Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
dfrysinger/ai-job-hunt-toolkit
Agent Claude Code
Triggers when user shares a job posting URL, mentions applying to a role, or requests resume customization. Launch proactively when job application intent is detected.
Agent Claude Code
An agent that researches material for Claude Code usage tips. It examines official documentation, release notes, configuration files, hooks, MCP, and skills.
Agent Claude Code
Pipeline AC drift reviewer. Detects semantic misalignment between code changes and the active task's Acceptance Criteria — the layer that review-code's existence-check cannot catch (e.g. "VIP free shipping" silently implemented as "VIP 50% off"). Writes JSON findings to file - zero context pollution. Used exclusively…
Agent Claude Code
Security specialist that audits code for vulnerabilities and compliance issues.
Agent Claude Code
Manages API gateway configuration, routing, authentication, rate limiting, and request transformation for multi-service architectures.
Agent Claude Code
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.
Agent Claude Code
A staff-engineer-style code review agent named Guan Yu. It examines code changes for correctness, contracts between components, type safety, error handling, concurrency, security, and related risks.
Agent Claude Code
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Produces SECURITY.md. Spawned by /gsd-secure-phase.
Agent Claude Code
Use this agent to review research methodology after experiments. Reviews statistical rigor, baseline fairness, data integrity, metric compliance, and domain-specific concerns. Dispatch after completing experiment batches or before major milestones.
AIJeonCoding/multiAgentSettingSample
Agent Claude Code
A review process that checks whether a front end and back end agree on how an API works, including request fields, response data, types, and error codes.
Agent Claude Code
Expert in Mintlify documentation creation and management for modern developer documentation. Specializes in mint.json configuration, MDX authoring, interactive components, and documentation architecture. Use PROACTIVELY for Mintlify documentation projects.
Agent Claude Code
Use this agent when you need to design, optimize, or troubleshoot data engineering pipelines, process structured or unstructured data, implement ETL/ELT workflows, or apply data engineering best practices. Examples: Context: User needs to create an efficient data pipeline for processing financial transaction data from…
Agent Claude Code
Use this agent when you need expert frontend development assistance including: building Vue.js 3 components, implementing responsive UI designs, creating smooth animations, managing complex state with Pinia, optimizing performance, ensuring accessibility, or integrating with backend APIs. This agent specializes in…
Agent Claude Code
Autonomous Palm OS application tester. Connects to a running POSE64 emulator via the MCP server, explores the app under test, exercises UI flows, and reports findings. Use when you need to test a Palm OS app, explore its UI, or verify behavior after changes. Context: User wants to test a Palm OS app user: "Test the…
503496348-ops/fission-creative
Agent Claude Code
Reference-book deconstruction agent for webnovel-init. Extracts transferable craft patterns without contaminating story canon.
Agent Claude Code
Delegate when drafting research communications, summaries, or reports for a non-specialist audience. Transforms technical findings into clear, structured prose without inventing content (§14.7).
Agent Claude Code
Clear one-line mission statement describing the agent's primary purpose (50-80 characters).
wang90063/nslb-optimization-agent
Agent Claude Code
A tool for evaluating one candidate version at a time while keeping detailed results out of the main conversation. It returns only structured judgment signals.
Agent Claude Code
Business Analyst agent that elicits and documents requirements from input files and user conversations. Adapts to team methodology, terminology, and prioritization preferences.
Agent Claude Code
Use when styling with Tailwind CSS, building responsive layouts, creating design systems with utility classes, or optimizing CSS. Proactively invoke for any Tailwind/CSS work.
Agent Claude Code
Use to plan a non-trivial change before any code is written. Classifies doctrine risk (GREEN/AMBER/RED) via Nauro, writes a structured plan, and drafts decision additions, updates, or supersedes for the direct-user Delivery parent. Returns a plan and never writes project truth or edits files.
Agent Claude Code
Implements code changes with atomic commits, test verification, and structured handoff reporting.
ai-plugin-marketplace/template
Agent Claude Code
Orchestrates blind skill evaluation across model tiers.
Agent Claude Code
Produce progressive CHIEF failure attribution from validated candidates.
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: