./.env.production*)
ask (1)
Bash(git push *)
allow (22)
Read
Glob
Grep
Bash(git *)
Bash(ls *)
Bash(pwd)
Bash(cat *)
Bash(head *)
Bash(tail *)
Bash(find *)
Bash(wc *)
Bash(npm *)
Bash(npx *)
Bash(pnpm *)
Bash(yarn *)
Bash(bun *)
Bash(pip *)
Bash(python *)
Bash(pytest *)
Bash(docker compose *)
Bash(docker ps *)
Bash(docker logs *)
Similar rigs
ufukyuksel-dev/SUPER_COMPUTER_AI
Build your own super AI: skills, MCP servers, agent roles and instructions for Claude Code and Codex, installed with one reversible command.
Orchestrator 806 tok · · Q5
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
yourconscience/tackroom
Dotfiles for your AI agents: one ~/.agents repo for skills, MCP servers, hooks, agent roles, and memory — synced natively to Claude Code, Codex, OMP/Pi, OpenCode, Droid, and Hermes. Commit-pinned and audited externals.
Orchestrator 1.4k tok · · Q8
ManeeshJupalle/claude-build-crew
Claude Code plugin: agents plan, build, review and ship; code gates decide what merges. macOS, Linux and Windows.
Orchestrator 563 tok · · Q0