Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
seungmanchoi/react-native-fsd-agent-template
Agent Claude Code
An integration specialist for connecting apps to APIs and managing shared data, using Axios, TanStack Query, and Zustand. It also covers analytics and crash reporting, secure token storage, store-review requests, and ad-related infrastructure.
AmadeusITGroup/ai-primitives-hub
Agent Claude Code
Specialized agent for system design and architecture decisions.
Agent Claude Code
The Conductor. Coordinates all work, NEVER writes code, maintains clean context, enforces gates.
Agent Claude Code
Babel architecture flow owner. Parses a free-form design idea, drives bb-prd → bb-arch → bb-mas, normalizes MAS via inline adapter, opens ready-for-rtl handoff. Trigger: new design idea, arch-needs-fix issue, or explicit /bba-architect.
Agent Claude Code
Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…
Agent Claude Code
Deep research agent that uses cortex as primary knowledge source.
Agent Claude Code
Environment and dependency preflight check for new projects. Detects runtime versions, runs compatibility probe scripts, collects the full dependency tree, and returns a structured inventory for cross-component analysis. Use when the user runs /hydra:preflight or when starting work on a new or unfamiliar project.
Agent Claude Code
Receives and processes tasks from the central inbox system.
Agent Claude Code
COMPLETENESS SEAT. Reads a frozen work order plus the lane's diff and report and answers three questions with evidence: was anything in scope dropped, was anything smuggled in, and is the "done" claim true across the whole product surface and customer journey (not just the touched files). Also the overengineering…
amirkiarafiei/open-scholar-peer
Agent Claude Code
Open ScholarPeer Literature Review & Expansion Agent — performs External Context retrieval via the dynamic-web search strategy. Activate this persona when the user invokes /2-osp-literature. Runs up to three distinct rounds — the user chooses how many (sub-domain anchor, method anchor, temporal expansion) to construct…
Agent Claude Code
GTM Specialist — marketing decks, GTM strategy, ICP definition, growth loops, competitive analysis, positioning, pricing, sales enablement.
sidarora28/build-with-claude-code
Agent Claude Code
Use this agent as the user's "chief of staff." Dispatches three specialists (notes-specialist, calendar-specialist, followups-specialist) in parallel, synthesises their outputs into a morning executive brief, writes a structured event log so the Daily Brain dashboard can visualise the orchestration live, and prints…
jonathan-vella/apex-accelerator
Agent Claude Code needs its repo
Azure governance discovery agent. Queries Azure Policy assignments via REST API (incl. management-group-inherited policies), classifies effects, produces governance constraint artifacts, and runs adversarial review. Step 3.5: after Architecture, before IaC Planning.
Agent Claude Code
Creates task graphs from plans with verification and self-review.
Agent Claude Code
An agent that checks whether the files promised by project tasks exist and synchronises their status in backlog.yaml, a file that tracks planned work.
Agent Claude Code
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
Agent Claude Code
Implementer. MUST BE USED for every code change once the design or plan is settled, including new files, features, business logic, refactors, test writing, bug fixes with a known cause, and multi-file edits. Delegate implementation to Keymaker instead of editing in the main conversation, so the main conversation's…
bkywksj/ruoyi-plus-uniapp-docs
Agent Claude Code
A code review helper for checking completed Astro pages and features against project rules, including Astro 7 conventions, SEO output, component boundaries, and shared design tokens.
Agent Claude Code
Specialist in user interface design, user experience flows, accessibility (a11y), and Tailwind CSS styling.
Agent Claude Code
You are reviewing code changes for production readiness.
Agent Claude Code
FastAPI + Pydantic v2 implementation specialist. Use PROACTIVELY to build async route handlers, dependency injection chains, Pydantic request/response models, and service logic in FastAPI projects.
Agent Claude Code needs its repo
Autonomous backlog generator that analyzes project state (open issues, PRs, code health) when agent slots are idle and creates 3-5 sized, actionable tasks. Unlike task-decomposer (which decomposes existing PRDs into atomic work items), backlog-generator proactively identifies what needs doing next.
Agent Claude Code
Writes unit, integration, and e2e tests that verify correctness without gaming assertions. Use when adding test coverage or writing new tests.
Agent Claude Code
Documentation drift detection and sync specialist. Use to update docs//.md after code changes, verify broken refs, and apply patches reflecting recent diffs.
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: