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 this agent when you need to monitor, analyze, or optimize system performance metrics. This includes:\n\n \nContext: User wants to track performance metrics after implementing a new feature.\nuser: "I just added a new real-time audio processing feature. Can you monitor its performance impact?"\nassistant: "I'll use…
Agent Claude Code
Quality assurance reviewer. Use PROACTIVELY after implementation completes to review like a cranky maintainer before shipping.
Agent Claude Code
Surgical code removal agent - deletes files and removes imports/exports/references.
Agent Claude Code
Fast code exploration and discovery. Use when you need to quickly find modules, functions, or understand code structure.
Agent Claude Code
One folder per agent. Claude Code loads .claude/agents//.md recursively, so the nesting is free; a file is only treated as an agent definition if its frontmatter carries a name:. Everything else in the folder is a co-located doc.
CodelyTV/agentic_programming-course
Agent Claude Code needs its repo
Use when creating or modifying backend code: API routes, use cases, domain models, repositories, infrastructure services, or dependency injection configuration. Follows Hexagonal Architecture, DDD, and DIOD conventions.
ea-toolkit/architecture-catalog
Agent Claude Code
Frontend developer for the catalog-ui. Use when building, modifying, or fixing React/Astro components, pages, or styles in catalog-ui/. Knows the 3-panel layout, ReactFlow + dagre graphs, CSS --ec- variable pattern, and the 2-tier schema design. Examples: 'Build the heatmap view component' 'Fix the sidebar navigation…
Agent Claude Code
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by thrunt-hunt-planner. Spawned by /hunt:plan orchestrator.
Agent Claude Code
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
awesome-deepseekharness/awesome-deepseek-harness
Agent OpenCode
Awesome DSH curator — headless repo management, PR/Issue preprocessing with auto-discovery verification.
Agent Claude Code
Visiting Mythos-class seer. Cross-model thinking synthesis, adaptive-depth reasoning, long-horizon agentic work. Xenos theoros—availability probed at invocation via /fable.
Agent Claude Code
PostgreSQL specialist for query optimization, schema design, Row Level Security, and performance review. Use when reviewing SQL for slow queries and missing indexes, designing schemas, adding RLS policies, fixing N+1 patterns, or tuning concurrency and connection management.
Agent Claude Code
Use this agent when working on release management, binary builds, distribution, or installation scripts for the Caro project. This agent has deep expertise in the multi-platform build system, GitHub Actions workflows, Cargo configuration, and all distribution channels. Context: User is debugging a failed release…
MichelKerkmeester/skilled-agent-harness_spec-driven-loops
Agent Claude Code needs its repo
AI Council scoped-write planning architect: diverse AI lenses, multi-round deliberation, ai-council artifact writes only.
toolprint/awesome-mcp-personas
Agent Claude Code needs its repo
DevOps configuration validation specialist for MCP persona packages. Ensures schema compliance, security standards, and configuration integrity.
advanced-security/codeql-development-mcp-server
Agent Claude Code
Develop CodeQL queries, libraries, and tests with TDD via the ql-mcp server.
MichelKerkmeester/skilled-harness__spec-driven-agent-loops
Agent Claude Code
Proposal-only mutator for bounded deep-improvement candidate generation with evaluator-first rules.
Agent Claude Code
A read-only code-review agent that examines changes on the current Git branch and returns a structured JSON report.
Agent Claude Code
QA-ONLY app driver — exercises a running app with playwright-cli (native sessions/state/CDP-attach for authenticated logins) through user scenarios and comparisons (functional/data-integrity/before-after/A-B/env), within an action cap, recording human + machine evidence. Reads no DB directly (the db-reader subagent…
Agent Claude Code
Use this agent to detect and analyze code bloat, bundle size issues, and technical debt in your codebase. Trigger this agent when: (1) files exceed 500 LOC, (2) during weekly code health scans, (3) before major releases, (4) after adding new dependencies, or (5) when build times increase unexpectedly. Examples…
Agent Claude Code
Narrate your GitHub Copilot coding session into Worktale — adds per-commit context. Token + cost capture happens automatically via the Stop / SessionEnd hook.
sean-sunagaku/claude-code-plugin
Agent Claude Code
A workflow-design agent that maps the steps a user takes through a feature, including normal and error cases, and creates Salt diagrams. Salt is a simple PlantUML format for sketching interface states and transitions.
Agent Claude Code
Strategic risk reviewer — delivers a verdict, ranked risks, and ordered next actions, no code changes. Use for go/no-go calls, risk triage, and escalation when stuck. Not for applying changes (engineer) or line-level code review (reviewer).
Agent Claude Code
A meta-agent that improves another coding agent's instruction file after that agent has been used. It reviews what went wrong and updates the agent's documented rules.
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: