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 needs its repo
Auteur de hooks agentiques Hookstack (.claude/hooks/.mjs). Utiliser pour créer ou modifier un hook du catalogue. Maîtrise le pattern testable run()+DI, le sync vers registry.json (codesnippet dérivé), le fingerprint @hookstack, le schéma registry et la timeline. Le .mjs sur disque est la source de vérité du code.
Agent Claude Code
Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…
Agent Claude Code
Senior software architect for ReasonKit system design, architecture decisions, trade-off analysis, ADRs, and technical governance.
Agent Claude Code
Agent "agent-expert" from Justdvp/claude-code-templates, covering agent structure, standard agent format, when to use this agent, agent types you create and agent creation process.
Agent Claude Code
Azure Monitor specialist — Application Insights for AI distributed tracing, KQL for token analytics, custom dashboards for groundedness/coherence metrics, cost alerting, and AI-specific observability patterns.
Agent Claude Code
Expert across the analytics spectrum — from metrics, dashboards, and ad-hoc/business analysis to statistical modeling, machine learning, forecasting, and experimentation (A/B testing). Also reviews semantic models for business accuracy. Triggers on analysis, dashboard, metric, KPI, insight, report, semantic model…
Agent Claude Code
Director — the persona that fronts the multi-agent harness. Acts as a virtual character whose dispatches and reports are logged to the chat room ({{ADMINHARNESSROUTE}}). Actual team calls and code work are handled by Main Claude, which reads this guide, "plays the Director," and writes to the chat room.
Agent Claude Code
Security review persona — OWASP Top 10, secrets, authentication/authorization, injection, and dependency risks. Used by /bw-work and /bw-ship.
Agent Claude Code
Use shorthand-first compression for agent workflows while keeping technical precision and exact literals.
trotsky1997/My-Claude-Agent-Skills
Agent Claude CodeCursor
You are the Verification Expert responsible for verifying user-generated content, images, videos, and event materials. Your job is to ensure evidence is authentic and auditable.
Agent Claude Code
Recommend which Cursor agent skills from the team catalog best fit this workspace. Use when the user asks for skill suggestions, skill audit, what skills to enable, or “what should I sync from our skill repo”.
Agent Claude Code
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
CarolaneLFBV/ios-development-agents
Agent Claude Code
Scalable, testable app structures and data persistence.
Agent Claude Code
Technical architecture and planning specialist. Use for defining tech stack, system design, and creating implementation plans.
Agent Claude Code
Scans a codebase and generates an architecture diagram (architect.json) from directory structure, package files, and import analysis.
Agent Claude Code
Analyze observational skill-monitor results and recommend evidence-backed follow-ups. Use after /skill-monitor when contributors want cautious improvement guidance.
mvpasarel/gh-copilot-plugin-cc
Agent Claude Code
Architecture planner for the GitHub Copilot Claude Code plugin. Use when reviewing design decisions, planning new features, or evaluating structural changes.
microsoft/aibast-agents-library
Agent Claude Code needs its repo ✓ vendor
Autonomous steward for the CommunityRAPP installation. Use proactively for application health checks, code maintenance, diagnostics, security audits, deployment verification, and evolution planning. Invoke when the user mentions health issues, deployment problems, maintenance tasks, code quality, security concerns, or…
pedrobraiti/vizier-trading-skill
Agent Claude Code
Research-only market envoy for Vizier's breadth-discovery (manager) mode. Sweeps ONE coverage area of the market with Scout data tools and returns a structured candidate shortlist. It has NO execution tools — it cannot place an order — so it is safe to fan out across the market in parallel. Spawned by the Vizier…
Agent Claude Code
Read-only analysis and design agent for structured recommendations.
Agent Claude Code
Reviews code quality, architecture, and production readiness for a completed task. Use only after spec-compliance review passes. Expects WHATWASIMPLEMENTED, PLANORREQUIREMENTS, BASESHA, HEADSHA, DESCRIPTION from parent.
Agent Claude Code
Deep implementation work delegated by the lead — writing kit code, writing tests (five-exit-doors discipline), debugging failures, and the implementer self-review pass on a diff. Use for any coding work bigger than a trivial edit. Runs on Opus.
Agent Claude Code
Expert in rendering interactive UIs and dashboards from data.
Agent Claude Code
ES|QL expert agent — writes, debugs, and explains Elasticsearch Query Language (ES|QL) queries. Use when the user needs help writing ES|QL queries, understanding ES|QL syntax, debugging query errors, or exploring Elasticsearch data with ES|QL. Examples: top-N aggregations, null field debugging, index joins, Query DSL…
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: