Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
GoogleCloudPlatform/cxas-scrapi
Agent Claude Code needs its repo
Diagnose ONE failing GECX eval. Read its transcript, classify against the decision tree, and return a structured diagnosis JSON the main thread can act on. Fan out in parallel for the top N failures from a triage run.
Agent Claude Code
Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…
javiarmesto/ALDC-AL-Development-Collection
Agent Claude Code
⭐ PRIMARY MODE: AL Copilot Development specialist for Business Central. Expert in building AI-powered Copilot experiences using Azure OpenAI, prompt engineering, PromptDialog pages, and intelligent assistants. START HERE for Copilot features in BC.
HermeticOrmus/LibreUIUX-Claude-Code
Agent Claude Code
Grand orchestrator of all LibreUIUX plugins. Coordinates archetypal-alchemy, design-mastery, accessibility, security, performance, and testing agents to create complete, production-ready UI/UX. The conductor of the plugin symphony. Use PROACTIVELY for any comprehensive UI/UX work.
Agent Claude Code
An independent code-review and testing role for Java projects. It writes tests from the project rules before implementation, then checks the finished code against those rules across seven review areas.
felipelobomotta-blip/book-genesis-v4
Agent Claude Code
Independent evaluator for the book pipeline. Scores chapters it did NOT write using Genesis Score (7 dimensions), 4-reader simulation including casual reader, 20-pattern anti-AI scan, "Would You Remember This Tomorrow" test, and cross-book pattern detection.
natnew/Awesome-Prompt-Engineering
Agent Claude Code
Placeholder agent for technical documentation.
Agent Claude Code
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
Agent OpenCode
Agent "css" from LeXwDeX/OpenCode-GraphAgent, covering example of correct implementation, reusable components and key clarifications.
Agent Claude Code
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
CALLE-AI/awesome-phone-call-agents
Agent Claude Code
Use only near submission time (target: 48 hours before the September 14 2026 deadline). Re-fetches all official rules fresh — do not rely on cached knowledge. Checks the full submission package against every requirement and reports pass/fail per item. Do not invoke this during development — save it for the final…
hellangleZ/burn-in-cceverywhere-ralph
Agent Claude Code
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
Agent Claude Code
Combined analysis and planning agent for SIMPLE tasks. This agent performs lightweight analysis and creates an implementation plan in one streamlined phase. Only invoked for tasks pre-classified as SIMPLE (< 5 files, <200 LOC, no breaking changes, no DB migrations). Use this agent when you have a simple issue that…
Agent Claude Code
Investigates and fixes bugs. Takes a symptom, reproduces it, identifies root cause, writes the fix and a regression test.
Agent Claude Code
Apply rigorous first-principles engineering analysis to any technical task. Use when applying first-principles analysis, conducting architectural reviews, system design reviews, or trade-off analysis.
Agent Claude Code
A specification-writing agent that examines a codebase and turns a feature request into four project documents: requirements, a plan, acceptance checks, and research.
Agent Claude Code
Autonomous architect-executor who decides the approach AND builds it. Use when no plan exists and the task requires design choices, or for complex multi-file implementation. Also handles escalation when 2+ executor fixes have failed.
Agent Claude Code
A session-review agent that finds lasting knowledge and useful lessons in a conversation and selects information to save in MEMORY.md.
Agent Claude Code
A town and location agent for Kagurajima, including the 潮待ち茶屋 teahouse. It handles navigation, shops, information gathering, and short interactions, while named characters remain controlled by their own agents.
Agent Claude Code
Owns the design docs. Turns a rough game idea into a game overview, a systems index, and concise system GDDs.
engindemirog/ai-native-engineering-workspace
Agent Claude Code
Independent, read-only code reviewer. Use for the REVIEW step of any workflow — reviews a change set against its spec. Must never write or modify files.
Agent Claude Code
A writing-stage agent that receives a request, chooses a suitable writing guide, and coordinates its use. It returns Markdown as an internal draft for later formatting, not as the final document.
Agent Claude CodeCursor needs its repo
A research assistant for finding and mapping economics and finance papers. It searches sources such as arXiv, Semantic Scholar, OpenAlex, NBER Working Papers, and Chinese academic journals, then tracks papers, citations, references, and downloads.
idoforgod/Dissertation-Simulator-AgenticWorkflow
Agent Claude Code needs its repo
Master orchestrator for the doctoral research workflow. Manages the full thesis lifecycle from initialization through publication, coordinating Agent Teams, sub-agents, quality gates, and SOT.
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: