By Brayanhenaor
Universal clean-code intelligence for Claude Code. Skills, agents and hooks that push for the cleanest, simplest, most maintainable code in any language — questioning the developer and itself, verifying before claiming done, and refusing to over-engineer. Deep .NET pack today; language-agnostic core for everything else.
Deep, isolated clean-code auditor. Reviews a given set of files or a diff against the full Supercode ruleset (clean-code-core + anti-overengineering + the active stack pack) and returns findings by severity with file:line, rationale, and a suggested fix. Read-only — never modifies code.
Deep, isolated security auditor. Reviews a set of files or a diff for exploitable vulnerabilities (OWASP Top 10, auth, injection, secrets, access control, data exposure) and returns findings by severity with the attack scenario and a fix. Read-only — never modifies code.
Generate an Architecture Decision Record after a real decision is made. Use when documenting an architectural choice — typically after the plan skill, or standalone. Forces conscious, justified decision-making (challenges the developer before writing) and emits the team's official ADR template, frozen.
Guard against over-engineering before and while writing code. Use when about to build or implement something from scratch, hand-roll a custom solution, add a dependency, introduce an abstraction/layer/pattern, or when a solution feels heavier than the problem. Pushes for the simplest thing that is still clean — questioning whether the code needs to exist at all, whether the standard library or platform already does it, whether a proven library already solves it (don't reinvent the wheel), and whether it can be done in fewer moving parts.
Senior-architect lens for decisions that cross services, layers, or systems. Use when designing a feature that spans boundaries, choosing between architectural approaches, adding an external integration, or anything affecting scalability, availability, or operational complexity. Surfaces trade-offs and failure modes before code is written.
Generate a professional change-control document for specific commits or pending changes. Use when you need a formal record of a change for review, QA, or release — distinct from a git commit message. Emits the team's official change-control template, frozen.
Analyze code for performance and efficiency problems — algorithmic complexity, N+1 queries, needless allocations, blocking I/O, and missing caching. Use when reviewing hot paths, data-access code, loops over large data, or endpoints returning collections. Grounds findings in evidence, not premature optimization.
Executes bash commands
Hook triggers when Bash tool is used
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.
Universal clean-code intelligence for Claude Code. A plugin of skills, agents, and hooks that push every change toward the cleanest, simplest, most maintainable form — in any language — questioning the developer and itself, verifying before claiming done, and refusing to over-engineer.
Deep .NET pack today; a language-agnostic core for everything else.
In Claude Code:
# 1. Add this repo as a plugin marketplace
/plugin marketplace add Brayanhenaor/ai-standards
# 2. Install the plugin
/plugin install supercode@supercode
# 3. Check it's active
/plugin
That's it. No per-project setup. To work better in a specific repo, run /supercode:init once — it
detects your stack and conventions and writes a short project profile so every skill adapts to your
codebase.
supercode works in two ways at the same time, and you don't choose between them:
Most skills activate on their own when the context calls for them, because Claude reads each skill's description and invokes the right one at the right moment. You don't type anything.
async/concurrent code → the concurrency lens watches for races and deadlocks..NET project → the dotnet pack layers on the .NET-specific rules.You can also just describe what you want ("review this", "plan how to add X", "is this ready to ship?") and Claude picks the matching skill automatically — no exact command needed.
When you want a specific skill on demand, call it with /supercode:<skill>. Anything after the name
is passed as input.
/supercode:review --diff # audit the current changes
/supercode:review --full src/payments # audit a whole area
/supercode:plan add idempotent payment retries
/supercode:security-audit --diff
/supercode:gate # pre-PR go / no-go
/supercode:adr use the outbox pattern for order events
Every skill works both ways. The list below groups them by how you'll usually reach for them.
| Command | What it does |
|---|---|
/supercode:review [--diff|--full [path]] | Audit code against the full ruleset; findings by severity with file:line + fix. Default --diff. |
/supercode:security-audit [--diff|--full] | OWASP-aligned security audit with the exploit path for each finding. |
/supercode:plan <what you want to build> | Architectural consultant — options, trade-offs, challenges you, no code until agreed. |
/supercode:grill | Pressure-tests your plan one sharp question at a time. |
/supercode:gate | Pre-PR orchestrator: build, tests, review, security, migration, hygiene → go/no-go. |
/supercode:scaffold <feature> | Lays down a feature mirroring your project's real architecture. |
/supercode:test <target> | Generates behavior-focused tests in your project's own stack. |
/supercode:refactor <target> | Behavior-preserving cleanup in small, test-backed steps. |
/supercode:commit | A Conventional Commits message from your real staged diff. |
/supercode:adr <decision> | Architecture Decision Record (official template), after challenging you on it. |
/supercode:changelog [commits] | Formal change-control document (official template). |
/supercode:tech-doc | Full technical-manual JSON extracted from the codebase. |
/supercode:migrate | Checks a DB migration for locks, data loss, and zero-downtime safety. |
/supercode:zoom-out | Maps an unfamiliar area of code before you dive in. |
/supercode:standup | A standup summary from your recent git activity. |
/supercode:init | One-time: detect stack + conventions, write a project profile. |
These work as background lenses while you code, and you can still call any of them by name:
npx claudepluginhub brayanhenaor/ai-standards --plugin supercodeFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
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.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
AI-powered development tools for code review, research, design, and workflow automation.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.