~ / rigs / maister-dev / maister

maister-dev/maister

Self-hosted execution and governance for reproducible AI-powered software delivery over private code.

↗ GitHub ★ 10 MIT updated 4d ago project Claude CodeCodex
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~74.7k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 20/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ claude mcp add github -e GITHUB_<redacted> -- npx -y @modelcontextprotocol/server-github
$ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem .
$ claude mcp add postgres -e DATABASE_URL=YOUR_DATABASE_URL -- npx -y @modelcontextprotocol/server-postgres
$ claude mcp add chromeDevtools -- npx -y chrome-devtools-mcp@latest --no-usage-statistics
$ claude mcp add playwright -- npx -y @playwright/mcp@latest
$ npx degit maister-dev/maister/.claude ./rig-maister  # 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.

$ claude mcp add github -e GITHUB_<redacted> -- npx -y @modelcontextprotocol/server-github
$ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem .
$ claude mcp add postgres -e DATABASE_URL=YOUR_DATABASE_URL -- npx -y @modelcontextprotocol/server-postgres
$ claude mcp add chromeDevtools -- npx -y chrome-devtools-mcp@latest --no-usage-statistics
$ claude mcp add playwright -- npx -y @playwright/mcp@latest
$ npx degit maister-dev/maister/.agents/skills/aif-architecture .claude/skills/aif-architecture
$ npx degit maister-dev/maister/.agents/skills/aif-best-practices .claude/skills/aif-best-practices
$ npx degit maister-dev/maister/.agents/skills/aif-build-automation .claude/skills/aif-build-automation
$ npx degit maister-dev/maister/.agents/skills/aif-ci .claude/skills/aif-ci
$ npx degit maister-dev/maister/.agents/skills/aif-commit .claude/skills/aif-commit
$ npx degit maister-dev/maister/.agents/skills/aif-distillation .claude/skills/aif-distillation
$ npx degit maister-dev/maister/.agents/skills/aif-dockerize .claude/skills/aif-dockerize
$ npx degit maister-dev/maister/.agents/skills/aif-docs .claude/skills/aif-docs
$ npx degit maister-dev/maister/.agents/skills/aif-evolve .claude/skills/aif-evolve
$ npx degit maister-dev/maister/.agents/skills/aif-explore .claude/skills/aif-explore
$ npx degit maister-dev/maister/.agents/skills/aif-fix .claude/skills/aif-fix
$ npx degit maister-dev/maister/.agents/skills/aif-grounded .claude/skills/aif-grounded
$ npx degit maister-dev/maister/.agents/skills/aif-implement .claude/skills/aif-implement
$ npx degit maister-dev/maister/.agents/skills/aif-improve .claude/skills/aif-improve
$ npx degit maister-dev/maister/.agents/skills/aif-loop .claude/skills/aif-loop
$ npx degit maister-dev/maister/.agents/skills/aif-plan .claude/skills/aif-plan
$ npx degit maister-dev/maister/.agents/skills/aif-qa .claude/skills/aif-qa
$ npx degit maister-dev/maister/.agents/skills/aif-reference .claude/skills/aif-reference
$ npx degit maister-dev/maister/.agents/skills/aif-review .claude/skills/aif-review
$ npx degit maister-dev/maister/.agents/skills/aif-roadmap .claude/skills/aif-roadmap
$ npx degit maister-dev/maister/.agents/skills/aif-rules-check .claude/skills/aif-rules-check
$ npx degit maister-dev/maister/.agents/skills/aif-rules .claude/skills/aif-rules
$ npx degit maister-dev/maister/.agents/skills/aif-security-checklist .claude/skills/aif-security-checklist
$ npx degit maister-dev/maister/.agents/skills/aif-skill-generator .claude/skills/aif-skill-generator
$ npx degit maister-dev/maister/.agents/skills/aif-verify .claude/skills/aif-verify
$ npx degit maister-dev/maister/.agents/skills/aif .claude/skills/aif
$ npx degit maister-dev/maister/.agents/skills/generate-claudemd .claude/skills/generate-claudemd
$ curl -fsSL --create-dirs -o .claude/agents/best-practices-sidecar.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/best-practices-sidecar.md
$ curl -fsSL --create-dirs -o .claude/agents/commit-preparer.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/commit-preparer.md
$ curl -fsSL --create-dirs -o .claude/agents/docs-auditor.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/docs-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/implement-coordinator.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/implement-coordinator.md
$ curl -fsSL --create-dirs -o .claude/agents/implement-worker.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/implement-worker.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-critic.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-critic.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-evaluator.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-evaluator.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-invariant-prep.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-invariant-prep.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-orchestrator.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-orchestrator.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-perf-prep.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-perf-prep.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-planner.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-planner.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-producer.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-producer.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-refiner.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-refiner.md
$ curl -fsSL --create-dirs -o .claude/agents/loop-test-prep.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/loop-test-prep.md
$ curl -fsSL --create-dirs -o .claude/agents/plan-coordinator.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/plan-coordinator.md
$ curl -fsSL --create-dirs -o .claude/agents/plan-polisher.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/plan-polisher.md
$ curl -fsSL --create-dirs -o .claude/agents/review-sidecar.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/review-sidecar.md
$ curl -fsSL --create-dirs -o .claude/agents/rules-sidecar.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/rules-sidecar.md
$ curl -fsSL --create-dirs -o .claude/agents/security-sidecar.md https://raw.githubusercontent.com/maister-dev/maister/master/.claude/agents/security-sidecar.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

MCP servers (5)

serversourceest. tokens
GitHub MCP · "github"
env: GITHUB_TOKEN
npm 18.0k
Filesystem npm 4.2k
Postgres
env: DATABASE_URL
npm 600
Chrome DevTools MCP · "chromeDevtools" npm 9.0k
Playwright MCP · "playwright" npm 7.5k

Skills (27)

Subagents (19)

best-practices-sidecar
model: inherit
Read-only background best-practices sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise maintainability review is needed.
commit-preparer
model: sonnet
Read-only background commit preparation sidecar for the current implementation scope. Use from implement-coordinator when deciding whether a final /aif-commit step can be streamlined.
docs-auditor
model: sonnet
Read-only background documentation drift sidecar for the current implementation scope. Use from implement-coordinator after code changes when deciding whether /aif-docs should run automatically.
implement-coordinator
model: inherit
Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via `claude --agent
implement-worker
model: inherit
Execute a single plan task in an isolated worktree — implement, verify, and return. Spawned by implement-coordinator for parallel task execution. Cannot spawn child agents — runs quality checks locall
loop-critic
model: sonnet
Convert failed evaluation rules into precise, minimal fix instructions for the refiner. Use proactively within /aif-loop when evaluation fails.
loop-evaluator
model: inherit
Evaluate artifact strictly against active loop criteria and return structured pass/fail output. Use proactively within /aif-loop when an objective verdict is needed.
loop-invariant-prep
model: haiku
Prepare invariant and consistency checks for the current loop iteration. Use proactively within /aif-loop in parallel with producer.
loop-orchestrator
model: sonnet
Route reflex-loop execution to the next role based on run state, stop guards, and last evaluation. Use proactively within /aif-loop when deciding the next step.
loop-perf-prep
model: haiku
Prepare lightweight performance checks (RPS/latency budget assertions) for the current loop iteration. Use proactively within /aif-loop in parallel with producer.
loop-planner
model: haiku
Build a short, execution-focused iteration plan (3-5 steps) aligned to active rules. Use proactively within /aif-loop when the next iteration plan is needed.
loop-producer
model: inherit
Produce the single markdown artifact for the current loop iteration from task and plan. Use proactively within /aif-loop when artifact generation is needed.
loop-refiner
model: inherit
Apply critique issues to produce a minimally changed improved artifact. Use proactively within /aif-loop when refinement is needed after failed evaluation.
loop-test-prep
model: haiku
Prepare lightweight test checks for the current loop iteration without blocking execution. Use proactively within /aif-loop in parallel with producer.
plan-coordinator
model: inherit
Iteratively polish a plan by launching plan-polisher in a loop until critique passes or max iterations reached. Use via `claude --agent plan-coordinator`.
plan-polisher
model: inherit
Create or refresh an /aif-plan plan, critique it, and run one refinement round at most. The caller launches another plan-polisher for further iterations if needed.
review-sidecar
model: inherit
Read-only background code review sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise bug-risk review is needed.
rules-sidecar
model: inherit
Read-only background rules compliance sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise rules check is needed.
security-sidecar
model: inherit
Read-only background security audit sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise security check is needed.

Similar rigs

copied ✓