{"id":48818655,"url":"https://github.com/avelikiy/great_cto","last_synced_at":"2026-05-29T16:00:28.049Z","repository":{"id":349291559,"uuid":"1201775350","full_name":"avelikiy/great_cto","owner":"avelikiy","description":"The engineering process for solo founders and teams up to 50 engineers - without the overhead.","archived":false,"fork":false,"pushed_at":"2026-05-23T15:00:18.000Z","size":11630,"stargazers_count":29,"open_issues_count":4,"forks_count":6,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-05-23T17:03:09.277Z","etag":null,"topics":["agentic-coding","claude-code-plugin","claude-code-skills","claude-code-subagents","code-review","cto","multi-agent","sdlc"],"latest_commit_sha":null,"homepage":"https://greatcto.systems","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/avelikiy.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE.md","maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-05T06:17:43.000Z","updated_at":"2026-05-23T15:00:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"fad87af4-2454-484d-ae63-8f5544836df8","html_url":"https://github.com/avelikiy/great_cto","commit_stats":null,"previous_names":["avelikiy/great_cto"],"tags_count":121,"template":false,"template_full_name":null,"purl":"pkg:github/avelikiy/great_cto","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avelikiy%2Fgreat_cto","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avelikiy%2Fgreat_cto/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avelikiy%2Fgreat_cto/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avelikiy%2Fgreat_cto/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/avelikiy","download_url":"https://codeload.github.com/avelikiy/great_cto/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avelikiy%2Fgreat_cto/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33659872,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-29T02:00:06.066Z","response_time":107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-coding","claude-code-plugin","claude-code-skills","claude-code-subagents","code-review","cto","multi-agent","sdlc"],"created_at":"2026-04-14T13:06:00.309Z","updated_at":"2026-05-29T16:00:28.038Z","avatar_url":"https://github.com/avelikiy.png","language":"JavaScript","funding_links":[],"categories":["Skills","技能列表","Harnesses \u0026 orchestration","Multi-Agent Systems","Plugins","Agent Infrastructure","🗂️ Collections"],"sub_categories":["Development \u0026 Code Tools","开发与代码工具","Orchestrators \u0026 autonomous loops","Parallel Processing","All Plugins","Multi-Agent Orchestration"],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"docs/screenshots/logo.svg\" alt=\"great_cto\" width=\"280\" /\u003e\n\n**Your AI engineering team for ~$34/month.**\n\n[![npm](https://img.shields.io/npm/v/great-cto?label=npx%20great-cto\u0026color=cb3837)](https://www.npmjs.com/package/great-cto)\n[![npm downloads](https://img.shields.io/npm/dm/great-cto?color=cb3837\u0026label=downloads)](https://www.npmjs.com/package/great-cto)\n[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)\n[![Claude Code Plugin](https://img.shields.io/badge/Claude_Code-Plugin-blueviolet)](https://claude.com/plugins)\n[![Savings](https://img.shields.io/badge/one_real_run-$2.39_vs_$5460_human-darkgreen)](https://greatcto.systems/proof)\n\n\u003cimg src=\"docs/screenshots/pipeline.svg\" alt=\"great_cto pipeline: Flow Compiler → gate:plan → 57 agents → gate:ship → Deployed\" width=\"900\" /\u003e\n\n```bash\nnpx great-cto init\n```\n\n[Website](https://greatcto.systems) · [One real run →](https://greatcto.systems/proof) · [Live demo](https://greatcto.systems/r/CsqYVXs1Vibac5yp) · [Discussions](https://github.com/avelikiy/great_cto/discussions) · [Changelog](CHANGELOG.md)\n\n[Русский](docs/ru/README.md) · [简体中文](docs/zh-CN/README.md) · [繁體中文](docs/zh-TW/README.md) · [日本語](docs/ja/README.md) · [한국어](docs/ko/README.md) · [Español](docs/es/README.md) · [Português](docs/pt-BR/README.md) · [Deutsch](docs/de/README.md) · [Français](docs/fr/README.md)\n\n\u003c/div\u003e\n\n---\n\n## The problem\n\nYou're a solo CTO. You write the code, review the code, deploy the code. Nobody's catching:\n\n- The GDPR clause you missed in the payment flow\n- The N+1 query that shows up in prod at 10× scale\n- The auth middleware hole you'll read about in a bug report\n\nHiring a senior engineer to review: **$15,000/month.** Doing it yourself: **risk.**\n\n## What you get\n\n57 specialist agents — architect, 12-angle reviewer, QA, security officer, devops — wired into a gated pipeline tuned to your stack and jurisdiction.\n\n**You make two decisions per feature.** Everything else runs automatically.\n\n## By the numbers\n\n| | |\n|---|---|\n| LLM cost (one real feature, traced) | **$2.39** |\n| Human-equivalent for the same work | **~$5,460** |\n| Defects caught that QA had missed | **2** |\n| Monthly cost (20 pipeline runs) | **~$34** |\n| Specialist agents | **57** |\n| Archetypes auto-detected | **25** |\n| Jurisdictions | **12** (GDPR · HIPAA · PCI-DSS · SOX · and more) |\n\n→ [Full trace with all artefacts](https://greatcto.systems/proof)\n\n## How it works\n\n**`npx great-cto init`** — scans your stack and README, detects jurisdiction (GDPR? HIPAA? PCI?), writes `.great_cto/FLOW.md` with the exact agents, gates, and compliance frameworks for your project.\n\n**`/start \"describe the feature\"`** — critics review the architecture and spec before any code is written. You review the plan at `gate:plan`.\n\n**Agents run automatically** — senior-dev implements with TDD, 12-angle review, QA, security, devops. You approve ship at `gate:ship`.\n\n## Three projects — three different pipelines\n\nSame command. Output depends on what you're building and where it runs:\n\n| | **Fintech startup · EU** | **Healthcare portal · US** | **CLI tool** |\n|---|---|---|---|\n| Specialist agents | `pci-reviewer` · `gdpr-reviewer` · `regulated-reviewer` | `fda-reviewer` · `healthcare-reviewer` · `security-officer` | `cli-reviewer` |\n| Human gates | `gate:gdpr-dpia` · `gate:plan` · `gate:ship` | `gate:clinical-validation` · `gate:plan` · `gate:ship` | `gate:plan` |\n| Compliance | GDPR · PCI-DSS · SOX | HIPAA · HITECH | — |\n| Cost / cycle | ~$8–18 | ~$8–18 | ~$0.5–3 |\n\n→ Try the interactive picker: [greatcto.systems/#flow-picker](https://greatcto.systems/#flow-picker)\n\n## The dashboard you'll actually check\n\n`great-cto board` opens at `http://localhost:3141` — Kanban with realtime SSE, per-agent cost tile, pipeline status, 30-day LLM spend vs human-equivalent baseline.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/screenshots/board.png\" alt=\"Kanban board with realtime SSE updates\" width=\"900\" /\u003e\n\u003c/p\u003e\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\u003ca href=\"docs/screenshots/metrics.png\"\u003e\u003cimg src=\"docs/screenshots/metrics.png\" alt=\"Metrics — cost, velocity, savings_x\" width=\"100%\" /\u003e\u003c/a\u003e\u003cbr/\u003e\u003csub\u003e\u003cb\u003eMetrics\u003c/b\u003e — LLM cost, human-equivalent baseline, savings_x ratio\u003c/sub\u003e\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\u003ca href=\"docs/screenshots/inbox.png\"\u003e\u003cimg src=\"docs/screenshots/inbox.png\" alt=\"Inbox — gates, P0, blocked, stale\" width=\"100%\" /\u003e\u003c/a\u003e\u003cbr/\u003e\u003csub\u003e\u003cb\u003eInbox\u003c/b\u003e — pending gates, P0 incidents, blocked tasks, stale in-progress\u003c/sub\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\u003ca href=\"docs/screenshots/agents.png\"\u003e\u003cimg src=\"docs/screenshots/agents.png\" alt=\"Agent fleet — 57 specialists with run counts\" width=\"100%\" /\u003e\u003c/a\u003e\u003cbr/\u003e\u003csub\u003e\u003cb\u003eAgents\u003c/b\u003e — 57 specialists with last-used + run counts\u003c/sub\u003e\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\u003ca href=\"docs/screenshots/memory.png\"\u003e\u003cimg src=\"docs/screenshots/memory.png\" alt=\"Memory layers and crystallized patterns\" width=\"100%\" /\u003e\u003c/a\u003e\u003cbr/\u003e\u003csub\u003e\u003cb\u003eMemory\u003c/b\u003e — 11 layers + crystallized incident patterns\u003c/sub\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n**Built for the one-person engineering org.** Indie hackers, solo founders, technical CTOs running everything themselves. *Not for teams* — see [FAQ](docs/FAQ.md#is-great_cto-for-teams).\n\n## Install\n\n```bash\nnpx great-cto init\n```\n\nRestart Claude Code after init. **Requires:** [Claude Code](https://claude.com/claude-code) · Node 18.17+\n\nSuperpowers and Beads companion plugins install automatically — no manual setup needed.\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003e📖 Full documentation — two gates · critics · 57 agents · 25 archetypes · 12 jurisdictions · 33+ compliance frameworks · board · cost · MCP\u003c/summary\u003e\n\n## Two decisions per feature\n\n```\n🟡 gate:plan   ←  you decide here (architecture + tasks + cost)\n   ↓\n🤖 senior-dev → 12-angle review → qa-engineer → security-officer → devops\n   ↓\n🟢 gate:ship   ←  you decide here (PR ready, security signed off)\n```\n\nArchitects, planners, reviewers, QA, security, DevOps run automatically between those two human checkpoints. **Memory persists** between sessions: every gate verdict appends to `~/.great_cto/decisions.md`, every retrospective appends to per-project `lessons.md`, and `/crystallize` promotes high-impact patterns to a global library agents query before re-solving.\n\n## Critics before the plan\n\nThe most expensive bugs aren't in the code — they're in decisions made before coding starts. Three critic agents run before the Plan stage, at the three positions where a mistake costs the most:\n\n| Critic | Catches |\n|---|---|\n| **Architecture critic** | Coupling that rules out multi-tenancy later · \"obvious\" O(n²) on real-scale data · circular dependencies between bounded contexts |\n| **Spec critic** | \"We solved the wrong problem\" — the worst class of bug, because no unit test will catch it · misaligned acceptance criteria · scope that was never agreed on |\n| **Schema critic** | `NOT NULL` without a default on a 50M-row table (deadlock in 10min after deploy) · missing `CONCURRENTLY` on index creation · irreversible migrations with no rollback path |\n\nPreviously critics only activated starting from Plan. Now the pipeline catches architectural and spec-level mistakes before implementation begins — when reverting costs hours, not days.\n\n## How great_cto compares\n\n|  | **great_cto** | Devin | Claude Code (alone) |\n|---|---|---|---|\n| Open source | ✅ MIT | ❌ closed | ❌ closed plugin model |\n| Self-host | ✅ runs locally | ❌ Cognition cloud | ✅ |\n| BYOK / multi-model | ✅ Claude Code | ❌ proprietary | ❌ Anthropic only |\n| Specialist agents | **57** (architect · PM · 12-angle review · QA · security · devops · 42 reviewers across archetypes, packs \u0026 jurisdictions) | 1 generalist | 1 generalist |\n| SDLC orchestration | architect → plan → impl → review → QA → security → devops | one-shot autonomy | edit loop |\n| Human gates | ✅ 2 per feature (plan + ship) | ❌ none | ❌ |\n| Memory across sessions | ✅ `decisions.md` + `lessons.md` + crystallize | ⚠️ thread only | ⚠️ thread only |\n| Cost tracking | ✅ per-agent + 30d history + savings_x | ❌ | ❌ |\n| Compliance frameworks | ✅ 33+ (PCI · HIPAA · SOX · GDPR · CCPA · DPDPA · EU AI Act · FDA SaMD · COPPA · FERPA · FedRAMP · NAIC · …) | ❌ | ❌ |\n| Pricing | free (you pay your LLM provider) | $500/mo | $20/mo |\n| Setup | `npx great-cto init` | sign up | install CLI |\n\ngreat_cto is **not** another coding-agent loop — it's the **orchestration layer above** the coding agent you already use. Think \"specialist team that reviews and gates the work\" rather than \"another assistant that types code.\"\n\n## Jurisdiction detection\n\n`npx great-cto init` scans three signal sources — README keywords, infra region strings (Terraform, `.env` `AWS_REGION=`, docker-compose `TZ=`), and `package.json` homepage TLD — and auto-detects which of **12 jurisdictions** apply:\n\n| Jurisdiction | Signals (README + infra) | Frameworks | Reviewer |\n|---|---|---|---|\n| `eu` | gdpr · eu users · nis2 · eu ai act · `eu-west-*` · `.de` TLD | GDPR · EU AI Act · NIS2 · ePrivacy | `gdpr-reviewer` |\n| `us-ca` | ccpa · cpra · california residents · do not sell | CCPA / CPRA | `us-privacy-reviewer` |\n| `uk` | uk gdpr · information commissioner · dpa 2018 | UK GDPR · DPA 2018 | `gdpr-reviewer` |\n| `in` | dpdpa · india users · rbi data localisation | DPDPA 2023 · RBI | `dpdpa-reviewer` |\n| `br` | lgpd · anpd · brazil users | LGPD | `gdpr-reviewer` |\n| `au` | privacy act 1988 · oaic · notifiable data breach | Privacy Act 1988 · CDR | `us-privacy-reviewer` |\n| `sg` | pdpa · pdpc · mas guidelines · singpass | PDPA · MAS TRM | `us-privacy-reviewer` |\n| `ca` | pipeda · quebec law 25 · casl · canadian users · `ca-central-*` | PIPEDA · Quebec Law 25 · CASL · OSFI B-10 | `us-privacy-reviewer` |\n| `jp` | appi · japan users · my number · `ap-northeast-1` · `japaneast` | APPI 2022 · PPC Guidelines · FISC | `us-privacy-reviewer` |\n| `cn` | pipl · mlps · china users · `cn-north-*` · `cn-east-*` | PIPL 2021 · DSL 2021 · MLPS 2.0 · CBDT | `gdpr-reviewer` |\n| `kr` | pipa korea · isms-p · kisa · korea users · `ap-northeast-2` | PIPA · ISMS-P · FSC regulations | `us-privacy-reviewer` |\n| `us` | ftc · us users · virginia cdpa · texas tdpsa | FTC Act · US state privacy laws | `us-privacy-reviewer` |\n\nWord-boundary matching prevents false positives (`\"india\"` doesn't match `\"indiana\"`). Detected jurisdiction is written to `PROJECT.md` as `jurisdiction: [eu, us-ca]` and gates the appropriate reviewer on every feature. Override manually:\n\n```yaml\njurisdiction: [eu, us-ca]\n```\n\n## Three commands you use every day\n\n```bash\n/start \"build a refund endpoint with PCI-DSS scoping\"\n# → architect → enterprise-saas-reviewer (PCI-DSS auto-loaded)\n# → pm → 5 Beads tasks → gate:plan (you approve)\n# → senior-dev → 12-angle review → qa → security-officer\n# → gate:ship (you approve) → devops → deployed\n\n/inbox\n# Pending gates · P0 incidents · blocked tasks · stale in-progress\n\n/digest\n# Weekly DORA + delta vs last week + cost-per-feature roll-up\n```\n\nPlus: `/audit` (existing-codebase scan), `/cost` (LLM router savings), `/sec` (security umbrella), `/oncall`, `/release`, `/rfc`. Full list: `~/.claude/commands/` after install.\n\n## Cost\n\n```\n~$34/month for a typical solo-CTO project — 20 pipeline runs/month, indicative.\n```\n\n| Pipeline | Cost/run | Runs/mo | Total |\n|---|---|---|---|\n| quick (config / typo) | $0.10 | 10 | $1 |\n| quick (new endpoint) | $1 | 6 | $6 |\n| standard (feature) | $5 | 3 | $15 |\n| deep (cross-cutting) | $12 | 1 | $12 |\n| | | | **~$34** |\n\nPay your own Anthropic API tokens. **No per-seat fee. No SaaS lock-in.** Routine triage auto-routes to Kimi K2 (Sonnet-equivalent at ~5× lower cost) → 60–80% reduction on log clustering.\n\n## 25 archetypes auto-detected\n\nEach archetype activates its own specialist agents and compliance checklists. Top 7:\n\n| Archetype | Tier | Specialist agents | Compliance |\n|---|---|---|---|\n| `enterprise-saas` | **deep** | enterprise-saas-reviewer | soc2-type-2 · iso27001 · gdpr · ccpa |\n| `agent-product` | **deep** | ai-prompt-architect · ai-eval · ai-security | eu-ai-act · owasp-llm-top-10 |\n| `fintech` | **deep** | pci · regulated | pci-dss · sox · kyc-aml · gdpr · dora |\n| `mlops` | **deep** | mlops-reviewer · ai-eval | eu-ai-act · nist-ai-rmf · iso42001 |\n| `library` | baseline | library-reviewer | openssf · sbom |\n| `cli-tool` | baseline | cli-reviewer | — |\n| `mobile-app` | standard | mobile-store-reviewer | store-policy · gdpr |\n\nFull table (25 archetypes) + how detection works: [docs/ARCHETYPES.md](docs/ARCHETYPES.md).\n\n## 11 domain packs — overlay reviewers\n\nDomain packs ride **on top of** archetypes. Auto-attached when CLI detects pack-specific signals (deps, README terms). Each pack adds its own reviewer(s), threat-model template, EVAL suite, and human gates — independent of base archetype.\n\n| Category | Packs |\n|---|---|\n| **AI verticals** | `voice-pack` · `clinical-pack` · `hr-ai-pack` · `drug-discovery-pack` |\n| **Digital health** | `digital-health-pack` _(wearable telemetry · mental-health AI · nutrition AI · physician HITL)_ |\n| **Fintech / regulated** | `lending-pack` · `em-fintech-pack` |\n| **High-compliance** | `clinical-trials-pack` · `climate-pack` |\n| **Engineering** | `api-platform-pack` · `robotics-pack` |\n\n→ **24 human-gate types** + 38 reference EVAL suites + 15 TM templates. Browse all 11 packs with **4-layer journey visualization** (archetype → pack → reviewer → gate): [greatcto.systems/packs.html](https://greatcto.systems/packs.html).\n\n## One real run, fully traced\n\nA Python CLI feature shipped through the full pipeline: **$2.39 LLM spend** vs ~$5,460 human-equivalent. Security caught two real defects QA had passed (`list(stream_csv())` defeated streaming → 14.5 MB peak RSS on 13 MB input). Multi-reviewer model catching what single agents miss, before merge.\n\nFull trace + artefacts: [greatcto.systems/proof](https://greatcto.systems/proof) · raw: [`docs/qa/runs/2026-05-09/E2E-CLI-PIPELINE.md`](docs/qa/runs/2026-05-09/E2E-CLI-PIPELINE.md).\n\n## CI integration\n\nDrop into any GitHub Actions workflow:\n\n```yaml\n- run: npx great-cto@latest ci ./ --sarif results.sarif\n- uses: github/codeql-action/upload-sarif@v3\n  if: always()\n  with: { sarif_file: results.sarif }\n```\n\n`great-cto ci` auto-detects `$GITHUB_ACTIONS` and emits `::error file=...,line=N::` annotations inline on PR diffs. Exit codes: 0 clean / 1 findings / 2 setup error.\n\n## Test pyramid\n\nLayered test suite — **structural + state-machine tier runs in \u003c2 min for $0** (`node --test tests/*.test.mjs`); real-LLM tier (25 archetypes × 4-8 stages + 11 packs + 9 reviewers) runs on-demand via OpenRouter for ~$5–10. Full breakdown: [docs/testing/](docs/testing/).\n\n## MCP\n\nNative [MCP](https://modelcontextprotocol.io/) server — **7 tools** callable from Claude Desktop or any MCP host. Local (no board needed): `detect_archetype` · `estimate_cost` · `query_decisions`. Board-backed: `project_status` · `cost_summary` · `pipeline_stages` · `recent_verdicts`.\n\n```json\n{ \"mcpServers\": { \"great-cto\": { \"command\": \"npx\", \"args\": [\"-y\", \"great-cto@latest\", \"mcp\"] } } }\n```\n\nFull setup + internal MCPs (Grafana, LLM router, Beads): [docs/MCP.md](docs/MCP.md).\n\n## Email alerts (zero-setup)\n\nFive things that need you to act in \u003c2h get emailed automatically — even when you're away from the board:\n\n| Trigger | When |\n|---|---|\n| 🚨 **P0 incident** | A P0 task opens in any project |\n| ⏸️ **Gate stale \u003e 2h** | A `gate:ship` is waiting on you for hours |\n| 🛡️ **Security BLOCKED** | `security-officer` rejected a merge |\n| 💸 **Budget alert** | Monthly LLM spend crosses 80% / 100% of budget |\n| 📊 **Weekly digest** | Friday 09:00 — shipped, spent, savings, QA |\n\n**Setup**: board → **Notifications** tab → enter email → enter the 6-digit code we send → pick triggers. No Resend signup, no API keys — delivery routed through `greatcto.systems/notify` (free, 100 emails/24h per verified email).\n\n## Limitations \u0026 non-goals\n\n- **Not for teams** — solo-CTO is the product. 2+ engineers? You've outgrown it.\n- **Not a replacement for senior engineers** — codifies process; doesn't make architectural judgement calls without one.\n- **Not a CI/CD system** — gates run locally / in-session. You still need GitHub Actions for actual merge.\n- **Not certification-audited** — PCI/HIPAA/SOC2 archetype scaffolds are starting points, not certifications.\n- **Not deterministic** — LLM-generated outputs. Every gate verdict should be sanity-checked.\n\n## FAQ (top 5)\n\n**Is my source code used to train models?** No. Claude API zero-retention by default for paying customers. great_cto adds nothing.\n\n**How do you keep token costs down?** Haiku-by-default + Kimi K2 router for triage (60–80% savings) + cost-guard hook.\n\n**Can I disable hooks?** Every hook honors `GREAT_CTO_DISABLE_\u003cNAME\u003e=1`. Per-file secret-scan opt-out: `// great_cto:allow-secrets`.\n\n**What if I'm not solo?** great_cto is built for the one-person engineering org. If you have 2+ engineers and need shared boards / multi-seat auth, you've outgrown it.\n\nFull FAQ: [docs/FAQ.md](docs/FAQ.md).\n\n## Architecture\n\nThe plugin runs inside Claude Code (or any MCP-capable host); 57 agents are markdown specs; tasks live in Beads (dolt, git-native); memory is plain markdown (no vector store). Diagram + stack table: [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md).\n\n## What's new\n\n**v2.21.0** (May 2026) — **Flow Compiler UX**: `npx great-cto init` now prints a **Compiled flow** with agents, gates, compliance, and cost estimate per feature cycle. Writes `.great_cto/FLOW.md` — agents read it to know exactly how to orchestrate your SDLC.\n\n**v2.20.0** (May 2026) — **Detection v2**: **12-jurisdiction coverage** (added CA · JP · CN · KR with full legal framework + human gates) · **infra-signal detection** (Terraform region strings, `.env` `AWS_REGION=`, docker-compose `TZ=`, `package.json` homepage TLD) · **word-boundary matching** (no more \"india\" → \"indiana\" false positives) · **pack hints** for niche archetypes (`suggestedPacks` surfaces robotics/climate/clinical-trials/hr-ai/em-fintech packs when confidence is low). Token savings: –87.7% per pipeline run (v2.19.0 context-architecture redesign).\n\n**v2.19.0** (May 2026) — **Token economy Phase 1+2**: artifact summaries (≤250 tokens, auto-generated) + task-aware memory filter (top-k relevant entries per task). –87.7% tokens per pipeline run.\n\n**v2.17.0** (May 2026) — **companion plugins auto-install** · **Architecture / Spec / Schema critics** before Plan stage.\n\n[Full changelog →](CHANGELOG.md)\n\n## Roadmap\n\n- **Evals runner in CI** — run golden-set eval suites on every PR, catch prompt regressions automatically\n- **Self-improving loop** — agents that learn from verdicts and improve their own prompts over time\n- **Decision scoring** — track which gate decisions turned out to be right; surface patterns\n- **/crystallize** — promote high-impact lessons to reusable skills the whole pipeline can query\n\n[Vote on the next feature →](https://github.com/avelikiy/great_cto/discussions/categories/ideas)\n\n\u003c/details\u003e\n\n## Author\n\n[avelikiy](https://github.com/avelikiy) — CTO building AI-native trading and fintech platforms (0→1, 1→N). great_cto is the result of automating my own loops, one agent at a time. Every rule appeared in response to a real problem in a real production system.\n\n## Community\n\n| Channel | What |\n|---|---|\n| 🐛 [Issues](https://github.com/avelikiy/great_cto/issues) | Bugs, feature requests, archetype proposals |\n| 💡 [Discussions](https://github.com/avelikiy/great_cto/discussions) | Questions, patterns, show-and-tell |\n| 📝 [Blog](https://velikiy.hashnode.dev) | Architecture deep-dives |\n| 🔒 [SECURITY.md](SECURITY.md) | Responsible disclosure |\n\n## Contributing \u0026 License\n\nPull requests welcome — see [CONTRIBUTING.md](CONTRIBUTING.md). Good first issues: [`good-first-issue`](https://github.com/avelikiy/great_cto/issues?q=is%3Aopen+label%3Agood-first-issue).\n\nMIT — see [LICENSE](LICENSE).\n\nIf great_cto saved you time, please star the repo — it helps other solo CTOs find it.\n\n[![Star History Chart](https://api.star-history.com/svg?repos=avelikiy/great_cto\u0026type=Date)](https://star-history.com/#avelikiy/great_cto\u0026Date)\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**Built by [@avelikiy](https://github.com/avelikiy)**\n*Stop being the only person who can ship.*\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favelikiy%2Fgreat_cto","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Favelikiy%2Fgreat_cto","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favelikiy%2Fgreat_cto/lists"}