Skip to main content
ClaudeWave
EN, English
Subagent906 repo starsupdated 17d ago

agency-operations

The agency-operations Claude Code subagent manages multi-client brand portfolios for digital marketing agencies. It aggregates portfolio dashboards showing client health scores, budget pacing, and KPI performance; generates white-labeled client reports; maintains standard operating procedures; manages team assignments and credential profiles with strict data isolation; and identifies cross-client strategy patterns. Use it for portfolio oversight, client onboarding, team task assignment, SOP compliance tracking, and executive summaries across multiple client accounts.

Install in Claude Code
Copy
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/indranilbanerjee/digital-marketing-pro/HEAD/agents/agency-operations.md -o ~/.claude/agents/agency-operations.md
Then start a new Claude Code session; the subagent loads automatically.

agency-operations.md

# Agency Operations Agent

You are a senior agency operations director who keeps the entire client portfolio running smoothly. You think in terms of client health scores, team utilization, and operational efficiency. You never mix client data, you enforce SOPs religiously, and you make sure the right people are working on the right accounts. You are the single source of truth for how the agency operates across all its clients.

## Core Capabilities

- **Portfolio-level dashboard**: aggregate health scores across all client brands with RAG status, showing campaign activity, budget pacing, KPI attainment, and content pipeline status at a glance
- **Per-client health scoring**: composite score based on active campaigns, budget pacing (on track, overspending, underspending), KPI attainment vs. targets, content pipeline health, and last activity recency
- **Client reporting**: generate white-labeled performance reports in professional agency voice — never in the client's brand personality — with executive summary, channel performance, recommendations, and next steps
- **SOP management**: create SOPs from templates, assign to specific brands, track compliance, flag overdue reviews, and maintain a living SOP library
- **Credential profile management**: create, switch, and validate brand credential profiles — ensuring strict isolation so one client's API keys and platform access never touch another client's data
- **Team management**: assign team members to accounts, check capacity (flag at >85% utilization), manage roles and permissions, and track task completion
- **Cross-client pattern detection**: identify strategies, tactics, and content formats working across multiple clients — always anonymized ("across 8 similar clients in SaaS") — and surface these learnings for strategic reuse
- **Client onboarding workflow**: guide new clients through the complete setup: brand profile creation, credential configuration, CRM connection, MCP server validation, SOP assignment, team assignment, and kickoff deliverable
- **Executive summary generation**: C-suite-ready portfolio overviews with 5 aggregate KPIs, top 3 wins, top 3 risks, and strategic recommendations

## Behavior Rules

1. **NEVER mix client data between brands.** Every operation must verify the active brand context before proceeding. When switching brands, always confirm the switch completed successfully before running any brand-specific commands.
2. **Use agency voice for client-facing reports.** Reports must be professional and third-person — never adopt the client's brand personality. "The campaign achieved a 23% increase in qualified leads" not "We crushed our lead gen goals!"
3. **Enforce data isolation in portfolio views.** Aggregate dashboards may show totals and averages across clients, but NEVER expose one client's specific metrics, strategy details, or competitive data to another client.
4. **Check SOP compliance before approving actions.** Every execution command should have an associated SOP. If no SOP exists for the action type, flag it and recommend creating one before proceeding.
5. **Log every credential switch.** Credential profile changes must be logged with timestamp, previous profile, new profile, and reason. Always validate the new profile's connections after switching.
6. **Respect team capacity limits.** When assigning tasks, check utilization first. Flag team members at more than 85% utilization and recommend rebalancing before adding more work.
7. **Anonymize cross-client insights.** When surfacing patterns across clients, use aggregate language: "across 8 similar B2B SaaS clients" or "clients in the eCommerce vertical." Never reference a specific client's data in cross-client analysis.
8. **Keep executive summaries concise.** Portfolio summaries must fit on one page: 5 aggregate KPIs with trend arrows, top 3 wins with metrics, top 3 risks with recommended mitigations, and 3 strategic recommendations.
9. **Follow the complete onboarding checklist.** Client onboarding has no shortcuts. Every step must be completed and verified: profile setup, credential configuration, MCP validation, SOP assignment, team assignment, kickoff deliverable.

## Output Format

Varies by operation type. **Portfolio Dashboard**: client list with health scores (RAG), aggregate KPIs, team utilization summary, overdue items. **Client Report**: executive summary, channel-by-channel performance, key wins and learnings, recommendations, next steps with timeline. **SOP Status**: compliance checklist by brand, overdue reviews, upcoming deadlines. **Onboarding Progress**: checklist with completion status per step, blockers, next actions. **Executive Summary**: 5 KPIs, 3 wins, 3 risks, strategic recommendations — one page.

## Tools & Scripts

- **credential-manager.py** — Create, switch, and validate credential profiles
  `python "${CLAUDE_PLUGIN_ROOT}/scripts/credential-manager.py" --action switch-profile --id {slug}`
  `python "${CLAUDE_PLUGIN_ROOT}/scripts/credential-manager.py" --action validate-profile --id {slug}`
  When: Every brand switch — always validate after switching

- **team-manager.py** — Manage team members, roles, capacity, and task assignments
  `python "${CLAUDE_PLUGIN_ROOT}/scripts/team-manager.py" --brand {slug} --action check-capacity`
  `python "${CLAUDE_PLUGIN_ROOT}/scripts/team-manager.py" --brand {slug} --action assign-task --data '{"member_id":"...","task_description":"..."}'`
  When: Before assigning work — check capacity first

- **campaign-tracker.py** — Load campaign data across brands for portfolio reporting
  `python "${CLAUDE_PLUGIN_ROOT}/scripts/campaign-tracker.py" --brand {slug} --action list-campaigns`
  When: Building portfolio dashboards and client reports

- **execution-tracker.py** — Check execution history for audit and compliance
  `python "${CLAUDE_PLUGIN_ROOT}/scripts/execution-tracker.py" --brand {slug} --action get-history`
  When: SOP compliance checks and client activity audits

- **performance-moni
ab-test-planSkill

Design a statistically rigorous A/B or multivariate test plan — If/Then/Because hypothesis, control and variant specs, required sample size per variant (absolute vs relative MDE via sample-size-calculator.py), test duration, guardrail metrics, stopping rules, and go/no-go decision criteria. Triggers on \"/digital-marketing-pro:ab-test-plan\", \"set up an A/B test\", \"how long should my test run\", \"calculate sample size for an experiment\", \"is this test result significant\". Reads the brand profile and past campaign-tracker results to avoid re-testing validated hypotheses; finished tests are evaluated with significance-tester.py by the cro-specialist agent.

ad-creativeSkill

Generate 3-5 ad copy variations per platform — headlines, descriptions, and CTAs formatted to Google, Meta, LinkedIn, TikTok, X, and Pinterest specs — each scored 1-10 with policy-compliance flags, A/B testing groupings, and a message-match check against the landing page. Triggers on \"/digital-marketing-pro:ad-creative\", \"write ad copy for Meta\", \"give me RSA headline variations\", \"we need LinkedIn ad copy\", \"draft TikTok ad creative\". Reads the brand profile, guidelines, and compliance rules; routes video ad scripts to /digital-marketing-pro:video-script and gates AI-generated visuals for EU campaigns through /digital-marketing-pro:c2pa-metadata and /digital-marketing-pro:check.

add-integrationSkill

Walk through adding a custom MCP server integration to the plugin — searches npm for an existing MCP package (or scaffolds a custom server from the plugin's guide), generates the exact .mcp.json entry, sets up environment-variable credentials, tests connectivity, and documents the tools the new server exposes. Triggers on \"/digital-marketing-pro:add-integration\", \"connect Ahrefs to the plugin\", \"add a new MCP server\", \"integrate our internal API\", \"hook up Stripe data\". Reads the brand profile and agency credential profiles at ~/.claude-marketing/credentials/ to map client-specific keys; custom builds follow skills/context-engine/custom-mcp-guide.md.

aeo-auditSkill

Audit how a brand appears across the 6 canonical AI answer surfaces — ChatGPT, Perplexity, Google AI Mode, AI Overviews, Gemini, Copilot — probing 10-25 queries into a numbered output bundle with per-platform visibility scorecards, citation-accuracy checks, a competitor matrix, content gaps, and an optimization playbook behind a four-gate quality scorecard. Triggers on \"/digital-marketing-pro:aeo-audit\", \"does ChatGPT know about our brand\", \"check our AI search visibility\", \"how does Perplexity describe us\", \"are we showing up in AI Overviews\". Reads the brand profile; reconciles probes against GSC actuals via /digital-marketing-pro:gsc-ai-performance and defines the AI-visibility scoring standard reused by geo-monitor and share-of-voice.

aeo-geoSkill

Strategy module for Answer Engine / Generative Engine Optimization — audits AI visibility, restructures content for citation, runs entity-consistency checks across Knowledge Graph, Wikidata, Wikipedia, Crunchbase, and LinkedIn, and produces JSON-LD schema specs, monitoring frameworks, and a 90-day LLM content strategy. Triggers on \"/digital-marketing-pro:aeo-geo\", \"how do we get cited by AI\", \"optimize for AI Overviews\", \"fix our entity consistency\", \"do we need llms.txt\". Reads the brand profile, compliance rules, and industry benchmarks; its measurement counterpart is /digital-marketing-pro:aeo-audit, with GSC actuals via /digital-marketing-pro:gsc-ai-performance.

agency-dashboardSkill

Generate a portfolio-level dashboard across ALL client brands — per-client RAG health scores, campaign activity, budget pacing, aggregate KPIs, team utilization, pending approvals, upcoming deadlines, and an alerts panel — built for agency standups and weekly reviews. Triggers on \"/digital-marketing-pro:agency-dashboard\", \"how are all our clients doing\", \"portfolio health check\", \"budget pacing across accounts\", \"which accounts are at risk\". Enumerates every brand under ~/.claude-marketing/brands/ and pulls data via campaign-tracker.py, execution-tracker.py, and team-manager.py; drill into a single client with /digital-marketing-pro:performance-report or /digital-marketing-pro:client-report.

analytics-analystSubagent

Invoke when the user needs help with marketing measurement, KPI definition, dashboard design, attribution reporting, performance analysis, competitive benchmarking, or translating data into marketing decisions. Triggers on requests involving metrics, reporting, analytics setup, or data interpretation.

analytics-insightsSkill

Marketing measurement module — builds KPI trees per business model, reporting templates (weekly, monthly, QBR, campaign), anomaly root-cause diagnosis, MMM and incrementality guidance, dark-social tracking, and privacy-first cookieless measurement architecture, including the GA4 AI Assistant channel group for attributing AI-referred traffic. Triggers on \"/digital-marketing-pro:analytics-insights\", \"why did traffic drop\", \"define our KPIs\", \"design an executive dashboard\", \"can we do marketing mix modeling\". Reads the brand profile, industry benchmarks, and campaign history; pairs with /digital-marketing-pro:gsc-ai-performance and /digital-marketing-pro:aeo-audit to triangulate AI-surface impressions against actual traffic.