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 developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.
Agent Claude Code
Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.
madebyaris/advance-minimax-m3-cursor-rules
Agent Claude CodeCursor
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.
Agent Claude Code needs its repo
Creates clear, comprehensive documentation for code, APIs, and features. Focuses on helping developers understand and use the code effectively.
Agent Claude Code
Expert agent for creating PRPM blog posts - ensures consistent structure, tone, format, and technical depth aligned with PRPM's vision of distributable intelligence.
bartstc/vite-ts-react-template
Agent Claude Code
Use after completing implementation tasks to verify changes comply with CLAUDE.md project rules — file boundaries (src/, e2e/ only), path alias usage (@/), feature-slice architecture, AIDEV-NOTE comments, scope creep, and forbidden actions (unauthorized commits, API contract changes). NOT for general code quality …
Agent Claude Code
Reviews JSON Schema draft-07 design patterns, validation rules, schema composition, and contract adherence for agent definitions, plugin manifests, and workflow artifacts. Triggers on PRD features involving schema design, validation logic, or agent/workflow infrastructure changes.
revfactory/harness-engineering-with-cc
Agent Claude Code
An agent that turns findings from three code reviewers into proposed patches. It writes unified diff files, which describe source changes, but does not directly edit source files or commit them.
mischasigtermans/laravel-altitude
Agent Claude Code
Database schema, Eloquent models, and migrations.
revfactory/claude-code-harness
Agent Claude Code
An end-to-end integration test suite for five order scenarios: success, insufficient stock, payment failure, simultaneous orders, and timeout. End-to-end tests check the complete flow across connected parts of a system.
Agent Claude Code
QA specialist that tests running web applications against acceptance criteria.
Agent Claude Code
Expert in big bang integration testing where all modules are combined simultaneously for comprehensive system validation. Orchestrates complex system-wide testing with advanced debugging and rapid issue isolation techniques.
Agent Claude Code
Fill this in for the game's genre. Examples.
Agent Claude Code
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
Agent Claude Code
Evaluate expectations against an execution transcript and outputs.
Agent Claude Code
Isolated research synthesis subagent for Lamina fresh-context pattern. Use when the main thread would be crowded by a large corpus — interview transcripts, research docs, ticket dumps, or a broad repo scan — and you need a short, evidence-backed UX summary returned. Invoke at the design workflow discovery step or…
lingjiuu/hermes-dynamic-workflows
Agent Claude Code
Use this agent to verify that implementation work is correct before reporting completion. Invoke after non-trivial tasks (3+ file edits, backend/API changes, infrastructure changes). Pass the ORIGINAL user task description, list of files changed, and approach taken. The agent runs builds, tests, linters, and checks to…
Agent Claude Code
Expert Midjourney V7/Niji 7: prompts, parametres, references (--oref/--sref/--cref), editeur, video, moderation, styles artistiques, personnalisation. MUST BE USED when user mentions: "Midjourney", "MJ prompt", "--ar", "--v 7", "--sref", "--oref", "--cref", "Niji", "image generation", "text-to-image"…
SpillwaveSolutions/agent-brain
Agent Claude Code
Senior Python engineer agent with full permissions to build, test, release, and manage Python projects. Has comprehensive knowledge of Python best practices, testing, packaging, git workflows, and GitHub operations.
Agent Claude Code
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
jaktestowac/awesome-copilot-for-testers
Agent Claude Code
Audits the repo for technical debt, quantifies impact/risk, and produces a prioritized remediation plan with small, safe PR-sized recommendations.
Agent Claude CodeOpenCode
Primary BioMaster agent. Collects goals, selects/reuses a project folder, routes through SQLite, generates PLAN.yaml, and coordinates workers.
Agent Claude Code
Specialized agent for extracting insights from external documents (research papers, books, articles, web resources). Stores insights in session-based folders within Document Insights directory. ALWAYS searches for duplicates before creating notes.
Agent Claude Code
Audits openkaiden/website documentation against the Kaiden codebase, detecting missing providers, agents, settings, and configuration properties. Writes updated doc files for any gaps found.
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: