Engineering base: 25 skills (process, backend, frontend, QA, security, ops), 12 specialized agents, session-continuity automation, ADR/SDD/release workflows.
Create a new Architecture Decision Record — /be:adr <short decision title>
Bootstrap the engineering base in the current project — docs structure, CLAUDE.md, and session protocol
Analyze the blast radius of the current changes — risk level + targeted review checklist
Run the pre-go-live checklist and draft the changelog entry for the release
Close a work session — update HISTORY.md, structural-analysis, lessons-learned, and commit docs with the code
Use for coordination work — sequencing multi-agent features, maintaining API contracts before development, removing blockers, and running the sprint protocol. Analysis role: does not edit application code.
Use for reliability and operations work — defining SLOs, configuring monitoring and alerts, writing runbooks, incident response coordination, and postmortems.
Use for test design and implementation — unit, integration, and E2E tests, coverage analysis, and bug reproduction. Rule: a bug becomes a failing test before it gets fixed.
Use for backend implementation tasks — REST endpoints, business rules, persistence, database migrations, and server-side security. Delegates security review to qa-security-reviewer and test design to qa-engineer.
Use for BI, analytics, and automatic-insight tasks — designing analytical queries, defining metrics and KPIs, and implementing anomaly/trend detection. Read-only over production data: never creates, changes, or removes records.
Use when creating a centralized exception handler, adding new error types, or defining a REST API's error response contract. Exception hierarchy, HTTP status mapping, and RFC 9457 problem-details format, with a Spring Boot example as a resource.
Use when creating the initial structure of a REST API, introducing a breaking change, or migrating unversioned endpoints to a versioned model. URL-prefix strategy (/api/v1/), breaking-change criteria, deprecation lifecycle with Sunset headers, and a phased migration checklist.
Use when creating tables, adding columns, creating indexes, changing constraints, or migrating data with any versioned migration tool (Flyway, Liquibase, Alembic, Prisma Migrate, Rails migrations). Naming, idempotency, and safe schema evolution rules.
Use when implementing token-based authentication (JWT), deciding how to revoke tokens on logout, or choosing where to store tokens on the client. Stack-agnostic flow, secret handling, blocklist revocation, and client storage rules, with Java/Spring examples as a resource.
Use when implementing or fixing any REST endpoint that returns a collection. Never return an unbounded list — server-side pagination with offset or cursor strategies, response contract, and limits. Spring Boot and Angular examples as on-demand resources.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A universal engineering base for AI-assisted software projects — delivered as a Claude Code plugin (skills, agents, commands, hooks) and as an npm installer for Copilot, Cursor, and any other AI tool.
basic-engineering is a foundational framework designed to maximize the value of any AI assistant in real-world software projects. AI tools are only as good as the context and structure surrounding them — without clear principles, defined roles, reusable knowledge, and living documentation, AI assistance degrades into noise. This base provides the scaffolding that elevates AI from autocomplete to a genuine engineering partner.
/plugin marketplace add barcelosvinicius/basic-engineering
/plugin install be@basic-engineering
Then, in your project: /be:bootstrap. Done — 25 skills, 12 agents, 7
commands, and the session-continuity hook are active. Update later with
/plugin update be@basic-engineering.
npx @barcelosvinicius/basic-engineering install # copies the base to .github/base/
npx @barcelosvinicius/basic-engineering check # check for updates
Then follow .github/base/BOOTSTRAP.md. The content is identical — plain
markdown readable by any tool.
check-version.shis deprecated — usebe checkinstead.
| Component | Count | What it is |
|---|---|---|
| Skills | 25 | Reusable technical knowledge in Agent Skills format (skills/<name>/SKILL.md + on-demand resources): process protocols (session continuity, SDD, ADR, code review, code documentation, impact/structural/domain analysis, dependency management), backend patterns (errors, versioning, migrations, auth, pagination), frontend (UX, accessibility), security (secrets), operations (observability), CI/CD, testing |
| Agents | 12 | Ready-to-use specialized subagents — dev (backend, frontend, data), mgmt (PO, PM, domain expert, architect), qa (engineer, security reviewer, pentest), infra (devops), ops (SRE). They work without customization: each reads the project's conventions from CLAUDE.md and docs/ at runtime. Analyst/security agents are tool-restricted to read-only |
| Commands | 7 | /be:session-start, /be:session-end, /be:adr, /be:impact, /be:release-check, /be:structural-analysis, /be:bootstrap |
| Hooks | 1 | SessionStart — injects docs/HISTORY.md Current State / Next Steps automatically (silent when the file doesn't exist) |
| Doc templates | 11 | Changelog, contributing, history, index, security policy, learning trail, structural analysis, lessons learned, onboarding, runbook, ADR |
| Principles | 1 | engineering-principles.md — technology-agnostic rules for UX, security, coupling, testing, observability, resilience, plus the AI documentation protocol |
The plugin deliberately ships no auto-started MCP servers — every server
adds processes, permissions, and context tokens. plugins/be/mcp.recommended.json
is a reviewed-by-you starting point (GitHub, docs server, read-only DB) to
copy into your project's .mcp.json.
proc-sdd skill)..claude-plugin/marketplace.json ← plugin marketplace manifest
plugins/be/ ← the canonical content (one source of truth)
├── .claude-plugin/plugin.json
├── skills/<name>/SKILL.md ← 25 skills + resources
├── agents/*.md ← 12 subagents
├── commands/*.md ← 7 slash commands
├── hooks/ ← SessionStart hook
├── templates/docs/ ← 11 documentation templates
├── BOOTSTRAP.md ← project kickoff guide
├── engineering-principles.md
├── ai-context.template.md ← CLAUDE.md template
└── mcp.recommended.json
bin/be.js · lib/installer.js ← npm CLI for non-Claude tools
scripts/validate.js · test/ ← structural validation + installer tests
npx claudepluginhub barcelosvinicius/basic-engineering --plugin beHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.