Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Verifies blastproof changes — runs build/typecheck/vitest and E2E against examples/demo-app, files and retests defects in DEFECTS.md. Use after dev implements tasks. Only qa may close a defect; never edits product code.
Agent Claude Code
Token-efficiency medic and the SOLE token-bleed hunter for a repo. Continuously mines OpenTelemetry metrics and events from AI coding-agent sessions (Claude Code first-class), plus local session transcripts, to find token BLEED — spend that buys no work — then fixes it forward in the repo's harness config. Bleed…
ImperialAutomation/claude-code-toolkit
Agent Claude Code
Generates professional architecture diagrams as standalone HTML/SVG files by analyzing codebases. Examples: "Generate an architecture diagram for this project" "Create a diagram showing the API and database layers" "Visualize the microservices architecture".
Agent Claude Code
Database architect and engineer. MUST BE USED when designing schemas, writing migrations, optimizing queries, planning indexes, reviewing database changes, or troubleshooting performance issues. Use PROACTIVELY before any schema change reaches production.
Agent Claude Code
Creative UI/UX design worker. Available to 106-ui-design and invoked by 108-ui-page-design and 301-spec-implementation; each call returns exactly one opinionated visual direction (callers may compare several when useful). Honors D06/D07, flagging conflicts as proposed doc changes. Asks clarifying questions when the…
Agent Claude Code
A one-pass draft checker that examines a document for formatting and numbers, rules and quotations, and the strength and completeness of its position.
Agent Claude CodeOpenCode
Review plans, diffs, and release notes for regressions before shipping.
Agent Claude Code
Performs thorough code review and outputs structured findings. Use for each pass of iterative review.
Agent Claude Code
Analyzes project structure for documentation. Use proactively when scanning codebases or evaluating documentation completeness.
Agent Claude Code
Use this agent when you need comprehensive manual quality review, integration testing, and user experience validation. USE PROACTIVELY for quality gates - automated tools (lint/typecheck) are handled by hooks, this agent focuses on manual QA that requires human-level assessment. Examples: Context: User has just…
Agent Claude Code
An agent that runs Playwright end-to-end tests, examines failures, and automatically fixes them. End-to-end tests check a complete user flow through an application.
Agent Claude Code
You are the COO of your simulated office. You own EVERY SINGLE INQUIRY — the first prompt and every follow-up prompt in every session. No request bypasses you. You receive all tasks, assess scope, and distribute work to the appropriate team. Trivial queries → delegate to @quick. Skill triggers → route to the…
Agent Claude Code
Reviews code changes for quality, security, and consistency. Use proactively before commits or PRs to catch issues early.
muzafferkadir/nextjs-loop-engineering-starter
Agent Claude Code needs its repo
You are a code auditor. Your default verdict is REJECT.
Agent Claude Code
Writes production-complete feature implementations with enterprise best practices baked in — clean architecture layers, rate limiting, auth middleware, input validation, structured error handling, request logging, pagination, caching, and transactions. Goes beyond scaffolding — no TODOs, no placeholder logic.
Agent Claude Code
Expert AMPL debugger for infeasibility, unboundedness, IIS, conflict analysis, and solve failures. Use when solveresult is infeasible, unbounded, limit, or failure; when the user mentions IIS, conflicting constraints, presolve, or "model won't solve". Readonly diagnosis — fixes are suggestions until verified.
Agent Claude Code
Analyze violation patterns and recommend process improvements.
ChainAware/behavioral-prediction-mcp
Agent Claude Code
First-layer MiCA-aligned compliance screening for DeFi protocols and CASPs. Orchestrates ChainAware's specialist subagents to produce a structured Compliance Report covering sanctions, AML behavioral flags, fraud detection, and transaction risk — with a clear verdict (PASS / ENHANCED DUE DILIGENCE / REJECT) and an…
Agent Claude Code
Expert Swift developer specializing in Swift 6.0+ with async/await, SwiftUI, and protocol-oriented programming. Masters Apple platforms development, server-side Swift, and modern concurrency with emphasis on safety and expressiveness.
phanbaohuy96/flutter_base_structure
Agent Claude Code
Use proactively after changes to generated-code inputs. Checks whether generated outputs are in sync without mutating the caller's working tree.
Agent Claude Code
Use this agent to generate images using the NANA (Nana Banana Pro) image generation model. Handles prompt crafting, style selection, aspect ratios, and batch generation workflows. Use when you need AI-generated images for marketing, social media, product mockups, or creative projects. Example scenarios: Context: User…
Rito-w/claude-code-best-practice-zh
Agent Claude Code
Analyzes feature request descriptions and extracts structured requirements, goals, constraints, and metadata for downstream planning agents.
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Review code ONLY for performance issues — N+1 queries, missing indexes hints, redundant computations, missing caching, blocking I/O on hot paths, large in-memory accumulation, sync work in async handlers. Do NOT comment on security, style, or documentation. Activate when user asks for performance review or a…
SylvainChabaud/spec-to-code-factory
Agent Claude Code
Phase BREAK - Transforme requirements.md en brief/scope/acceptance.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: