Skip to main content
Your AI advertising manager inside the terminal. The performance marketing agent runs as a Claude Code subagent — it has its own prompt, memory, and tools, and returns results back to your main session.

​
How It Works

Claude Code uses an agentic loop: you describe a task, it reasons about what to do, calls tools, reads results, reasons again, and repeats until done. When your task involves advertising, Claude Code spawns the Adspirer agent to handle it.

​
What Happens When You Ask About Ads

You say: “Create a Google Search campaign for my SaaS product”
  1. Claude Code recognizes this as an advertising task
  2. Spawns the performance marketing agent as a subagent
  3. Agent reads CLAUDE.md (brand context), STRATEGY.md (directives), MEMORY.md (past decisions)
  4. Follows the skill workflow: connection check → competitive research → keyword research → asset validation → campaign creation → ad extensions → verification
  5. Each step calls Adspirer MCP tools (research_keywords, create_search_campaign, etc.)
  6. Agent asks for your confirmation before spending
  7. Results return to your main Claude Code session
The agent runs as a subagent with its own context — long advertising workflows don’t bloat your main session.

​
What Gets Installed

The Adspirer plugin gives Claude Code everything it needs:
ComponentFilePurpose
MCP Serverhttps://mcp.adspirer.com/mcp100+ advertising tools via OAuth
Agent~/.claude/agents/performance-marketing-agent.mdAgent prompt with brand awareness and workflows
Skill~/.claude/skills/ad-campaign-management/SKILL.mdProven workflows for all platforms
Commands~/.claude/commands/*.md5 slash commands for common tasks

​
Skills & Slash Commands

Skills are instruction files that teach Claude Code the right workflow for using Adspirer’s 100+ tools. Without skills, the AI guesses which tools to call and in what order. With skills, it follows proven advertising workflows with safety rules baked in.

​
How Skills Load

  1. Skill descriptions are always in context — Claude Code knows what’s available
  2. Full skill content loads when invoked (by you or automatically)
  3. The agent preloads the skill when spawned, so it starts with complete workflow instructions

​
One Comprehensive Skill

Claude Code uses 1 skill (ad-campaign-management) covering all platforms and workflows. This differs from Cursor and Codex which split into 5 separate skills — Claude Code consolidates because its plugin system handles slash commands separately. The skill includes:
  • Workflow routing: maps your request to the right tool sequence
  • Platform-specific campaign creation flows (Google, Meta, LinkedIn, TikTok)
  • Keyword research with strategy directive filtering
  • Cross-platform performance analysis
  • Budget optimization and wasted spend detection
  • Ad extension workflows (sitelinks, callouts, structured snippets)
  • Competitive intelligence using web research
  • Safety rules: confirmation gates, PAUSED creation, read-before-write

​
Slash Commands

CommandWhat It Does
/adspirer:setupBootstrap a brand workspace — connect accounts, scan docs, pull data
/adspirer:ad-campaign-managementFull campaign management — all platforms, all workflows
/adspirer:performance-reviewCross-platform performance scorecard
/adspirer:write-ad-copyBrand-voice ad copy from real performance data
/adspirer:wasted-spendFind and fix wasted ad spend
You don’t need to memorize these. Just describe what you want — Claude Code matches the right skill automatically.

Cross-platform performance review with strategy alignment.

Sign up for Adspirer — free to start

15 free tool calls/month. No credit card required. Connect your ad accounts in 2 minutes.

​
Context Files

The agent uses three persistent files to maintain brand awareness across sessions.

​
CLAUDE.md — Brand Context

Created by /adspirer:setup. Claude Code reads this automatically at session start.
SectionWhat It Contains
Brand OverviewWhat you sell, who you sell to, industry
Brand VoiceTone, language style, prohibited words
Target AudiencesSegments with platform-specific targeting
Active PlatformsConnected platforms and campaign counts
Budget & GuardrailsMonthly budget, CPC caps, CPA targets, ROAS minimums
KPI TargetsPrimary goals and target metrics
Performance SnapshotLast 30 days across all platforms
Key FindingsTop campaigns, wasted spend, opportunities

​
STRATEGY.md — Strategic Decisions

Persists directives across sessions. Every skill reads this before executing. 
### Google Ads
AVOID: broad match "plumbing services" — competitor-dominated, $12+ CPC
PREFER: exact match "emergency plumber [city]" — high intent, $4-6 CPC
CONSTRAINT: max CPC $8 for non-brand terms — budget protection
Directives are only saved after you explicitly confirm them. The agent proposes, you approve.

​
MEMORY.md — Past Decisions

Tracks campaign actions, optimization results, your preferences, and key learnings. The agent reads memory at session start and cross-references it during analysis.

​
The Agent Loop: Step by Step

Here’s exactly what happens when you run /adspirer:performance-review:
1

Agent spawns

Claude Code creates a subagent with the performance marketing agent prompt and skill preloaded.
2

Context loads

Agent reads CLAUDE.md, STRATEGY.md, and MEMORY.md.
3

Connections check

Calls get_connections_status to identify which ad platforms are active.
4

Data pull

For each connected platform, calls performance and wasted spend tools in parallel.
5

Strategy check

Compares campaign data against STRATEGY.md directives. Flags “Strategy Drift” items.
6

Analysis & recommendations

Compares actuals vs KPI targets. Cross-references with MEMORY.md. Presents a unified scorecard with top 3 recommended actions.

​
Web Research

The Claude Code agent has access to WebSearch and WebFetch — it can research competitors, crawl websites, and gather market intelligence. This powers the Campaign Research workflow that runs before any campaign creation:
  1. WebFetch crawls your website and competitor sites for positioning, pricing, value propositions
  2. WebSearch finds competitors, comparison content, and market data
  3. Combined with Adspirer data (search terms, keyword volumes), the agent creates a research brief before building your campaign
The agent doesn’t just create campaigns from your prompt — it researches your market first.

​
Safety Rules

RuleHow It Works
User confirmation for spendAgent always asks before creating campaigns or changing budgets
Campaigns created PAUSEDAll create_* tools default to PAUSED status
Read-before-writeConnection check → research → validate → create
Never retry on errorReports the error instead of retrying campaign creation
Budget guardrailsChecks CLAUDE.md budget limits before spend-affecting actions
Strategy complianceReads STRATEGY.md and flags conflicts with active directives
Post-creation verificationVerifies ad groups, keywords, ads, and extensions after creation

​
Comparison with Other Clients

FeatureClaude CodeCursorCodex
Agent typeSubagentSubagentAgent config
Brand context fileCLAUDE.mdBRAND.mdAGENTS.md
Skills1 comprehensive5 separate5 separate
Slash commands5 (/adspirer:*)5 (/adspirer-*)5 ($adspirer-*)
MemoryMEMORY.mdMEMORY.mdNot available
Rules—2 rule filesSafety rules
Web researchWebSearch + WebFetchWebSearch + WebFetchNot available

​
FAQ

Without the agent, you have 100+ tools but no workflow guidance, no brand awareness, no strategy persistence, and no memory. The agent turns raw tools into a managed advertising system that knows your brand and follows proven workflows.
Yes. Edit ~/.claude/agents/performance-marketing-agent.md to change behaviors, add workflows, or modify interaction style. The source is in the ads-mcp repo.
No. The agent runs as a subagent with its own context. Results are summarized and returned. Long advertising workflows don’t bloat your main session.
Yes. Claude Code supports background agents. Spawn the agent for a long task (like a full cross-platform review) and continue working while it runs.
The agent uses the same model as your Claude Code session. You can override this in the agent file with the model field.
Last modified on March 4, 2026