By hryer
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Implement the next task incrementally — build, test, verify, commit
Simplify code for clarity and maintainability — reduce complexity without changing behavior
Break work into small verifiable tasks with acceptance criteria and dependency ordering
Conduct a five-axis code review — correctness, readability, architecture, security, performance
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
Use to perform a staff-engineer review of Web3 backend code, architecture, or design docs. Focuses on production concerns specific to crypto products — idempotency, reorg handling, multi-chain edge cases, financial conservation, key management, vendor integrations (Fireblocks/Privy/Fordefi/QuickNode), database schema for wallets/addresses, fallback strategy, on-chain debugging (Tenderly), observability, and operational runbooks. This agent reviews from the perspective of someone who has shipped wallet infrastructure, indexers, and trading systems to production.
Use for security-focused review of wallet infrastructure code or design — key management, signing flows, MPC/multisig, ERC-4337, EIP-7702, paymaster abuse, recovery procedures. This agent reviews from a "what would an attacker do" perspective with deep knowledge of wallet-specific failure modes.
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
Use when designing or reviewing a crypto debit/credit card product. Covers card issuer integration (Marqeta, Stripe Issuing, GPS, Galileo), funding flow (auth → settle), ledger architecture for crypto-to-fiat conversion, KYC/AML compliance, BIN sponsorship, FX and crypto pricing, and chargeback handling. Use whenever the user mentions crypto card, debit card, card issuing, authorization flow, settlement, BIN sponsor, or interchange.
Use when designing or reviewing the internal accounting ledger for a crypto exchange, custodian, wallet product, or any system that holds user funds. Covers double-entry primitives (accounts, journals, transactions, entries), conservation invariants per currency, multi-currency entries without FX inside the ledger, pending/hold semantics, idempotency on inbound events, reversal via compensating entries, append-only storage, derived vs materialized balances, and the split between trade ledger and settlement ledger. Use whenever the user mentions internal ledger, double-entry, balances, user balances, accounting, ledger schema, conservation, idempotent debits/credits, hold accounts, settlement ledger, or "how do we track who owns what".
Use when designing or reviewing a crypto/financial matching engine. Covers order book data structures, matching algorithms (price-time priority, pro-rata), Go-side architecture (hexagonal/clean), single-pair vs multi-pair, in-memory vs persistent, hot-path optimization, and concurrency patterns. Use whenever the user mentions order book, matching engine, exchange backend, CEX architecture, limit order, or order matching.
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.
Production-grade engineering skills, agents, and commands for AI coding agents — built for crypto / Web3 backend work and covering the full lifecycle from spec to ship.
This is a Claude Code plugin. It teaches your agent how to write, test, review, and ship wallet infrastructure, indexers, matching engines, swap integrations, crypto-card products, and the vendor integrations behind them — with the rigor of a staff engineer who has shipped these systems to production.
Language guidance is pinned to canonical references so authoring and review share one definition of "good":
| Layer | Count | What it is |
|---|---|---|
| Commands | 7 | User-facing entry points (/build, /ship, …) that compose personas + skills |
| Agents (personas) | 5 | Single-role reviewers/auditors that produce a structured report |
| Skills | 55 | Workflows with steps + exit criteria, in three families (below) |
| Guidelines | 5 | Shared checklists (security, performance, testing, a11y, orchestration) |
The three layers compose like this (see agents/README.md for detail):
| Layer | Job | Example |
|---|---|---|
| Skill | The how — a workflow, invoked from inside a persona or command | incremental-implementation |
| Persona | The who — adopts a viewpoint, produces a report | web3-backend-reviewer |
| Command | The when — composes personas + skills | /review, /ship |
In Claude Code:
# Add this repo as a plugin marketplace
/plugin marketplace add hryer/crypto-infra-skills
# Install the plugin
/plugin install crypto-infra-skills@crypto-infra-skills
Local development (from a clone of this repo):
/plugin marketplace add .
/plugin install crypto-infra-skills@crypto-infra-skills
Once installed, the commands (/build, /ship, …) become available, agents can be invoked, and skills auto-trigger based on what you're doing.
Type a slash command to run a workflow. Each composes the relevant skills and personas.
| Command | What it does |
|---|---|
/spec | Write a structured specification before writing code |
/plan | Break work into small verifiable tasks with acceptance criteria + dependency order |
/build | Implement the next task incrementally — build, test, verify, commit |
/test | TDD workflow — write failing tests, implement, verify (Prove-It pattern for bugs) |
/review | Five-axis code review — correctness, readability, architecture, security, performance |
/code-simplify | Reduce complexity without changing behavior |
/ship | Pre-launch checklist via parallel fan-out to specialist personas → go/no-go |
A typical flow: /spec → /plan → /build (repeat per task) → /review → /ship.
Skills load automatically when your request matches their description (e.g., asking about a Fireblocks integration pulls in vendor-fireblocks). You can also invoke one explicitly by name. Skills are the knowledge layer — you rarely call them directly; commands and agents pull them in.
Invoke a persona for a focused review. They produce a structured report and do not call each other (you or a command orchestrate them).
| Agent | Role | Use for |
|---|---|---|
| code-reviewer | Senior Staff Engineer | Five-axis review before merge |
| security-auditor | Security Engineer | OWASP-style vulnerability audit |
| test-engineer | QA Engineer | Test strategy + coverage |
| web3-backend-reviewer | Web3 Staff Engineer | Crypto backend review: reorg, idempotency, ledger conservation, vendor integrations, key mgmt, infra, distributed systems, debugging |
| wallet-security-auditor | Wallet Security Engineer | Adversarial review of custody, signing, MPC/multisig, ERC-4337, Solana programs |
55 skills in three families, distinguished by name prefix.
category-* — decision frameworks (13)The entry point for a problem area. Each frames the use case, lays out vendor options, gives a build-it-yourself path, includes inline Go/TS/Rust + infra best practices, and branches to vendor-* skills.
npx claudepluginhub hryer/crypto-infra-skills --plugin crypto-infra-skillsAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
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.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.