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
Database engineering specialist for Laravel 13. Expert in SQL optimization, indexing strategy, PostgreSQL features (JSONB, materialized views, partitioning), MySQL features (InnoDB, utf8mb4, partitioning, replication), transaction management, read replicas, and Laravel 13 vector search with pgvector.
FuZhiyu/ResearchProjectTemplate
Agent Claude Code
Review analysis code for correctness and adherence to project guidelines. Focus on data integrity, merge correctness, and empirical research best practices. Check if implicit data handling (like missing values) aligns with analytical objectives.
Agent Claude Code
Code search and analysis across the entire firmware project. Uses fw-context index for symbol lookup, cross-references, and code explanations. Use for any code exploration — finding functions/classes, tracing call chains, understanding modules across domains (BLE, modem, CBOR, RTOS, OTA). Does not replace…
Agent Claude Code
Security review persona — OWASP Top 10, secrets, authentication/authorization, injection, and dependency risks. Used by /bw-review (called by /bw-work and /bw-ship).
Agent Claude Code
Read-only Obsidian vault exploration. Use proactively when searching notes, understanding vault structure, finding connections, or gathering context from a vault.
dynatrace-oss/dynatrace-snowflake-observability-agent
Agent Claude Code
../../.agents/dsoa-dev.md.
Agent Claude Code
Use proactively after non-trivial changes to @epam/ai-dial-ui-kit. Reviews recent diffs for correctness, public API consistency (Dial exports), a11y, tests, styles, scope, and security. Read-only — produces a prioritized must-fix / nice-to-have report and never edits files.
Agent Claude Code
Write clean, safe, readable shell scripts following best practices. Use proactively whenever tasks involve creating or modifying shell scripts, bash scripts, or installation scripts.
Agent Claude Code
Blocking structured native correction executor.
Agent Claude Code
Weekly SSOT freshness check — compares CLAUDE.md and docs/ARCHITECTURE.md against the actual codebase state and flags sections that have drifted. Trigger phrases: "check drift", "ssot health", "is CLAUDE.md current", "run drift monitor", "check harness freshness".
Agent Claude Code
Use this agent when working with iOS 26-specific UI components or features, particularly when implementing or updating liquid glass components or other iOS 26-exclusive design patterns. Examples:\n\n \nContext: User is implementing a new liquid glass component in their iOS 26 app.\nuser: "I need to create a liquid…
Agent Claude Code
DevOps Engineer responsible for stack-aligned Infrastructure as Code, technology-optimized CI/CD pipelines, architecture-informed deployment execution, technology-aware environment management, and stack-specific rollback procedures.
Agent Claude Code
Budget and bidding specialist. Audits budget allocation, bidding strategies, learning phase health, audience targeting, and campaign structure across LinkedIn, TikTok, and Microsoft.
Agent Claude Code
PROACTIVELY scan codebases for LLM API usage patterns and classify each call by task type, model used, and optimization potential.
Agent Claude Code
Builds and revises Livewire Flux UI — Blade markup using components, forms, modals, tables, page layouts and icons. Use when a task involves creating or changing a Flux interface, picking the right Flux component, checking whether a component needs Flux Pro, or resolving Heroicon names. Resolves every Flux question…
Agent Claude Code
MUST BE USED PROACTIVELY. Universal read-only explorer agent. Combines jrag graph navigation (call chains, service boundaries, routes, impact analysis, FQN resolution) with broad file-system search (grep, glob, excerpt reading). Use for any exploration task: locating code, tracing dependencies, finding patterns…
lhpaul/ai-dev-framework-template
Agent Claude Code
Coordination agent for a single workflow item via /run-item (or deprecated /run-item-work). Runs the shared bounded prelude then Protocol 91 until waiting on a human, blocked, or escalated.
SarutobiSasuke8/agentops-template
Agent Claude Code
Acceptance testing and ship-readiness lens. Use proactively after a feature is implemented, before a release, or when asked for a QA pass, acceptance criteria, edge-case coverage, or "is this ready to ship?". Reports findings with severity and a fix list. Read-only.
Agent Claude Code
CFO advisory agent for financial strategy, modeling, analysis, and fiscal leadership. Use when analyzing financial statements, building financial models, DCF analysis, Monte Carlo simulations, board financial presentations, capital allocation, risk management, or when user mentions CFO, financial planning, budgeting…
kasperjunge/agent-resources-legacy
Agent Claude Code
A simple subagent that greets the user.
tornikegomareli/claude-plugin-codex
Agent Claude Code
Proactively use when Codex is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Claude Code through the companion runtime.
Agent Claude Code
Validates and synchronizes marketplace.json AND README.md with all plugin changes. Use PROACTIVELY after creating, updating, or modifying any plugin in this repository to ensure the marketplace registry and documentation stay accurate.
hongsw/claude-agents-power-mcp-server
Agent Claude Code
A coding-agent role for building complete web applications, covering both the part users see and the server and database behind it.
Agent Claude Code
AUDIT orchestra conductor (orchestra #21). ALWAYS spawn after any high-stakes orchestra output — BUILD, AI/ML, AUTOMATION & OPS, EXECUTIVE ADVISORY, PERSONAL FINANCE, or any change to install.sh / hooks / .github/workflows / secrets. Defaults to NEEDS WORK. Requires fresh verification evidence before flipping to…
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: