avelikiy/great_cto
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and thr
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add great_cto -- npx -y great-cto@3.58.2 mcp $ npx degit avelikiy/great_cto/agents ./rig-great_cto/agents $ npx degit avelikiy/great_cto/commands ./rig-great_cto/commands $ npx degit avelikiy/great_cto/skills ./rig-great_cto/skills $ npx degit avelikiy/great_cto/hooks ./rig-great_cto/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.
$ claude mcp add great_cto -- npx -y great-cto@3.58.2 mcp $ npx degit avelikiy/great_cto/skills/aesthetic-instrument .claude/skills/aesthetic-instrument $ npx degit avelikiy/great_cto/skills/anti-patterns .claude/skills/anti-patterns $ npx degit avelikiy/great_cto/skills/anydesign .claude/skills/anydesign $ npx degit avelikiy/great_cto/skills/archetype-review-base .claude/skills/archetype-review-base $ npx degit avelikiy/great_cto/skills/brainstorming .claude/skills/brainstorming $ npx degit avelikiy/great_cto/skills/codex-host .claude/skills/codex-host $ npx degit avelikiy/great_cto/skills/committed-aesthetic .claude/skills/committed-aesthetic $ npx degit avelikiy/great_cto/skills/cost-model .claude/skills/cost-model $ npx degit avelikiy/great_cto/skills/crystallize .claude/skills/crystallize $ npx degit avelikiy/great_cto/skills/decision-eval .claude/skills/decision-eval $ npx degit avelikiy/great_cto/skills/deploy-landed .claude/skills/deploy-landed $ npx degit avelikiy/great_cto/skills/discovery .claude/skills/discovery $ npx degit avelikiy/great_cto/skills/done-blocked .claude/skills/done-blocked $ npx degit avelikiy/great_cto/skills/great_cto .claude/skills/great_cto $ npx degit avelikiy/great_cto/skills/lifecycle-messaging .claude/skills/lifecycle-messaging $ npx degit avelikiy/great_cto/skills/migration-ready-schema .claude/skills/migration-ready-schema $ npx degit avelikiy/great_cto/skills/observability-baseline .claude/skills/observability-baseline $ npx degit avelikiy/great_cto/skills/opportunity-solution-tree .claude/skills/opportunity-solution-tree $ npx degit avelikiy/great_cto/skills/outcome-roadmap .claude/skills/outcome-roadmap $ npx degit avelikiy/great_cto/skills/pm-planning .claude/skills/pm-planning $ npx degit avelikiy/great_cto/skills/pre-mortem .claude/skills/pre-mortem $ npx degit avelikiy/great_cto/skills/product-economics .claude/skills/product-economics $ npx degit avelikiy/great_cto/skills/prose-style .claude/skills/prose-style $ npx degit avelikiy/great_cto/skills/quant-validation .claude/skills/quant-validation $ npx degit avelikiy/great_cto/skills/secrets-rotation .claude/skills/secrets-rotation $ npx degit avelikiy/great_cto/skills/signing-preflight .claude/skills/signing-preflight $ npx degit avelikiy/great_cto/skills/skeptical-triage .claude/skills/skeptical-triage $ npx degit avelikiy/great_cto/skills/stack-baseline .claude/skills/stack-baseline $ npx degit avelikiy/great_cto/skills/test-strategy .claude/skills/test-strategy $ npx degit avelikiy/great_cto/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max $ npx degit avelikiy/great_cto/skills/vertical-onboarding .claude/skills/vertical-onboarding $ npx degit avelikiy/great_cto/skills/verticals .claude/skills/verticals $ npx degit avelikiy/great_cto/skills/well-architected .claude/skills/well-architected
$ curl -fsSL --create-dirs -o .claude/agents/argument-quality.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/argument-quality.md $ curl -fsSL --create-dirs -o .claude/agents/artifact-summary-contract.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/artifact-summary-contract.md $ curl -fsSL --create-dirs -o .claude/agents/compress-prompt.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/compress-prompt.md $ curl -fsSL --create-dirs -o .claude/agents/contract-agent-altitude.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/contract-agent-altitude.md $ curl -fsSL --create-dirs -o .claude/agents/deploy-failure-modes.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/deploy-failure-modes.md $ curl -fsSL --create-dirs -o .claude/agents/evidence-discipline.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/evidence-discipline.md $ curl -fsSL --create-dirs -o .claude/agents/handoff-format.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/handoff-format.md $ curl -fsSL --create-dirs -o .claude/agents/phase-task.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/phase-task.md $ curl -fsSL --create-dirs -o .claude/agents/privacy-guardrails.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/privacy-guardrails.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer-verdict.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/reviewer-verdict.md $ curl -fsSL --create-dirs -o .claude/agents/sandbox-cwd-policy.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/sandbox-cwd-policy.md $ curl -fsSL --create-dirs -o .claude/agents/skill-catalog-browse.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/skill-catalog-browse.md $ curl -fsSL --create-dirs -o .claude/agents/task-brief.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/task-brief.md $ curl -fsSL --create-dirs -o .claude/agents/untrusted-content.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/untrusted-content.md $ curl -fsSL --create-dirs -o .claude/agents/verdict-format.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/verdict-format.md $ curl -fsSL --create-dirs -o .claude/agents/verify-by-running.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/verify-by-running.md $ curl -fsSL --create-dirs -o .claude/agents/work-fast.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/_shared/work-fast.md $ curl -fsSL --create-dirs -o .claude/agents/accounting-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/accounting-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/adtech-privacy-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/adtech-privacy-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/ai-eval-engineer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/ai-eval-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/ai-prompt-architect.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/ai-prompt-architect.md $ curl -fsSL --create-dirs -o .claude/agents/ai-security-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/ai-security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/api-platform-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/api-platform-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/app-scaffolder.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/app-scaffolder.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/auth-engineer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/auth-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/ci-resolver.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/ci-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/cli-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/cli-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/cmmc-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/cmmc-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/cms-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/cms-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/connector-builder.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/connector-builder.md $ curl -fsSL --create-dirs -o .claude/agents/continuous-learner.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/continuous-learner.md $ curl -fsSL --create-dirs -o .claude/agents/coordinator.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/coordinator.md $ curl -fsSL --create-dirs -o .claude/agents/data-platform-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/data-platform-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/db-migration-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/db-migration-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/decision-scorer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/decision-scorer.md $ curl -fsSL --create-dirs -o .claude/agents/design-advisor.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/design-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/devtools-reviewer.md https://raw.githubusercontent.com/avelikiy/great_cto/main/agents/devtools-reviewer.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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| great-cto · "great_cto" | npm | 2.5k |
Skills (33)
aesthetic-instrumentanti-patternsanydesignarchetype-review-basebrainstormingcodex-hostcommitted-aestheticcost-modelcrystallizedecision-evaldeploy-landeddiscoverydone-blockedgreat_ctolifecycle-messagingmigration-ready-schemaobservability-baselineopportunity-solution-treeoutcome-roadmappm-planningpre-mortemproduct-economicsprose-stylequant-validationsecrets-rotationsigning-preflightskeptical-triagestack-baselinetest-strategyui-ux-pro-maxvertical-onboardingverticalswell-architected
Subagents (80)
| argument-quality | — |
| artifact-summary-contract | — |
| compress-prompt | — |
| contract-agent-altitude | — |
| deploy-failure-modes | — |
| evidence-discipline | — |
| handoff-format | — |
| phase-task | — |
| privacy-guardrails | — |
| reviewer-verdict | — |
| sandbox-cwd-policy | — |
| skill-catalog-browse | — |
| task-brief | — |
| untrusted-content | — |
| verdict-format | — |
| verify-by-running | — |
| work-fast | — |
| accounting-reviewer model: sonnet | Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/Hi |
| adtech-privacy-reviewer model: sonnet | US adtech / web-tracking privacy-litigation pre-implementation reviewer. Outputs threat model TM-adtech-{slug}.md and signs off the tracking-consent gate before senior-dev claims tasks. |
| ai-eval-engineer model: haiku | Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-*.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overr |
| ai-prompt-architect model: sonnet | Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/adr/ADR-{NN}-PROMPT-{name}.md files with sha256-pinned prompt text, jailbreak resistance test cases, and |
| ai-security-reviewer model: sonnet | AI-specific pre-implementation threat modelling for ai-system / agent-product archetypes. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks. |
| api-platform-reviewer model: sonnet | API platform / dev-API pre-implementation reviewer. Outputs threat model TM-{slug}.md. |
| app-scaffolder model: sonnet | Project-scaffolding builder that stands up a working base application from the pinned stack-baseline so senior-dev implements FEATURES, not boilerplate. Creates the Next.js + TypeScript + Tailwind/sha |
| architect model: claude-opus-5 | Use when starting any new feature. Creates architecture docs, ADRs, cost estimates, Well-Architected review. Always first in the pipeline. |
| auth-engineer model: sonnet | Authentication and access-control specialist for SMB Product-Builder products. Owns the auth contract — provider choice (Auth.js default / Clerk fast-path), session model, RBAC, multi-tenant row-level |
| ci-resolver model: sonnet | Use when CI or a build is red. Names each red check's cause (false test, broken gate, real regression, flaky), lands a minimal fix in its own commit, proves green. Never skips a check. |
| cli-reviewer model: sonnet | CLI tool pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off CLI surface decisions before senior-dev claims tasks. |
| cmmc-reviewer model: sonnet | US defense-contractor (GovCon) pre-implementation reviewer. Outputs threat model TM-cmmc-{slug}.md and signs off the CMMC-assessment gate before senior-dev claims tasks. |
| cms-reviewer model: sonnet | CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks. |
| code-reviewer model: haiku | Use after senior-dev completes a task and before gate:ship. One stable, human-grade reviewer (correctness, security, performance, readability) — replaces ad-hoc inline review forks. Reads the diff, fi |
| connector-builder model: sonnet | Source-connector specialist for dashboard / analytics Product-Builder products. The read-side twin of integrations-engineer — owns the connector contract for pulling data IN from sources (Stripe, Goog |
| continuous-learner model: claude-haiku-4-5 | Use at session end (auto-triggered by SessionEnd hook) or via /crystallize learn. Extracts repeatable patterns, decisions, and cost outliers from the session and writes structured entries to .great_ct |
| coordinator model: sonnet | Multi-agent coordinator. Use when a CTO request spans 3+ independent work streams, requires parallel research before implementation, or the task graph is complex enough that sequencing matters. Orches |
| data-platform-reviewer model: sonnet | Data-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off retention + lineage decisions before senior-dev claims tasks. |
| db-migration-reviewer model: sonnet | Database migration safety specialist. Activates when migrations/ files are detected in a PR or feature branch. Checks lock duration, rollback strategy, zero-downtime patterns, PII column handling, and |
| decision-scorer model: claude-sonnet-5 | Scores 2+ architectural alternatives against PROJECT.md criteria. Called by architect after proposing variants. Outputs a weighted scoring table and recommended choice. |
| design-advisor model: claude-opus-5 | Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory |
| devops model: haiku | Use after gate:ship is approved. Deploys using the method matching the project type. |
| devtools-reviewer model: sonnet | Devtools (CLI plugin / IDE extension / dev SDK) pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off supply-chain decisions before senior-dev claims tasks. |
Slash commands (21)
/agent/audit/board/crystallize/digest/doctor/exception/help/inbox/ownership/poc/recall/release/resume/review/rfc/save/sec/spec/start/trace
Similar rigs
roadhero/claude-code-setup
My actual Claude Code setup: a stack-agnostic engineering spine, auto-activating rule packs, 50 scoped subagents across web/Android/iOS/compute, safety hooks, and a repo scaffolder. From the book "42: The AI Builder's Stack."
Orchestrator 7.3k tok ·
addit-digital/addit-harness
Config harness for Claude Code — subagents, language conventions, an engineering-loop process, ADRs, and a one-line auto-detecting install
Orchestrator 3.6k tok ·
PenguinAlleyApps/paco-framework
—
Orchestrator 2.6k tok ·
minhtuluc/Claude-Code-Configs
—
Orchestrator 2.2k tok ·