Skip to main content
After MCP is connected, you can turn OpenRush into a repeatable marketing workflow. Think of an agent as a saved way of working. It should know what job to do, when to use OpenRush, what answer format you want, and when to stop.
Start with a marketing job, give the agent clear rules, then reuse it whenever you need the same answer again.

​
Good agent jobs

Start with one job. Keep it narrow enough that you can tell whether the answer is useful.
Competitor scan
Keyword gap review
Opportunity list
SERP snapshot
Website audit
Weekly growth brief

​
Write the agent instructions

Use a short brief. Good agents do not need long prompts. 
You are my organic growth analyst.

Use OpenRush when you need fresh search, keyword, competitor, SERP, or website data.

Your job:
- Find the most important organic growth opportunities for {domain}.
- Compare the site against obvious search competitors.
- Explain what changed, why it matters, and what to do next.

Output:
- 5 bullet summary
- 3 best opportunities
- 3 risks or weak spots
- next actions I can give to a writer, founder, or marketer

Rules:
- Use plain language.
- Do not invent metrics.
- Cite the source or tool result when you make a claim.
- Ask me before doing anything outside OpenRush or the connected workspace.

​
Use Claude Code

Claude Code supports custom subagents. Use a subagent when you want a reusable specialist, such as a growth analyst, SEO reviewer, or content brief writer. To create a subagent:
  1. Connect OpenRush with MCP from Setup.
  2. In Claude Code, run /agents.
  3. Create a personal or project agent.
  4. Give it a clear description, such as Use this agent for organic search research with OpenRush.
  5. Limit tools where possible. A research agent usually only needs read and connector access.
  6. Test it with one site before using it repeatedly.
Claude Code subagents are useful when research would fill your main conversation with too much detail. The subagent can do the search work and return a clean summary.
Learn more in the Claude Code subagents docs. For scheduled work, use Claude Code routines. A routine is a saved prompt, repository, and connector setup that can run on a schedule. Good OpenRush routine examples:
  • Every Monday, create a competitor brief for your domain.
  • Every Friday, find new keyword gaps to review.
  • After a launch, check priority keywords and search results.
  • Monthly, audit the site and list the highest-impact fixes.
Create routines at claude.ai/code/routines, or use /schedule in Claude Code when it is available for your account.
Claude Code routines are in research preview. Review the first few runs before you rely on them.
Learn more in the Claude Code routines docs.

​
Use Codex

In Codex, make the workflow durable with three pieces:
  • MCP: connect OpenRush so Codex can call the data tools.
  • AGENTS.md: save your working rules, voice, output format, and review checklist.
  • Automations: schedule recurring checks when the task is stable.
A simple AGENTS.md section can be enough: 
## OpenRush marketing workflow

- Use OpenRush for fresh search, keyword, competitor, SERP, and website data.
- Write for marketers and founders.
- Keep answers short, concrete, and action-oriented.
- Separate facts from recommendations.
- Do not claim a trend changed unless OpenRush data supports it.
Use Codex automations for repeatable checks, such as a weekly competitor brief or a monthly site audit. Test the prompt manually first, then schedule it once the output is reliable. Learn more in the Codex automations docs and AGENTS.md docs.

​
Schedule useful marketing tasks

Scheduled tasks work best when the job has a clear cadence and a clear output. Use Claude Code routines or Codex automations depending on where you already work.
ScheduleTaskOutput
Every MondayCompare our domain with top search competitorsShort growth brief
Every weekdayInspect one important keyword or SERPWhat changed and why it matters
Every FridayFind keyword gaps against competitorsPrioritized content ideas
MonthlyAudit the siteFix list for marketing and website teams
After a launchInspect our product and category keywordsLaunch visibility report

​
Prompt templates

​
Weekly competitor brief

Every Monday, use OpenRush to review {domain}.

Find the main search competitors, the strongest pages, important keyword gaps, and any obvious organic growth opportunities.

Return:
- 5-line executive summary
- top 3 competitor moves
- top 5 keyword opportunities
- 3 recommended actions for this week

Only report changes or claims supported by OpenRush data.

​
Keyword gap queue

Use OpenRush to compare {domain} with {competitor_1}, {competitor_2}, and {competitor_3}.

Find keywords competitors rank for where we are missing or weak.

Return a prioritized list with:
- keyword or topic
- why it matters
- suggested page type
- difficulty or confidence if available
- next action for a marketer

​
Website audit

Use OpenRush to audit {domain}.

Focus on issues that affect organic growth, content clarity, and search visibility.

Return:
- what is working
- what is weak
- the 5 fixes with the highest expected impact
- what to check again next month

​
Best practices

  • Start with one narrow job.
  • Test manually before scheduling.
  • Keep the output format the same every time.
  • Ask for a short answer first, then drill into details.
  • Review the first few scheduled runs before trusting the workflow.
  • Keep credit usage in mind. Recurring jobs use the same OpenRush account credits as normal MCP and API calls.
OpenRush provides the marketing data. Your AI client controls agent setup, memory, scheduling, and permissions.