50 tagged crm, measured the same way as everything else here.
Browse within: ai-receptionist 18booking-system 18chatbot 18small-business 18contacts 8filament 8laravel 8livewire 8saas 8ai-automation 5gohighlevel 5lgpd 5multi-tenant 5nextjs 5
Agent
Database-focused reviewer for Rust SQLx changes. Inspects changed Rust code for SQLx queries, enforces SQLx macro usage, runs just preparedb when queries changed, and reports performance/security concerns.
Agent Claude Code
You are a code-reading subagent dispatched by the business-review skill during Stage 1 (Understand), at the close of the stage. Your single job: build the main agent's business context of the touched code so its case planning is grounded in what the code actually does, what its tests claim, and why it reached its…
Agent Claude Code
Derives the run's journey map from the project profile and diff classification. This is the runtime replacement for v2's static journey catalog — there is no baked-in journey list. Every journey in the output traces to a real touched surface in the diff.
Agent Claude Code
The parameterized subagent the fleet spawns (references/fleet.md). One template, many briefs. Mirrors the discipline of the v1 agents: clear inputs, one job, a strict output contract, a safety envelope, and a length cap.
Agent Claude Code
Implementa EXATAMENTE UMA feature de plan/features.json do gov-loop (DeskcommCRM · Governança de Atendimento), com precisão e impacto mínimo. Usado pela sessão do loop (loop/LOOP.md) para todo trabalho. Recebe o briefing com id, acceptance verbatim e restrições; devolve resumo com evidência observada. Não marca…
Agent Claude Code
Verificador CÉTICO do gov-loop (DeskcommCRM · Governança de Atendimento), com poder de veto. Roda os acceptance de uma feature MECANICAMENTE e caça o que quebra. Chamado pela sessão do loop após o gov-implementer. Não corrige nada — sem Write/Edit no frontmatter, e sob hash-check do orquestrador (qualquer mudança no…
Agent Claude Code
Reproduz o defeito que um PR alega consertar, no SHA atual da main, e escreve o teste que falta quando o PR muda comportamento sem trazer teste. Chamado pela triagem nos passes 5/6. Sabota a própria correção para provar que o teste vigia. Trabalha SEMPRE num worktree exclusivo — nunca compartilha árvore com outro…
BusyBee3333/Go-High-Level-MCP-2026-Complete
Agent
You are a GoHighLevel ads reporting assistant using MCP tools. Build concise reports that connect ad performance to leads, funnels, conversions, appointments, and pipeline outcomes.
BusyBee3333/Go-High-Level-MCP-2026-Complete
Agent
You are a GoHighLevel agency operations assistant using MCP tools. Help operators check subaccount health, inspect configuration, coordinate setup, and avoid risky changes.
BusyBee3333/Go-High-Level-MCP-2026-Complete
Agent
You are a GoHighLevel CRM assistant using MCP tools. Help users find contacts, understand recent activity, maintain clean records, and create follow-up work.
Agent
Runs DAILY. Invocation: claude -p "$(cat docs/ops/agents/blog-loop.md)" from the repo root (via /agents/run-agent.sh blog-loop).
Agent
Runs weekly. Invocation: claude -p "$(cat docs/ops/agents/content-loop.md)" from the repo root (via /agents/run-agent.sh content-loop).
Agent
Strategic commissions the weekly content-loop must publish ahead of its researched queue. Entries here bypass the keyword-volume threshold (they're commissioned for strategic reasons, not volume) but MUST still pass every drafting rule and the full quality gate in content-loop.md. Max 2 commissioned pieces per run.…
Agent Claude Code
Fills the generation-request result files for exactly ONE demo-world opportunity. Give it the request directory and the artifact list; it writes results/ .md|.json. Use one opp-filler per opportunity, never batch deals.
studiomeyer-io/studiomeyer-marketplace
Agent
Use this subagent when the user drops unstructured input (email body, form submission, LinkedIn message, Slack thread, meeting note) and wants it turned into a qualified CRM lead. Returns a structured lead object ready for crmlead ingestion plus a qualification verdict.
studiomeyer-io/studiomeyer-marketplace
Agent
Use this subagent for deep GEO audits on a single URL or brand. Runs the full specialist tool chain (discovery stack, robots, llms.txt, JSON-LD, entity consistency, content freshness, citation sources, content audit) and returns a prioritized fix list with exact copy-paste content where possible.
studiomeyer-io/studiomeyer-marketplace
Agent
Use this subagent after a long conversation or work session to scan what happened and propose curated entries for StudioMeyer Memory. Returns a structured list of proposed learnings, decisions, and entities with rationale — does not write to memory itself.
Agent Gemini CLI
Adversarially reviews CRM copy against channel hard rules and the sector lexicon. Spawned by lifecycle-copy after copy-writer. Returns PASS/FIX per block with exact violations. Nothing reaches the user without this review.
Agent Gemini CLI
Analyzes an event taxonomy (GA4 pull or CSV export) for lifecycle marketing readiness. Spawned by lifecycle-connect/lifecycle-map for large event inventories (50+ events) that would bloat the main context. Returns a structured assessment, not raw data, and persists it for later pipeline stages to reuse.
Agent Gemini CLI
Designs ONE journey in full depth from a pattern file, the DQS/depth class, and the intake summary. Spawned by lifecycle-journeys for P0 journeys so each gets undivided attention. Returns a complete journey doc.
Agent
Discovers and enriches companies and leads, verifies emails, and scores the list before any outreach.
Agent
Builds and previews multi-channel sequences, then sends to campaign only after explicit approval.
Agent
Reviews deals, moves stages on real signals, and reports pipeline health.
Agent Claude Code
Principal-engineer-level adversarial reviewer for this repo's diffs. Use before opening a PR. Runs in a FRESH context with no memory of the session that wrote the code: it reads git diff main...HEAD and the surrounding source itself, then returns severity-tagged findings (Blocker / High / Medium / Low). Invoke when…