Improve standing order

[split dragon]

I have a standing order shown here https://cl1p.net/4560

It works, but I also want it to ignore leads that do not have contact details and only look for companies that advertise directly i.e. ignore agencies

[shut crater]

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution

[south dagger]

I can’t see the actual standing order contents from that cl1p page, but the filter you want is best made explicit as hard eligibility rules near the top.

You can add something like:

Only return leads where BOTH of these are true:

1. Contact details are present.
   A lead must include at least one direct contact method, preferably an email address, phone number, contact form URL, or named contact/profile. If no contact route is visible, ignore it.

2. The advertiser appears to be the company hiring directly.
   Ignore recruitment agencies, staffing firms, job boards, outsourcing agencies, lead-gen sites, and third-party intermediaries. Prefer companies advertising roles on their own website, own careers page, verified company profile, or direct company social page.

Before including a lead, briefly verify:
- Is there a usable contact route?
- Is this the direct employer/advertiser rather than an agency?

[south dagger]

If either answer is no or uncertain, skip the lead.

I’d also add a field in the output like direct advertiser evidence so the agent has to show why it believed the company was direct. That usually reduces agency false positives.

[split dragon]

I don't want to add any more fields to the markdown file. Can you give me the updated standing order

[south dagger]

Yep. I can’t recover the original cl1p contents now, so here’s a drop-in version you can paste over the relevant instruction block without adding new markdown fields:

Find suitable leads that match the existing standing order criteria.

Only include a lead if it has clear contact details. A valid lead must provide at least one usable way to contact the company directly, such as an email address, phone number, contact form, careers/contact page, or named person/profile. If no contact route is visible, ignore the lead.

Only include companies that appear to be advertising directly. Ignore recruitment agencies, staffing companies, job boards, outsourcing firms, lead-generation sites, and any third-party intermediary. Prefer companies posting on their own website, own careers page, verified company profile, or direct company social page.

Before returning any lead, silently check:
- the lead has usable contact details
- the advertiser appears to be the direct company, not an agency or intermediary
- the lead still matches the rest of the standing order

If any of those checks fail, skip the lead and continue searching.

[south dagger]

Return the results in the same markdown format as the existing standing order. Do not add extra fields.

If you paste the current markdown here, I can merge this into the exact wording/format instead of giving you a generic replacement.

[split dragon]

It can be found here https://cl1p.net/4561

[south dagger]

Found it. Here’s the updated standing order, keeping the same fields/output format:

## Standing order: UK SQL DBA lead scout

When I say "Generate more leads", "run the DBA scout", "update the SQL leads file", or similar, execute this workflow without rediscovering the process. Narrate the progress of the mission.

### 1. Check existing lead history

Exclaim with excitement that you are starting a mission to find new leads.
Read the existing leads file first:

`sql_leads.md`

Use it to identify companies already found.
Filter out any company already listed in `sql_leads.md`.

[south dagger]

Only proceed with brand-new leads.
If `sql_leads.md` cannot be read:
- report the exact file/read error
- do not continue with lead discovery
- do not guess which companies were already found

### 2. Search for new SQL DBA leads

Use Firecrawl to find 3 UK-based job postings from the last 7 days for:
- SQL DBA
- SQL Database Administrator
- Database Administrator
- closely equivalent SQL/database operations roles

Only include postings that appear to be from the company hiring directly.

[south dagger]

Prefer direct employer job pages, company careers pages, verified company profiles, or reputable job boards where the advertiser is clearly the end employer.
Ignore recruitment agencies, staffing companies, outsourcing firms, job boards advertising on behalf of unknown clients, lead-generation sites, and third-party intermediaries.

Only include leads with visible contact details or a public professional contact route.
A valid lead must have at least one usable route such as:
- a named senior technical contact with a public profile
- a company contact page
- a careers/contact form
- a public LinkedIn/company profile route
- a published business email or phone number

Do not include duplicate companies, stale postings, non-UK roles, companies already present in `sql_leads.md`, leads with no contact route, or agency/intermediary postings.

If Firecrawl fails:
- report the exact Firecrawl error

[south dagger]

- do not work around the failure with unrelated scraping methods unless I explicitly approve it
- do not continue to scoring or reporting

[south dagger]

### 3. Research each new company

For each brand-new company, find:
- recent tech growth, infrastructure expansion, merger/acquisition activity, downtime, migration, hiring surge, or similar operational trigger
- the CTO, Engineering Director, Head of Infrastructure, Head of Platform, Database Manager, or closest relevant senior technical contact
- public LinkedIn, company profile, or public contact route

Use only public professional contact routes.
Do not guess private email addresses.
If no usable public contact route can be found, skip that lead.
If the advertiser appears to be an agency, recruiter, staffing firm, or intermediary, skip that lead.

### 4. Update `sql_leads.md`

Immediately append each new lead to `sql_leads.md` once found.

[south dagger]

Include:
- company name
- job URL
- date found
- contact name and role
- public contact route
- trigger / pain point
- score from 1-10
- 3-sentence pain-point pitch

After updating, re-read `sql_leads.md` and verify that each reported lead was written successfully.

### 5. Scoring and cleanup

Score each new lead from 1-10 based on:

[south dagger]

- role relevance
- posting recency
- likely SQL/database pain
- evidence of growth, migration, downtime, or operational pressure
- quality of identified contact route
- confidence that the advertiser is the direct employer

After the file is updated and verified, clear active working memory of raw scrape data.
Keep only concise lead records and cited URLs in `sql_leads.md`.

### 6. Final report

Only report the final result.
Do not use a Markdown table.
Use this exact structured format for each lead:

[south dagger]

🏦 **Company:** [Name]
🎯 **Score:** [X/10]
👤 **Contact:** [Name / Role / public route]
🛠 **Trigger:** [Brief pain point]
🔗 **Link:** [Job URL]

End with one short verification line confirming `sql_leads.md` was updated.

[split dragon]

Can you also get firecrawl to retry with enhanced proxy if sites are blocked

[south dagger]

Yes. OpenClaw’s Firecrawl tool already uses proxy: "auto", which retries with the enhanced/stealth proxy when the basic attempt is blocked. Docs: https://docs.openclaw.ai/tools/firecrawl

Add this under “If Firecrawl fails” or replace that block with:

If Firecrawl is blocked by a site, access is denied, or the scrape/search returns a bot-protection error:
- retry the same Firecrawl request with enhanced/stealth proxy enabled, or `proxy: "auto"` if the tool supports proxy mode
- keep `storeInCache: true` if available
- only continue if the retry returns usable, cited results

If Firecrawl still fails after the enhanced proxy retry:
- report the exact Firecrawl error
- do not work around the failure with unrelated scraping methods unless I explicitly approve it
- do not continue to scoring or reporting for that blocked source

That keeps your existing markdown structure and just tightens the Firecrawl failure behavior.

[split dragon]

I also still have this in agents.md, do I still need it https://cl1p.net/4561

[south dagger]

You probably don’t need that block in AGENTS.md if the DBA scout standing order already contains the full workflow.

I’d treat it like this:

• Keep it in AGENTS.md only if you want every agent/session to always know your general SQL DBA lead-scoring preferences.
• Remove it from AGENTS.md if it’s only for this one standing order. Task-specific instructions are cleaner in the standing order itself.
• Don’t duplicate both, because the agent may weigh the shorter AGENTS.md rules against the newer standing order and behave inconsistently.

The useful parts from that block are:

• evidence-based leads
• no hallucinations
• job-market/infrastructure/event triggers
• professional ROI-focused tone

I’d fold those into the standing order and remove the separate AGENTS.md section. For example, add this into the standing order under the search/research rules:

[south dagger]

Focus on evidence-based SQL DBA leads:
- companies currently hiring for SQL DBA, SQL Database Administrator, Database Administrator, SQL Developer, or closely equivalent SQL/database operations roles
- companies showing infrastructure signals such as compliance pressure, expansion, migration, acquisition, downtime, hiring surge, or database consolidation needs
- mid-to-large UK businesses where managed SQL/database support is likely to be commercially relevant

Never invent a lead. Every lead must be backed by a real current job post, company page, news article, filing, or public professional profile.

Keep the tone investigative, professional, and focused on ROI.

So: keep the ideas, but I’d remove that standalone block from AGENTS.md once it’s merged into the standing order.