mariomile/builder-os
BuilderOS: the operating system for product builders. Eight gated phases from an idea to a product in production, with source-tagged evidence and zero prerequisites.
field: unknown workflow: Planning & specsFrontend & designTesting & TDDCI/CD & deployPR / code review
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 mariomile/builder-os/agents ./rig-builder-os/agents $ npx degit mariomile/builder-os/commands ./rig-builder-os/commands $ npx degit mariomile/builder-os/skills ./rig-builder-os/skills $ npx degit mariomile/builder-os/hooks ./rig-builder-os/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 mariomile/builder-os/skills/agent-design .claude/skills/agent-design $ npx degit mariomile/builder-os/skills/agents-md .claude/skills/agents-md $ npx degit mariomile/builder-os/skills/bug-diagnosis .claude/skills/bug-diagnosis $ npx degit mariomile/builder-os/skills/builder-os .claude/skills/builder-os $ npx degit mariomile/builder-os/skills/business-case .claude/skills/business-case $ npx degit mariomile/builder-os/skills/delivery-discipline .claude/skills/delivery-discipline $ npx degit mariomile/builder-os/skills/domain-model .claude/skills/domain-model $ npx degit mariomile/builder-os/skills/evidence-ledger .claude/skills/evidence-ledger $ npx degit mariomile/builder-os/skills/gate-checks .claude/skills/gate-checks $ npx degit mariomile/builder-os/skills/go-to-market .claude/skills/go-to-market $ npx degit mariomile/builder-os/skills/ideation-methods .claude/skills/ideation-methods $ npx degit mariomile/builder-os/skills/opportunity-mapping .claude/skills/opportunity-mapping $ npx degit mariomile/builder-os/skills/outcome-review .claude/skills/outcome-review $ npx degit mariomile/builder-os/skills/pressure-testing .claude/skills/pressure-testing $ npx degit mariomile/builder-os/skills/problem-framing .claude/skills/problem-framing $ npx degit mariomile/builder-os/skills/product-analysis .claude/skills/product-analysis $ npx degit mariomile/builder-os/skills/release-ops .claude/skills/release-ops $ npx degit mariomile/builder-os/skills/research-methods .claude/skills/research-methods $ npx degit mariomile/builder-os/skills/spec-writing .claude/skills/spec-writing $ npx degit mariomile/builder-os/skills/system-design .claude/skills/system-design $ npx degit mariomile/builder-os/skills/tracking-standards .claude/skills/tracking-standards $ npx degit mariomile/builder-os/skills/using-builder-os .claude/skills/using-builder-os $ npx degit mariomile/builder-os/skills/ux-architecture .claude/skills/ux-architecture $ npx degit mariomile/builder-os/skills/wayfinding .claude/skills/wayfinding
$ curl -fsSL --create-dirs -o .claude/agents/build-reviewer.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/build-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/delivery-planner.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/delivery-planner.md $ curl -fsSL --create-dirs -o .claude/agents/discovery-synthesizer.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/discovery-synthesizer.md $ curl -fsSL --create-dirs -o .claude/agents/experiment-designer.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/experiment-designer.md $ curl -fsSL --create-dirs -o .claude/agents/opportunity-mapper.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/opportunity-mapper.md $ curl -fsSL --create-dirs -o .claude/agents/problem-framer.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/problem-framer.md $ curl -fsSL --create-dirs -o .claude/agents/product-diagnostician.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/product-diagnostician.md $ curl -fsSL --create-dirs -o .claude/agents/product-writer.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/product-writer.md $ curl -fsSL --create-dirs -o .claude/agents/release-manager.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/release-manager.md $ curl -fsSL --create-dirs -o .claude/agents/research-planner.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/research-planner.md $ curl -fsSL --create-dirs -o .claude/agents/solution-architect.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/solution-architect.md $ curl -fsSL --create-dirs -o .claude/agents/spec-writer.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/spec-writer.md $ curl -fsSL --create-dirs -o .claude/agents/tracking-architect.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/tracking-architect.md $ curl -fsSL --create-dirs -o .claude/agents/ux-architect.md https://raw.githubusercontent.com/mariomile/builder-os/main/agents/ux-architect.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 *)"
]
}
} Skills (24)
agent-designagents-mdbug-diagnosisbuilder-osbusiness-casedelivery-disciplinedomain-modelevidence-ledgergate-checksgo-to-marketideation-methodsopportunity-mappingoutcome-reviewpressure-testingproblem-framingproduct-analysisrelease-opsresearch-methodsspec-writingsystem-designtracking-standardsusing-builder-osux-architecturewayfinding
Subagents (14)
| build-reviewer model: inherit | Reviews built work against code standards and the spec, checks scope creep and that instrumentation fires. Closes phase 5. |
| delivery-planner model: inherit | Writes the phase 5 build plan before any code: tracer-bullet slices, blockers, risks, test baseline, a test per criterion. |
| discovery-synthesizer model: inherit | Synthesizes raw research (transcripts, feedback, tickets) into coded themes with counts and scored opportunities. |
| experiment-designer model: inherit | Designs experiments with a pre-registered decision rule and sample size, and reads results against that rule. |
| opportunity-mapper model: inherit | Phase 2: turns validated discovery into an opportunity tree, picks one with written rejections, sets a metric with a baseline. |
| problem-framer model: inherit | Phase 0: turns an idea or complaint into a stated problem, a named ICP, a dated why-now and a falsifiable assumption. |
| product-diagnostician model: inherit | Answers product-analysis questions in an isolated context: health, activation, retention, revenue, PMF, OKRs, competitors. |
| product-writer model: inherit | Writes PRDs, release notes, stakeholder updates and executive summaries, carrying evidence tags through. |
| release-manager model: inherit | Phase 6: rollout with a tested rollback, production instrumentation verified, baseline before exposure, review scheduled. |
| research-planner model: inherit | Phase 1: plans and runs the research that tests the riskiest assumption and returns VALIDATED, KILLED or RESHAPED. |
| solution-architect model: inherit | Phase 3: generates distinct solution options, selects the bet, writes kill criteria, designs the cheapest test. |
| spec-writer model: inherit | Phase 4: turns the selected bet into a buildable spec with bounded scope, testable criteria, states and a tracking plan. |
| tracking-architect model: inherit | Designs event taxonomies, funnels and dashboard specs for a feature, and audits existing instrumentation. |
| ux-architect model: inherit | Phase 4 structure: information architecture, flows with every entry and exit, six states per step, components, accessibility. |
Slash commands (16)
/bos-adr/bos-ask/bos-build/bos-define/bos-discover/bos-discovery-sprint/bos-frame/bos-gate/bos-ideate/bos-init/bos-learn/bos-review/bos-shape/bos-ship/bos-status/bos
Similar rigs
aleksandradovgopolova-boop/ai-ops-kit
AI Ops Kit помогает командам вести задачи с ИИ-агентами: от плана и реализации до проверки результата.
Orchestrator 5.6k tok · · Q0
s977043/PlanGate
Gate-based workflow for AI coding agents
Orchestrator 4.8k tok · · Q15
guiller91/harness-SF-v3
Harness para desarrollar en Salesforce con agentes de IA: las reglas se imponen por código (hooks, gates, evidencia).
Fort Knox 3.3k tok · · Q18
ftvision/system-design-skill
System design interview practice skill for Claude Code & Codex (mock, learn, postmortem, generate)
Minimalist 86 tok · · Q0