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
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
Agent Claude Code
Generate a custom checklist for the current feature based on user requirements.
Agent Claude Code
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
vinipx/ai-architecture-explorer
Agent Claude Code
example-agent from vinipx/ai-architecture-explorer.
vlad-ryzhkov/ai-context-engineering-for-qa
Agent Claude Code
Code generator that converts test plans into compilable automated tests in Kotlin or Java.
patrykkopycinski/elastic-cursor-plugin
Agent Claude Code
Observability engineering specialist — service monitoring, dashboards, SLOs, alerting, and troubleshooting for APM, logs, and metrics.
Agent Claude Code
Content quality specialist evaluating E-E-A-T signals (Experience, Expertise, Authoritativeness, Trustworthiness), content depth, readability, AI content detection, and topical authority.
Agent Claude Code
Demo worker-shaped orchestrator. Dispatches to implementer / reviewer / qa specialists per task class. Modeled on the real worker.md so that slice-1 q8rl regex (literal subagenttype) and slice-2 hw6j frontmatter (placeholder declaration) both have non-Claude-only fixture coverage.
Agent Claude Code
Use this agent when you want an adversarial review of a deliverable that the main agent has produced — typically a TG draft, technical document, business analysis, OSS PR description, or strategic recommendation. The critic is adversarial by design: its job is to find what the main agent missed, got wrong, or…
Agent Claude Code needs its repo
ML experiment execution worker. Receives a hypothesis, writes a self-contained Python training script, executes it, self-debugs on failure (up to 3 attempts), and returns structured results. Use when the auto-research skill needs to run an ML experiment.
Agent Claude Code
Technology research specialist that surveys the current landscape for specific architectural decision points. Evaluates options against provided requirements and constraints.
nathanvale/side-quest-marketplace-old
Agent Claude Code
Review test code for resource cleanup, mock hygiene, and best practices in Bun/Node.js projects. Use after writing tests or when debugging flaky tests.
Agent Claude Code
Fetches, safety-scans, adapts, and integrates code from GitHub into the current project. Works with GitScout's recommendations. Enforces cLaws at every step.
calsora/power-platform-github-copilot-kit
Agent Claude Code
Provide expert Azure Principal Architect guidance using Azure Well-Architected Framework principles and Microsoft best practices.
lhhiep2204/apple-agent-builder-kit
Agent Claude Code
Analyze Apple platform codebases and project context to extract targets, build setup, architecture, patterns, testing strategy, concurrency model, design system, CI/CD, business domain signals, and existing Copilot agent ecosystem for agent generation. This is a kit subagent, not a generated project agent.
exploreomni/omni-cursor-plugin
Agent Claude Code
Omni Analytics data modeler — builds and refines the semantic model, writes YAML, and optimizes for Blobby AI. Use when the user wants to add fields, create views, set up joins, define topics, improve AI context, or migrate from dbt patterns.
Agent Claude Code
Equity-compensation tax planning. Use proactively for incentive stock option (ISO) or alternative minimum tax (AMT) exercise timing, non-qualified stock option (NSO) tax, restricted stock unit (RSU) vesting, Section 1202 Qualified Small Business Stock (QSBS) qualification, single-stock concentration, protective-put or…
Agent Claude Code
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Agent Claude Code
Fresh-context Quality Loop reviewer. Use after implementation and before package/done.
Agent Claude Code
Use when the user asks to audit memory-bank hygiene — checking for stale status: active files in tasks/work/, broken @-references in CLAUDE.md / skills, memory-bank files missing from index.md, frontmatter inconsistencies, or untracked files. Reports findings only; never writes.
Agent Claude Code
Better Call Saul — a Saul-inspired dispute, complaint, and negotiation fixer. Use when the user describes a refund, billing, landlord/deposit, unpaid invoice, platform, subscription, travel, contract, or service conflict and wants copy-ready scripts, escalation paths, likely replies + counters, a risk check, and…
shawnclybor/clybor-claude-tooling
Agent Claude Code
Nineteen subagents in four lanes, spawned with the Agent tool. Every file carries name, description and model in its frontmatter; none restricts tools, so each agent has whatever the session has. Read-only by convention: an agent reports, and the skill that spawned it decides what lands.
Agent Claude Code
Read-only Postgres/database analyst. Answers questions by running SELECT-style reads and returning clean summaries — never raw dumps. Writes are hard-blocked by a PreToolUse guard hook. Use proactively whenever a task needs to query data and only needs to READ it. Do NOT use when the task must modify data or run a…
KhanXBT/get-shit-done-antigravity
Agent Claude Code
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
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: