Fadi88/one-man-startup
Build a software startup without writing code. Not vibe coding: a proven team workflow (requirements, design, test-first build, QA, release approval) run by AI agents.
field: unknown workflow: Frontend & designTesting & TDDCI/CD & deployPlanning & specsPR / code review
stack: Python
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
GUARDRAILS
3/5
Blocks destructive commands · No YOLO mode · Sandbox or ask-first rules · details
Quality 32/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit Fadi88/one-man-startup/.claude ./rig-one-man-startup # 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 Fadi88/one-man-startup/.claude/skills/bug-fix .claude/skills/bug-fix $ npx degit Fadi88/one-man-startup/.claude/skills/commit .claude/skills/commit $ npx degit Fadi88/one-man-startup/.claude/skills/context-budget .claude/skills/context-budget $ npx degit Fadi88/one-man-startup/.claude/skills/cost-audit .claude/skills/cost-audit $ npx degit Fadi88/one-man-startup/.claude/skills/decision-log .claude/skills/decision-log $ npx degit Fadi88/one-man-startup/.claude/skills/experiment .claude/skills/experiment $ npx degit Fadi88/one-man-startup/.claude/skills/founder-voice .claude/skills/founder-voice $ npx degit Fadi88/one-man-startup/.claude/skills/frontend-design .claude/skills/frontend-design $ npx degit Fadi88/one-man-startup/.claude/skills/gates .claude/skills/gates $ npx degit Fadi88/one-man-startup/.claude/skills/grilling .claude/skills/grilling $ npx degit Fadi88/one-man-startup/.claude/skills/handoff .claude/skills/handoff $ npx degit Fadi88/one-man-startup/.claude/skills/human-design .claude/skills/human-design $ npx degit Fadi88/one-man-startup/.claude/skills/human-steps .claude/skills/human-steps $ npx degit Fadi88/one-man-startup/.claude/skills/karpathy-guidelines .claude/skills/karpathy-guidelines $ npx degit Fadi88/one-man-startup/.claude/skills/known-reds .claude/skills/known-reds $ npx degit Fadi88/one-man-startup/.claude/skills/legal-review .claude/skills/legal-review $ npx degit Fadi88/one-man-startup/.claude/skills/new-feature .claude/skills/new-feature $ npx degit Fadi88/one-man-startup/.claude/skills/observability .claude/skills/observability $ npx degit Fadi88/one-man-startup/.claude/skills/ordered-steps .claude/skills/ordered-steps $ npx degit Fadi88/one-man-startup/.claude/skills/performance .claude/skills/performance $ npx degit Fadi88/one-man-startup/.claude/skills/readiness-gate .claude/skills/readiness-gate $ npx degit Fadi88/one-man-startup/.claude/skills/release .claude/skills/release $ npx degit Fadi88/one-man-startup/.claude/skills/requirement-first .claude/skills/requirement-first $ npx degit Fadi88/one-man-startup/.claude/skills/safe-data-write .claude/skills/safe-data-write $ npx degit Fadi88/one-man-startup/.claude/skills/setup .claude/skills/setup $ npx degit Fadi88/one-man-startup/.claude/skills/single-source .claude/skills/single-source $ npx degit Fadi88/one-man-startup/.claude/skills/spec-audit .claude/skills/spec-audit $ npx degit Fadi88/one-man-startup/.claude/skills/tailoring .claude/skills/tailoring $ npx degit Fadi88/one-man-startup/.claude/skills/twin-check .claude/skills/twin-check $ npx degit Fadi88/one-man-startup/.claude/skills/verified-claims .claude/skills/verified-claims $ npx degit Fadi88/one-man-startup/.claude/skills/verify-green .claude/skills/verify-green
$ curl -fsSL --create-dirs -o .claude/agents/agentic-workflow.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/agentic-workflow.md $ curl -fsSL --create-dirs -o .claude/agents/android-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/android-dev.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/backend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/dashboard.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/dashboard.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/desktop-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/desktop-dev.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/explainer-writer.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/explainer-writer.md $ curl -fsSL --create-dirs -o .claude/agents/feasibility.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/feasibility.md $ curl -fsSL --create-dirs -o .claude/agents/growth.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/growth.md $ curl -fsSL --create-dirs -o .claude/agents/ios-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/ios-dev.md $ curl -fsSL --create-dirs -o .claude/agents/legal.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/legal.md $ curl -fsSL --create-dirs -o .claude/agents/optimizer.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/platform-architect.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/platform-architect.md $ curl -fsSL --create-dirs -o .claude/agents/platform-designer.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/platform-designer.md $ curl -fsSL --create-dirs -o .claude/agents/product-designer.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/product-designer.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/rollback.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/rollback.md $ curl -fsSL --create-dirs -o .claude/agents/security.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/security.md $ curl -fsSL --create-dirs -o .claude/agents/setup.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/setup.md $ curl -fsSL --create-dirs -o .claude/agents/social-media.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/social-media.md $ curl -fsSL --create-dirs -o .claude/agents/web-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/.claude/agents/web-dev.md $ curl -fsSL --create-dirs -o .claude/agents/agentic-workflow.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/agentic-workflow.md $ curl -fsSL --create-dirs -o .claude/agents/android-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/android-dev.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/backend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/dashboard.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/dashboard.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/desktop-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/desktop-dev.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/explainer-writer.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/explainer-writer.md $ curl -fsSL --create-dirs -o .claude/agents/feasibility.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/feasibility.md $ curl -fsSL --create-dirs -o .claude/agents/growth.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/growth.md $ curl -fsSL --create-dirs -o .claude/agents/ios-dev.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/ios-dev.md $ curl -fsSL --create-dirs -o .claude/agents/legal.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/legal.md $ curl -fsSL --create-dirs -o .claude/agents/optimizer.md https://raw.githubusercontent.com/Fadi88/one-man-startup/main/agents/optimizer.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": [
"Edit(.claude/agents/**)",
"Edit(.claude/skills/**)",
"Edit(.cursor/rules/**)",
"Edit(CLAUDE.md)",
"Edit(GEMINI.md)"
],
"ask": [
"Bash(git push:*)",
"Bash(git merge:*)",
"Bash(git reset --hard:*)",
"Bash(rm -rf:*)",
"Bash(rm -fr *)",
"Bash(rm -r *)",
"Bash(git clean *)",
"Bash(git branch -D *)",
"Bash(gh pr merge *)",
"Bash(gh release *)",
"Bash(gh repo delete *)",
"Bash(gh repo edit *)",
"Bash(npm publish *)",
"Bash(docker push *)",
"Bash(vercel *)",
"Bash(netlify deploy *)",
"Bash(fly deploy *)",
"Bash(firebase deploy *)",
"Bash(supabase db push *)",
"PowerShell(Remove-Item *)",
"PowerShell(git push *)",
"PowerShell(git merge *)",
"PowerShell(git reset --hard *)",
"PowerShell(git clean *)",
"PowerShell(gh pr merge *)"
]
}
} Skills (31)
bug-fixcommitcontext-budgetcost-auditdecision-logexperimentfounder-voicefrontend-designgatesgrillinghandoffhuman-designhuman-stepskarpathy-guidelinesknown-redslegal-reviewnew-featureobservabilityordered-stepsperformancereadiness-gatereleaserequirement-firstsafe-data-writesetupsingle-sourcespec-audittailoringtwin-checkverified-claimsverify-green
Subagents (52)
| agentic-workflow model: opus | Designs the AI agent workflows inside the product - whether a task needs an agent, one AI call or no AI at all, then the steps, tools, model per step, prompts, guardrails, human approval points, evals |
| android-dev model: sonnet | Builds the Android app (phones and tablets) from product-designer's design and the API contract, test first - Android's own conventions, permissions, background limits, offline use, devices and screen |
| architect model: opus | Software architect for the whole system - keeps the system map, owns cross-cutting decisions (data model, auth, integrations, observability, cost guards), and turns each approved spec into a design, A |
| backend-dev model: sonnet | Builds the server, data layer, jobs and third-party integrations from tickets and the API contract, test first, with every data write provable and reversible. Use for any ticket behind the contract. |
| dashboard model: sonnet | Designs and builds the founder's own dashboard - the few numbers that show whether the product is working (users, activity, revenue, errors) and, for any product that calls AI or another paid service, |
| debugger model: opus | Finds the root cause of hard bugs - a fix that failed three times, a production incident after a rollback, a flaky or intermittent failure, a bug nobody can reproduce - by measuring rather than guessi |
| desktop-dev model: sonnet | Builds the desktop app (Windows, macOS, Linux, as project.toml says) from product-designer's design and the API contract, test first - each system's conventions, windows, menus and keyboard shortcuts, |
| devops model: sonnet | Owns environments, CI, releases, rollback, backups and monitoring. Use to set up hosting and CI after setup, and for every release - and it never deploys, migrates or deletes without the founder's go |
| explainer-writer model: sonnet | Writes scripts for the product's short explainer videos, each teaching one idea from the product's domain, in every language the product has, every claim sourced, worded as education and never advice, |
| feasibility model: sonnet | Checks whether a grilled idea or feature can actually be built and run with this project's stack, services, budget and data - technical risk, what the services really support, cost at ten times today' |
| growth model: sonnet | Positioning, landing page and store copy, pricing and packaging options, launch plan and the analytics needed to read them - every growth idea framed as an experiment with a falsifier. Use for bets, l |
| ios-dev model: sonnet | Builds the iPhone and iPad app from product-designer's design and the API contract, test first - Apple's own conventions, permissions, background limits, offline use, devices and screen sizes, and the |
| legal model: opus | Checks the product against the law of every region in project.toml - privacy and data protection, consent, terms, consumer rules, AI transparency, app store and payment rules - and drafts policies fla |
| optimizer model: sonnet | Audits the agent workflow itself for cost and waste - which model each agent runs on, how much context each step loads, duplicated or skipped steps, over-spawning, slow checks - and proposes ranked cu |
| orchestrator model: opus | Project manager for the agent team. Use first on any request that is more than a question - it picks the track (fix, feature, bet), the agents, the order and the gates, and it is the only agent that d |
| platform-architect model: opus | Architect for one platform's app (Android, iOS, desktop or web, named in the brief) - how that app is built inside (modules, on-device storage, platform services, background work, offline use, permiss |
| platform-designer model: sonnet | Designs everything users see and touch in one platform's app (Android, iOS, desktop or web, named in the brief) - flows, screens, every state, interface copy, accessibility - following that platform's |
| product-designer model: sonnet | Designs everything users see and touch, on every platform the product has (web, Android, iOS, desktop) - flows, screens, every state, interface copy, accessibility, one design system shared across pla |
| qa model: sonnet | Tests every change against its requirement rows, hunts regressions, writes the QA report and holds the release gate. Use after any build step and before any release. |
| researcher model: sonnet | Finds what similar products and projects already do about an idea or feature - who they are, what they offer, how they price it, what their users complain about - and writes a sourced brief that the g |
| reviewer model: opus | An independent second reader for both documents and code - reviews specs, designs, contracts and tickets for gaps and contradictions before they are handed on, and every developer diff for correctness |
| rollback model: sonnet | Puts the last version that worked back live when a release causes a major error - users cannot finish the main flow, data is being lost, corrupted or exposed, payments or charges are wrong, or spend i |
| security model: opus | Reviews designs and diffs for security and privacy risk - auth, access control, secrets, injection, dependencies, data exposure. It writes its report and never changes code. Use on any feature touchin |
| setup model: opus | Customises this template for a new company. Use once at the start, and again when the founder changes region, market, audience, customer size or stack - it interviews the founder and writes project.to |
| social-media model: sonnet | Plans and drafts the product's social media - which platforms the target customer actually uses, the voice, a content calendar, posts, build-in-public updates and community replies - each channel run |
| web-dev model: sonnet | Builds the web app and site from product-designer's design and the API contract, test first - every screen and state in ux.md, browsers, phone to wide screens, accessibility in code, performance on th |
| agentic-workflow | Designs the AI agent workflows inside the product - whether a task needs an agent, one AI call or no AI at all, then the steps, tools, model per step, prompts, guardrails, human approval points, evals |
| android-dev | Builds the Android app (phones and tablets) from product-designer's design and the API contract, test first - Android's own conventions, permissions, background limits, offline use, devices and screen |
| architect | Software architect for the whole system - keeps the system map, owns cross-cutting decisions (data model, auth, integrations, observability, cost guards), and turns each approved spec into a design, A |
| backend-dev | Builds the server, data layer, jobs and third-party integrations from tickets and the API contract, test first, with every data write provable and reversible. Use for any ticket behind the contract. |
| dashboard | Designs and builds the founder's own dashboard - the few numbers that show whether the product is working (users, activity, revenue, errors) and, for any product that calls AI or another paid service, |
| debugger | Finds the root cause of hard bugs - a fix that failed three times, a production incident after a rollback, a flaky or intermittent failure, a bug nobody can reproduce - by measuring rather than guessi |
| desktop-dev | Builds the desktop app (Windows, macOS, Linux, as project.toml says) from product-designer's design and the API contract, test first - each system's conventions, windows, menus and keyboard shortcuts, |
| devops | Owns environments, CI, releases, rollback, backups and monitoring. Use to set up hosting and CI after setup, and for every release - and it never deploys, migrates or deletes without the founder's go |
| explainer-writer | Writes scripts for the product's short explainer videos, each teaching one idea from the product's domain, in every language the product has, every claim sourced, worded as education and never advice, |
| feasibility | Checks whether a grilled idea or feature can actually be built and run with this project's stack, services, budget and data - technical risk, what the services really support, cost at ten times today' |
| growth | Positioning, landing page and store copy, pricing and packaging options, launch plan and the analytics needed to read them - every growth idea framed as an experiment with a falsifier. Use for bets, l |
| ios-dev | Builds the iPhone and iPad app from product-designer's design and the API contract, test first - Apple's own conventions, permissions, background limits, offline use, devices and screen sizes, and the |
| legal | Checks the product against the law of every region in project.toml - privacy and data protection, consent, terms, consumer rules, AI transparency, app store and payment rules - and drafts policies fla |
| optimizer | Audits the agent workflow itself for cost and waste - which model each agent runs on, how much context each step loads, duplicated or skipped steps, over-spawning, slow checks - and proposes ranked cu |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup|resume|compact | python tools/session_start.py |
Cursor rules (57)
agent-agentic-workflowagent-android-devagent-architectagent-backend-devagent-dashboardagent-debuggeragent-desktop-devagent-devopsagent-explainer-writeragent-feasibilityagent-growthagent-ios-devagent-legalagent-optimizeragent-orchestratoragent-platform-architectagent-platform-designeragent-product-designeragent-qaagent-researcheragent-revieweragent-rollbackagent-securityagent-setupagent-social-mediaagent-web-devskill-bug-fixskill-commitskill-context-budgetskill-cost-auditskill-decision-logskill-experimentskill-founder-voiceskill-frontend-designskill-gatesskill-grillingskill-handoffskill-human-designskill-human-stepsskill-karpathy-guidelinesskill-known-redsskill-legal-reviewskill-new-featureskill-observabilityskill-ordered-stepsskill-performanceskill-readiness-gateskill-releaseskill-requirement-firstskill-safe-data-writeskill-setupskill-single-sourceskill-spec-auditskill-tailoringskill-twin-checkskill-verified-claimsskill-verify-green
Permissions
deny (5)
Edit(.claude/agents/**)
Edit(.claude/skills/**)
Edit(.cursor/rules/**)
Edit(CLAUDE.md)
Edit(GEMINI.md)
ask (25)
Bash(git push:*)
Bash(git merge:*)
Bash(git reset --hard:*)
Bash(rm -rf:*)
Bash(rm -fr *)
Bash(rm -r *)
Bash(git clean *)
Bash(git branch -D *)
Bash(gh pr merge *)
Bash(gh release *)
Bash(gh repo delete *)
Bash(gh repo edit *)
Bash(npm publish *)
Bash(docker push *)
Bash(vercel *)
Bash(netlify deploy *)
Bash(fly deploy *)
Bash(firebase deploy *)
Bash(supabase db push *)
PowerShell(Remove-Item *)
PowerShell(git push *)
PowerShell(git merge *)
PowerShell(git reset --hard *)
PowerShell(git clean *)
PowerShell(gh pr merge *)
allow (0)
—
Similar rigs
IntuitivePhella/AI-PhellOS
Portable AI development workflow template and CLI for spec-driven, test-aware software delivery with Codex, Claude Code, and other coding agents.
Orchestrator 3.1k tok · · Q31
hun99999/agent-bootstrap
Process-first bootstrap for Codex and Claude Code with superpowers, role-based subagents, token-efficient workflows, and multilingual setup docs.
Orchestrator 2.6k tok · · Q0
AbuBakarPial/ai-software-firm
One person. Any project. Production-ready output.
Orchestrator 5.2k tok · · Q48
AgentWorkforce/relay
Infrastructure for coding agents
Orchestrator 8.0k tok · · Q18