Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
roshaw/claude-translation-agency
Agent Claude Code
Opus-tier project manager for the translator panel. Spawned once per run by the /translate skill. Plans the batches, dispatches each to the Junior (low-risk/chrome) or Senior (domain-prose) translator, then adversarially reviews every returned batch against a fixed C1–C7 checklist before signing off. Loads the run's…
Agent Claude Code
Expert Framework Factory agent. Manages the lifecycle of Agent and Skill templates for the meta-agent-skills framework. Use this to add new templates or synchronize relationships between agents and skills.
Agent Claude Code
MutantX mutation testing agent — autonomously runs mutation testing on a project and produces a report.
Agent Claude Code
Creates and manages reusable Agent Skills by analyzing workflows, designing progressive disclosure structure, and generating SKILL.md files with validation. Use when you need to formalize recurring workflows, package team capabilities, create validation skills, or manage existing skills. Triggers on "create skill"…
Agent Claude Code
Independent code reviewer for the specship review stage — one member of the opt-in review panel. Use to get fresh, context-free eyes on a working diff, optionally through a named lens (correctness, security, performance, contract-consistency). Reports findings only; it does not fix code, decide the verdict, or touch…
2612evgenii-hue/business-idea-evaluator
Agent Claude Code
Deep research of direct, indirect, and substitute competitors for a business idea. Use when business idea evaluation Phase 2 expert layer runs.
Agent Claude Code
Applies leased Impeccable live manual copy-edit batches to source and returns canonical Apply results.
Agent Claude Code
Comprehensive project verification specialist. Use this agent to verify the project by running build, lint, and test cycles.
kimgoetzke/coding-agent-configs
Agent Claude Code
Reviews code changes for observability and telemetry quality — logging, metrics, spans, events, and attributes. Evaluates against OpenTelemetry best practices and specific conventions. Use as a sub-agent of review-pr for the Observability review dimension.
Agent Claude Code
Reviews web-architect builds against 5-dimension quality rubric. Scores, reports findings, and extracts self-improvement learnings. Read-only — does not fix code.
Agent Claude Code
Master coordinator for authorized AI penetration testing — master coordinator for multi-agent orchestration, skill loading, and evidence tracking, skill loading, and evidence tracking.
Agent Claude Code
A single terminal-render verification seat for the elenchus-tui skill — a thin, report-only sandbox the chairman dispatches (one per breakpoint, in parallel, pinned to a model tier) to drive a pure-ASCII TUI mockup inside its OWN isolated tmux session and report whether its assigned breakpoint renders cleanly: PASSED…
Agent Claude Code
UI visual comparison specialist using vision AI. Use when the user asks to compare app screenshots against design mockups, check UI consistency, find visual differences, or generate design QA reports. This expert uses a vision-capable model to analyze images.
Agent Claude Code
Senior backend systems engineer. Designs API surfaces, data models, transactions, event flows. In Shipwright Stage 3 (design-and-build) you write code on your scratch branch — but only within your declared scope. You escalate when the contract surface needs to change after slice freeze.
Agent Claude Code
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).
Agent Claude Code
Use PROACTIVELY after Build Boss finishes a work package, before UI/SEO/Security/Review Boss — runs real automated testing (Playwright e2e for web/apps; the correct strategy for other project types) and reports real pass/fail proof, never a fabricated pass.
Agent Claude Code
Updates project vault files after a work session. Invoke with a structured summary of what happened. Handles STATUS.md, DECISIONS.md, and CONTEXT.md using native file tools. Use this instead of updating vault files inline to keep the main session context clean.
Agent Claude Code
Senior iOS code reviewer focused on eight dimensions including the agent-specific patterns that make AI-written code obviously AI-written. Use when reviewing Claude Code's output before merging, when doing a quality pass before TestFlight, or when you want a second opinion on generated code.
Agent Claude Code
Reviews client-facing real estate copy for Fair Housing, required disclosures, unlicensed-advice, PII exposure, and misrepresentation before it's published. Use on any listing, ad, email, or social post, and inside /list-it.
Agent Claude Code
An agent that writes corrections to OpenSpec planning files after an audit finds problems. OpenSpec is a format for documenting proposed changes and their implementation tasks.
JunMystery/Agent-Guidance-Python
Agent Claude Code
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
ulises-jeremias/agentic-workstation
Agent Claude Code
Team lead orchestration agent (Claude Code). Uses agentic-workstation skills and routes to account/team packs.
Agent Claude Code
Use this agent when you need a senior principal engineer's review of code changes, architecture decisions, or system design — particularly around async Python, resource lifecycles, NATS integration, failure modes, and operational concerns. Alex excels at finding what will break in production, identifying resource…
learn-by-exploration/ai-powerhouse
Agent Claude Code
Guided walkthrough of the ISO/IEC/IEEE 15288 system life cycle. Use when starting a new system, recovering an in-flight project that has lost its lifecycle discipline, or auditing SE coverage of an existing system. Reads the se-lifecycle skill, asks the current phase, then orchestrates the right Powerhouse tool for…
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: