By gagandeepp
Shared guardrails layer for all coding agent families — enforces safety, quality, governance, observability gates, and optional ChromaDB vector memory for semantic session recall
Initialise the SQL Server audit database -- creates the guardrails schema and all four audit tables (AuditLog, CostLog, RateLog, CircuitBreakerState) if they do not already exist. Safe to re-run (idempotent). Uses sqlcmd on Windows; Python/pyodbc on Linux/macOS.
Rebuild the ChromaDB vector index from JSONL memory files. Iterates all agent-family JSONL files and .story-memory.jsonl, skips hook-only records, and upserts each surviving record into the correct Chroma collection. Idempotent — safe to re-run at any time.
Reset the guardrails circuit breaker counter for the current workspace. Use after investigating and resolving the cause of 3 consecutive P0/ceiling failures.
Use after every guardrail gate invocation — writes a structured JSONL record to .guardrails-audit.jsonl with timestamp, agentFamily, skill, check, result, detail, userStoryId, sessionId, and resolvedBy. Always-on; cannot be disabled.
Use at invocation start and poll mid-session — enforces token budget per session, rate limit per user per hour, circuit breaker after consecutive failures, and user story cost ceiling. This skill is the sole enforcer of budget ceilings; cost-tracker only aggregates.
Use when committing, pushing, and raising a PR — stages changed files, writes a Conventional Commits message, pushes to the remote branch, creates a GitHub PR via gh CLI, then posts the PR URL to configured Slack or Teams channels for review. Channel targets are configurable via .commit-push-pr.json or prompted interactively.
Use when a session is approaching token budget limits, processing large codebases, multi-ticket sprint runs, or multi-scanner security triages where context growth could exhaust the token budget mid-task.
Use at session end — aggregates token cost for the current session, appends to .guardrails-costs.jsonl, maintains a per-userStoryId rollup, and exposes the accumulated total to budget-monitor for ceiling enforcement. Does not enforce ceilings itself.
Modifies files
Hook triggers on file write and edit operations
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 monorepo of Claude Code plugin families providing backend, frontend, database, DevOps, security, guardrails, sprint planning, testing, and story implementation coding agents for enterprise teams. Each agent follows idiomatic best practices, enforces team coding guidelines, bundles LSP integration, and publishes to an internal org-wide plugin marketplace with governance controls.
A polyglot backend agent that implements features, fixes bugs, and writes tests in C#, Go, Java, and Node.js. Routes based on language detection.
| Plugin | Role | Required |
|---|---|---|
@Vensure-Devops-QA/backend-coding-agent | Core: config, routing, detection, guidelines, shared skills | Always |
@Vensure-Devops-QA/backend-csharp | C# (ASP.NET Core, xUnit, OmniSharp LSP) | Per team |
@Vensure-Devops-QA/backend-golang | Go (Gin/Echo/Chi, testify, gopls LSP) | Per team |
@Vensure-Devops-QA/backend-java | Java (Spring Boot, JUnit 5, jdtls LSP) | Per team |
@Vensure-Devops-QA/backend-nodejs | Node.js (NestJS/Express/Fastify, Jest, TS LSP) | Per team |
claude plugin install @Vensure-Devops-QA/backend-coding-agent
claude plugin install @Vensure-Devops-QA/backend-csharp
claude plugin install @Vensure-Devops-QA/backend-nodejs
/backend-init
.backend-agent.json, directory mapping, and auto-detection| Command | Purpose |
|---|---|
/backend-init | Scaffold .backend-agent.json and check prerequisites |
/backend-review | On-demand language-aware code review |
A component-aware frontend agent that builds pages, components, and features in React + Next.js and Angular. Routes based on both framework detection and component type (page, component, hook, layout, utility). Uses Prismatic (the org's internal design system) as the default UI library for React and Angular.
| Plugin | Role | Required |
|---|---|---|
@Vensure-Devops-QA/frontend-coding-agent | Core: component routing, styling resolution, a11y, guidelines, shared skills | Always |
@Vensure-Devops-QA/frontend-react | React + Next.js (Vitest, RTL, TS LSP) | Per team |
@Vensure-Devops-QA/frontend-angular | Angular (@angular/language-service LSP) | Per team |
claude plugin install @Vensure-Devops-QA/frontend-coding-agent
claude plugin install @Vensure-Devops-QA/frontend-react
claude plugin install @Vensure-Devops-QA/frontend-angular
/frontend-init
.frontend-agent.json, directory mapping, and auto-detection| Library | React | Angular |
|---|---|---|
| Prismatic (org default) | @Vensure-Devops-QA/prismatic-react | @Vensure-Devops-QA/prismatic-angular |
| Material | Material UI (@mui/material) | Angular Material |
| Bootstrap | React-Bootstrap | ng-bootstrap |
| Tailwind | Tailwind CSS | Tailwind CSS |
| Command | Purpose |
|---|---|
/frontend-init | Scaffold .frontend-agent.json and check prerequisites |
/frontend-review | On-demand component-aware code review |
A polyglot database agent that writes schemas, stored procedures, indexes, migrations, seed data, and ORM/ODM models for SQL Server, PostgreSQL, MongoDB, and Azure Cosmos DB. Routes based on engine detection.
Node.js/TypeScript language module for the backend coding agent — NestJS/Express/Fastify, Jest, typescript-language-server LSP
C# language module for the backend coding agent — ASP.NET Core, xUnit, OmniSharp LSP
Snyk Code (SAST), Open Source (SCA), IaC, and Container remediation skills for the security-coding-agent
Core plugin for the frontend coding agent. Provides config resolution, component-first routing, accessibility review, guidelines ingestion, optional vector memory, and shared skills for React + Next.js, Angular, and Vue + Nuxt.
Go language module for the backend coding agent — Gin/Echo/Chi, testify, gopls LSP
npx claudepluginhub gagandeepp/software-agent-teams --plugin guardrails-coding-agentComprehensive 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.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.