mehrad-dm/mastermind
⚗️ Experimental — A markdown brain that gives your AI coding tools judgment and rigor: sharp defaults, real decisions, and the discipline to verify before saying done. For Claude Code, Cursor and Codex. It improves itself over time.
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 mehrad-dm/mastermind/agents ./rig-mastermind/agents $ npx degit mehrad-dm/mastermind/skills ./rig-mastermind/skills $ npx degit mehrad-dm/mastermind/hooks ./rig-mastermind/hooks
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 mehrad-dm/mastermind/skills/analyze .claude/skills/analyze $ npx degit mehrad-dm/mastermind/skills/assess .claude/skills/assess $ npx degit mehrad-dm/mastermind/skills/blueprint .claude/skills/blueprint $ npx degit mehrad-dm/mastermind/skills/breakdown .claude/skills/breakdown $ npx degit mehrad-dm/mastermind/skills/checklist .claude/skills/checklist $ npx degit mehrad-dm/mastermind/skills/clarify .claude/skills/clarify $ npx degit mehrad-dm/mastermind/skills/constitution .claude/skills/constitution $ npx degit mehrad-dm/mastermind/skills/converge .claude/skills/converge $ npx degit mehrad-dm/mastermind/skills/debug .claude/skills/debug $ npx degit mehrad-dm/mastermind/skills/deepen .claude/skills/deepen $ npx degit mehrad-dm/mastermind/skills/deprecate .claude/skills/deprecate $ npx degit mehrad-dm/mastermind/skills/double-check .claude/skills/double-check $ npx degit mehrad-dm/mastermind/skills/explain .claude/skills/explain $ npx degit mehrad-dm/mastermind/skills/handoff .claude/skills/handoff $ npx degit mehrad-dm/mastermind/skills/help .claude/skills/help $ npx degit mehrad-dm/mastermind/skills/init .claude/skills/init $ npx degit mehrad-dm/mastermind/skills/interview .claude/skills/interview $ npx degit mehrad-dm/mastermind/skills/learn .claude/skills/learn $ npx degit mehrad-dm/mastermind/skills/levelup .claude/skills/levelup $ npx degit mehrad-dm/mastermind/skills/lint .claude/skills/lint $ npx degit mehrad-dm/mastermind/skills/living-docs .claude/skills/living-docs $ npx degit mehrad-dm/mastermind/skills/performance .claude/skills/performance $ npx degit mehrad-dm/mastermind/skills/persona .claude/skills/persona $ npx degit mehrad-dm/mastermind/skills/prompt .claude/skills/prompt $ npx degit mehrad-dm/mastermind/skills/prototype .claude/skills/prototype $ npx degit mehrad-dm/mastermind/skills/qa .claude/skills/qa $ npx degit mehrad-dm/mastermind/skills/quarantine .claude/skills/quarantine $ npx degit mehrad-dm/mastermind/skills/report .claude/skills/report $ npx degit mehrad-dm/mastermind/skills/roadmap .claude/skills/roadmap $ npx degit mehrad-dm/mastermind/skills/route .claude/skills/route $ npx degit mehrad-dm/mastermind/skills/signature .claude/skills/signature $ npx degit mehrad-dm/mastermind/skills/specify .claude/skills/specify
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/about/architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/about/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/about/refactorer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-scout.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/about/tech-scout.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/refactorer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-scout.md https://raw.githubusercontent.com/mehrad-dm/mastermind/master/agents/tech-scout.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"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(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (32)
analyzeassessblueprintbreakdownchecklistclarifyconstitutionconvergedebugdeependeprecatedouble-checkexplainhandoffhelpinitinterviewlearnleveluplintliving-docsperformancepersonapromptprototypeqaquarantinereportroadmaproutesignaturespecify
Subagents (8)
| architect | — |
| code-reviewer | — |
| refactorer | — |
| tech-scout | — |
| architect | Designs the solution BEFORE code is written, module/API boundaries, data model, state, contracts, and tech decisions, for whatever field is active (frontend, backend, mobile…). Use for any non-trivial |
| code-reviewer model: sonnet | Reviews a diff, a file, or a whole area against MasterMind's principles and rigor gate: correctness, security, edge cases, types, architecture, stack defaults, the field's audit rules. Use after a non |
| refactorer | Restructures working code toward better design WITHOUT changing behavior: deeper modules, a cleaner data model, illegal states made unrepresentable, tangled dependencies unpicked. Use to pay down desi |
| tech-scout | Makes a technical ADOPTION decision, \"should we use library/tool/pattern X (vs Y, vs build it)?\": evaluated against MasterMind's reuse-with-judgment rubric and returned as a clear verdict with trade |
Similar rigs
rsmdt/the-startup
The Agentic Startup - A collection of Claude Code commands, skills, and agents.
Skill Collector 3.1k tok ·
devduck123/swe-os
Engineering judgment for people and their coding agents. One set of Markdown files: a learning site for humans, instructions for agents.
Pragmatist 1.2k tok ·
codeboehm/maxim
Training wheels for Mistral Vibe: discipline skills + a deterministic spec verifier. Guardrails, not a model upgrade.
Pragmatist 661 tok ·
lamngockhuong/aiteamkit
Multi-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard
Skill Collector 26.8k tok ·