Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
TserenTserenov/FMT-exocortex-template
Agent Claude Code
A helper agent that updates a work-plan document using the actual status of related work plans. A work plan is a project record of tasks, blockers, and progress.
Agent Claude Code
Adversarial research idea evaluator — stress-tests ideas along 7 dimensions (novelty, impact, timing, feasibility, competitive landscape, nugget, narrative) and returns a Pursue/Refine/Kill verdict.
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
Evaluates a startup idea on a single assigned dimension using calibrated binary rubrics. Spawned by the /tweak:evaluate orchestrator for independent dimension evaluation.
Agent Claude Code
Creates task graphs from plans with verification and self-review.
protokol/solidity-typescript-hardhat-template
Agent Claude Code
Review Solidity contracts for security vulnerabilities, incentive design, and OpenZeppelin best practices.
Agent Claude Code
A storyboard specialist that turns a script into organised visual storyboard prompts.
Agent Claude Code
Backend specialist for API design, database operations, server-side logic, authentication, and system architecture.
Agent Claude Code
Receives and processes tasks from the central inbox system.
Agent Claude Code
Full-spectrum engineering health auditor. Evaluates Cyclomatic Complexity, Cognitive Complexity, Nesting Depth, Function Length, File Length, Maintainability, Code Smells, Duplicate Code, Technical Debt, Type Safety, Test Coverage, Test Quality, Security Findings, Dependency Risk, Build Health, Lint Health…
Agent Claude Code
Part of the agentcheck package for automated code review. Analyzes security implications of code changes. Runs when user finishes commit work or requests agentic review. Relevant after any changes involving authentication, data handling, or external APIs. Focuses on new security risks introduced by modifications.…
manikosto/claude-code-python-stack
Agent Claude Code
API test automation specialist. Generates OOP-based pytest test suites with httpx/requests, Pydantic models, Allure reporting, and proper test data management. Use when writing new API tests or expanding test coverage.
Agent Claude Code
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Agent Claude Code
Independent adversarial reviewer for a code change. Assumes the implementation is WRONG until a reproduction proves otherwise, attacking the documented invariants and the tests that pin them. Produces a findings JSON the gate records and enforces. Never fixes the implementation and never sees the author's reasoning …
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
Implements a planned story in an isolated context. Invoked by /ks-execute.
Agent Claude Code
Architecture scout used only by /sdd-architecture-scan. Analyzes one worklist unit and writes its report to .sdd-scan/reports/. Not for general tasks.
Agent Claude Code
Workflow management and orchestration specialist agent.
Agent Claude Code
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
Agent Claude Code
Copilot and cursor as a top-notch coding agent.
Agent Claude Code
The Conductor. Coordinates all work, NEVER writes code, maintains clean context, enforces gates.
bighardperson/computer-science-skills-collection
Agent Claude Code
Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough…
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…
YuDefine/nuxt-supabase-starter
Agent Claude Code needs its repo
An agent for taking screenshots of a website or app and checking whether its interface looks correct. It returns a report based on the requested visual checks.
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: