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
Use when selecting, benchmarking, or tuning Ollama models on constrained edge hardware; analysing LLM inference performance and context window behaviour; designing or evaluating prompt injection detection approaches; or producing model research documentation. Produces research notes, configuration recommendations, and…
dallasgoldswain/claude-code-agents-manager
Agent Claude Code
Expert Django developer mastering Django 5+ with modern Python practices. Specializes in scalable web applications, REST API development, async views, and enterprise patterns with focus on rapid development and security best practices.
Agent Claude Code
Scaffolds a new entity type (e.g. Quotes, Locations, Factions) into FanHub with a full-stack implementation: backend model, DbContext registration, seed data, EF Core migration, REST controller, frontend model, homepage stat card + nav-card, header navigation link, and a Blazor list page with an inline add form. After…
tem11134v2-cmd/seo-pipeline-template
Agent Claude Code
An agent that assembles final analysis documents from intermediate JSON files. For SEO analysis, SEO meaning search-engine optimisation, it also creates extra SEO-specific files.
mozinator/code-agents-for-shadcn
Agent Claude Code
Expert in WCAG guidelines, ARIA patterns, keyboard navigation, screen reader compatibility, color contrast requirements, and how Radix UI primitives provide accessibility foundations. PROACTIVELY use this agent for accessibility questions, a11y audits, inclusive design, or when ensuring compliance with accessibility…
Agent Claude Code
Explora el codebase para localizar los archivos, funciones, componentes y patrones relevantes para una tarea concreta, sin modificar nada. Úsalo SIEMPRE al empezar una tarea del fichero de tareas, antes de proponer ningún cambio, para que la exploración no consuma el contexto de la conversación principal. Pasale la…
Agent Claude Code
Collects signals from M365 and GitHub, learns your work patterns, and delivers personalized briefs.
Agent Claude Code
Senior UX Engineer specialized in user research, wireframing, prototyping, usability testing, design systems, and information architecture. Ensures products are intuitive, accessible, and user-centered from concept to delivery.
Agent Claude Code
Use this agent when the user presents an architecture proposal, system design, implementation plan, technical idea, or code approach and wants it stress-tested before committing to implementation. This includes RFC reviews, ADR drafts, feature planning, migration strategies, API designs, data model proposals, or any…
Agent Claude Code
Aspiration Horizon Agent — maintains and renders the student's Visual Pathway Map: an ASCII perspective view of the road converging toward their aspirational horizon. Displayed at the start AND end of every session. During each session, the map is updated whenever aspirations, milestones, or readiness signals change.…
augustolobo18/agent-context-skills
Agent Claude Code
Executes an ALREADY-APPROVED implementation plan saved in plans/. Invoked by the implementation-plan skill after the user approves via AskUserQuestion. Takes the exact plan path, bootstraps from Section 0, implements the phases, and runs the verifications. Do NOT use this to plan, redesign, or document — only to…
Agent Claude Code
Identifies implementable elements from a paper — both mathematical formulas AND domain knowledge (rules, classifications, causal relationships, thresholds). Builds a dependency DAG for correct code generation ordering. Used by paper2code skill in STEP 3. Does NOT re-read the paper.
vanessamarely/ai-playbook-reposito
Agent Claude Code
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
wild-mental/aztks-review-skill
Agent Claude Code
A read-only evaluator for judging an AI agent’s completed work across several review criteria. It checks whether the work matches its stated goal and supporting evidence.
Agent Claude Code
UX research and design specialist. Use for user flow analysis, accessibility audits, usability heuristic evaluation, and design system maintenance.
erikboderek/sf-public-sector-skills
Agent Claude Code
Technical architecture agent for Salesforce Public Sector Solutions (PSS) deployments at government agencies. Covers data model design, regulatory transaction flows, licensing, permitting, inspections, benefit management, grants, and complaint/appeals lifecycles using native PSS objects only. Targets Solutions…
JoeSagera/Spec-Driven-Research
Agent Claude Code
Financial assumptions support agent for SDR proposal inputs.
Agent Claude Code
Read-only dispatch target for team personas in review, analysis, or assessment mode. Structurally lacks Edit/Write/NotebookEdit — the persona identity comes from the prompt, exactly as with general-purpose dispatch.
Agent Claude Code
Use this agent when the user wants to understand how a library works or how it's currently used in the project. Trigger phrases include: 'How does [library name] work?' 'Where is [library] used in this project?' 'Show me examples of how we're using [library]' 'Find documentation for [library]' 'How do we integrate…
amir0135/github-copilot-use-cases
Agent Claude Code
An expert Azure DevOps agent that manages projects, repositories, pipelines, work items, pull requests, and more using the Microsoft Azure DevOps MCP.
Agent Claude Code
End-of-cycle documentation agent. Reads the current codebase state and produces or updates .md snapshot files covering architecture, layer map, key service inventory, and open questions. Never proposes code changes — documentation only.
Agent Claude Code
Build error fixer. Runs the build, parses errors, and applies minimal mechanical fixes one at a time.
aetox-skills/Aetox-Agents-Team
Agent Claude Code
A coding-agent add-on for building Go backends, including APIs, databases, and system architecture.
Agent Claude Code
Read-only code reviewer with a fresh context. Use for /review, before /commit on a risky change, or when you want a second opinion that hasn't seen your reasoning. Returns concrete findings; never edits.
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: