{
  "markdown": "# SoftCo — Autonomous AI Coding Agent & Software Company Skill\n\n[![GitHub stars](https://img.shields.io/github/stars/shihabshahrier/softco.svg)](https://github.com/shihabshahrier/softco/stargazers)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Supported AI Agents](https://img.shields.io/badge/AI_Agents-Claude_Code_|_Cursor_|_Windsurf_|_Cline-blue.svg)](#agent-support)\n\nTurn any AI coding agent (Claude Code, Cursor, Windsurf, Cline) into a complete, autonomous software company. The user describes their product or software idea; **SoftCo** handles the entire lifecycle: planning, system design, documentation, test-first coding, DevOps containerization, continuous integration, and automated deployment. The user only ever needs to configure the `.env` file.\n\n## 🚀 What it is\n\nAn **Agent Skill** (supporting [Agent Skills](https://docs.claude.com/en/docs/claude-code/skills)) that transforms any supported large language model (LLM) agent or developer assistant into a fully-functional, autonomous software engineering firm. It simulates an entire development team: Product Manager, Software Architect, Senior Engineer, DevOps Engineer, QA Engineer, Security Expert, and Technical Writer. \n\nThe agent operates under a highly-disciplined, professional software development lifecycle (SDLC) phase order:\n\n```\nPhase 0 → Phase 1 → Phase 2 → Phase 3 → Phase 4 → Phase 5 → Phase 6\nDiscovery  Design    Docs      Code      Test      Infra     Deploy\n```\n\nDocumentation and tests come before code. Test coverage of ≥ 80% is strictly enforced. Secrets are never committed to git. Every project ships with a standardized `AGENT.md` contract file that lets a fresh agent session continue the work seamlessly without questions.\n\n\n## 🤖 Supported AI Coding Agents & Platforms\n\nSoftCo integrates natively as a custom skill, system prompt instruction, or custom rule system across all major AI coding assistants and agent environments:\n\n| Agent / Editor | Works | Install Path / Setup |\n|-------|-------|-------------|\n| **Claude Code** | ✓ | `~/.claude/skills/softco` |\n| **opencode (SST)** | ✓ | `~/.claude/skills/softco` (shared) |\n| **OpenAI Codex** | ✓ | `~/.agents/skills/softco` |\n| **Amp / Goose / Kiro** | ✓ | `~/.agents/skills/softco` (shared) |\n| **Gemini CLI** | ✓ | `~/.gemini/antigravity/skills/softco` |\n| **Cursor** | ✓ | `.cursor/rules/softco.mdc` (included rules file) |\n| **Windsurf** | ✓ | `.windsurf/rules/softco.md` (included rules file) |\n| **Cline** | ✓ | `.clinerules/softco.md` (included custom rules) |\n| **GitHub Copilot** | ✓ | `.github/copilot-instructions.md` (included instructions) |\n\n## ⚙️ Installation & Setup\n\nEasily install SoftCo across all detected AI agents on your local machine using the automated installer script:\n\n```bash\n./install.sh\n```\n\nThis symlinks the `skill/` directory to all detected agent paths. Restart your agent session to load.\n\n### Install for one specific agent only:\n\n```bash\n./install.sh --agent claude     # Claude Code + opencode\n./install.sh --agent codex      # Codex / Amp / Goose / Kiro\n./install.sh --agent gemini     # Gemini CLI\n./install.sh --agent opencode   # opencode explicit path\n./install.sh --agent openclaw   # OpenClaw\n```\n\n### Uninstall from all agents:\n\n```bash\n./install.sh --uninstall\n```\n\n### Copy files instead of symlinking (useful for distributing configurations):\n\n```bash\n./install.sh --copy\n```\n\n## 🛠️ Manual Installation\n\nIf you prefer manual configuration, run the appropriate setup commands for your AI toolchain:\n\n```bash\n# Claude Code Skill Setup\nmkdir -p ~/.claude/skills && ln -s \"$(pwd)/skill\" ~/.claude/skills/softco\n\n# Codex / Amp / Goose / Kiro Setup\nmkdir -p ~/.agents/skills && ln -s \"$(pwd)/skill\" ~/.agents/skills/softco\n\n# Gemini CLI / Antigravity Setup\nmkdir -p ~/.gemini/antigravity/skills && ln -s \"$(pwd)/skill\" ~/.gemini/antigravity/skills/softco\n\n# opencode Custom Skill Setup\nmkdir -p ~/.config/opencode/skills && ln -s \"$(pwd)/skill\" ~/.config/opencode/skills/softco\n```\n\n## 🎯 Trigger Phrases & Intent Detection\n\nSoftCo activates automatically within your agent workspace on natural language developer requests:\n\n* **SaaS & API Greenfield Development**: `\"build me a SaaS / web app / backend API / CLI tool\"`\n* **Architecture Planning**: `\"design the architecture and system flow for ...\"`\n* **Infrastructure as Code (IaC) & DevOps**: `\"set up CI/CD pipeline, Dockerfile, Kubernetes clusters, or Terraform modules\"`\n* **LLM & AI Agent Integration**: `\"integrate Claude, OpenAI GPT, Gemini, RAG workflows, or MCP tools\"`\n* **Deployment & Orchestration**: `\"deploy our application to AWS, GCP, Azure, Fly.io, or Render\"`\n* **Code Auditing & Security Review**: `\"review my repository or audit my code for production readiness\"`\n* **Bug Fixing & Root-Cause Resolution**: `\"fix this bug or resolve this specific runtime error\"`\n\n## ⚡ Core Capabilities & Supported Stack\n\nSoftCo is pre-configured with industry-standard tech stack templates to accelerate development:\n\n* **Frontend Frameworks**: React + Vite, Next.js (App Router), Vue, Svelte, React Native (Expo)\n* **Backend Frameworks**: FastAPI (Python), Go + Gin, NestJS (Node), Express, Hono, Django, Flask\n* **AI & LLM Integration**: Anthropic Claude, OpenAI GPT, Google Gemini, AWS Bedrock, GCP Vertex AI, Groq, Together AI, Ollama; LangChain, LangGraph, CrewAI, Haystack, Model Context Protocol (MCP); RAG + agentic loops + structured JSON outputs + prompt versioning\n* **Databases & Vector Stores**: PostgreSQL + pgvector (default), MySQL, MongoDB, DynamoDB, Redis Cache, Qdrant, Pinecone, Weaviate, Neo4j, OpenSearch\n* **Infrastructure (IaC)**: Terraform-first (modular architecture); AWS, GCP, Azure, DigitalOcean, Fly.io, Render; Docker multi-stage builds; Kubernetes orchestration\n* **CI/CD Automation**: GitHub Actions standard workflows (Python / Node / Go templates); OIDC authentication; Trivy security vulnerability scanning; Release Please auto-changelogs\n* **Observability & Logging**: OpenTelemetry instrumentation, structured JSON logging (structlog, pino, slog), Prometheus + Grafana metrics, Sentry error tracking, Langfuse for LLM evaluation\n* **Security Standards**: OWASP Top 10 defaults, OIDC for cloud authentication, Secrets Manager integration, API Rate-Limiting, PostgreSQL RLS multi-tenancy, Prompt-Injection defenses\n\n## 📂 Repository Architecture & File Layout\n\n```\nskill/                              # custom skill source directory (symlinked to agent paths)\n├── SKILL.md                        # core entry point loaded by AI agents\n├── references/                     # detailed technical guides\n│   ├── 00-workflow.md              # phase-by-phase development workflow\n│   ├── 01-frontend.md              # React/Next.js/SPA/SSR best practices\n│   ├── 02-backend.md               # FastAPI/Go/Node API design patterns\n│   ├── 03-ai-integration.md        # RAG, LLM orchestration & prompt engineering\n│   ├── 04-databases.md             # SQL/NoSQL schema design & optimization\n│   ├── 05-infrastructure.md        # AWS/GCP cloud setup with Terraform\n│   ├── 06-cicd.md                  # GitHub Actions workflow pipelines\n│   ├── 07-security.md              # OWASP compliance & secret management\n│   ├── 08-observability.md         # OpenTelemetry, logging & APM metrics\n│   ├── 09-testing.md               # Unit, integration, E2E, & AI testing\n│   ├── 10-prompt-engineering.md    # Prompt optimization & version control\n│   ├── 11-doc-templates.md         # Markdown document templates\n│   ├── 12-verification.md          # Live-proof gate — run it & observe before \"done\"\n│   └── 13-design.md                # UI direction, design tokens, component inventory\n├── scripts/                        # helper automation scripts\n│   ├── scaffold.sh                 # bootstraps standard project skeleton\n│   ├── validate_env.py             # validates .env variables against .env.example\n│   ├── gen_schema.py               # compiles SQLAlchemy models to DB_SCHEMA.md\n│   └── cost_estimate.py            # calculates rough monthly cloud + LLM cost\n└── assets/                         # pre-packaged templates\n    ├── github-actions-templates/   # CI/CD pipelines (ci-python.yml, deploy-ecs, etc.)\n    ├── terraform-modules/          # modular cloud infra (network, ECS, RDS)\n    └── docker-templates/           # optimized multi-stage Dockerfiles\n```\n\n### Editor & Agent Adapters (Read directly by specific assistants)\n* **Cursor rules**: `.cursor/rules/softco.mdc`\n* **Windsurf rules**: `.windsurf/rules/softco.md`\n* **Cline custom rules**: `.clinerules/softco.md`\n* **OpenAI Codex hooks**: `.codex/hooks.json`\n* **GitHub Copilot instructions**: `.github/copilot-instructions.md`\n* **Agent configs**: `agents/openai.yaml`, [AGENTS.md](file:///Users/shahriar/Desktop/github/softco/AGENTS.md), [GEMINI.md](file:///Users/shahriar/Desktop/github/softco/GEMINI.md)\n\n## 💡 Example Usage & Workflows\n\nRun prompts like these inside any supported agent workspace session:\n\n### Greenfield Project\n```\n> build me a small SaaS for tracking gym workouts, with AI workout suggestions\n```\n*The agent detects intent, loads the SoftCo skill, and starts at Phase 0 (Discovery). Answer the interactive questions, approve the TDR architecture plan, watch the documentation land, and review the test-driven code modules.*\n\n### Repository Audit\n```\n> audit this repo and tell me what's missing for production readiness\n```\n*SoftCo parses the existing project, maps the architecture, and outputs a complete remediation plan (`docs/AUDIT.md`) scoring test coverage, security vulnerabilities, CI/CD pipelines, and documentation gaps.*\n\n### Scoped Feature Extensions\n```\n> add password reset to my FastAPI app\n```\n*SoftCo updates `docs/MODULES.md` and related specs, writes failing tests first, implements the logic, verifies the tests pass, and details the changes in the changelog.*\n\n## 🚫 Prohibited Actions & Strict Guardrails\n\nSoftCo strictly adheres to enterprise-grade engineering principles and **never**:\n* Hardcodes API keys, secrets, or passwords (always uses Secrets Manager or `.env.example`).\n* Runs unoptimized or dangerous database queries (e.g., `SELECT *` in production schemas).\n* Skips the documentation first phase (SDLC rigor is always enforced).\n* Merges to the `main` branch without passing linting, formatting, and test suites.\n* Implements authentication from scratch when proven libraries exist (Clerk, NextAuth, Supabase).\n* Deploys services without active health check and readiness probe endpoints.\n* Generates `.env` files with plaintext production credentials.\n* Allows un-typed or dangerous types (like `any` in TypeScript) in production code.\n\n## 📄 License\n\nThis project is licensed under the [MIT License](file:///Users/shahriar/Desktop/github/softco/LICENSE) — see the LICENSE file for details.\n\n---\n\n📖 **Project page:** https://shihub.online/projects/softco\n",
  "bytes": 10930,
  "sha": "d51f20fa214063eb4ecccd2e34d1246d99baf9efed38da22cf1f46009dbb7b87",
  "repo_slug": "shihabshahrier/softco",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_shihabshahrier_softco_312b3798/readme"
}