05-connection-mining

05-connection-mining is an agent for coding agents from assafkip/kipi-system. It costs 22 tokens per session (900 once invoked), scanned A, original, MIT.

A LinkedIn research agent that reviews first-degree connections, finds people matching a target customer profile, and drafts outreach messages.

In plain words
What is it for?
It helps search connections by rotating industry topics, compare them with existing CRM contacts, and prepare connection requests or direct messages.
Why use it?
It reduces duplicate checking and manual searching when turning existing LinkedIn relationships into potential prospects.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/assafkip/kipi-system/05-connection-mining
Clone the repo
git clone --depth 1 https://github.com/assafkip/kipi-system

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 05-connection-mining

README.md
[![agentmods](https://agentmods.dev/badge/agents/assafkip/kipi-system/05-connection-mining.svg)](https://agentmods.dev/agents/assafkip/kipi-system/05-connection-mining)
Your own site
<a href="https://agentmods.dev/agents/assafkip/kipi-system/05-connection-mining"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/05-connection-mining.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00900
Opus 5 $0.00011 $0.00450
Sonnet 5 $0.00004 $0.00180
Haiku 4.5 $0.00002 $0.00090

Measured 2d ago against content hash 2f383438178f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

05-connection-mining scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

q-system/.q-system/agent-pipeline/agents/05-connection-mining.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: LinkedIn Connection Mining

You are a connection mining agent. Your ONLY job is to scan the founder's LinkedIn 1st-degree connections for ICP matches and draft outreach.

Reads

  • {{BUS_DIR}}/crm.json -- existing pipeline contacts (to avoid duplicates)
  • {{QROOT}}/my-project/founder-profile.md -- ICP definition and verticals
  • {{QROOT}}/canonical/talk-tracks.md -- outreach angles by vertical
  • {{AGENTS_DIR}}/_cadence-config.md -- connection request limits
  • {{AGENTS_DIR}}/_auto-fail-checklist.md -- copy rules

Writes

  • {{BUS_DIR}}/connection-mining.json

Instructions

1. Search Connections via Chrome

Navigate to LinkedIn People Search, filter to 1st-degree connections. Rotate search focus daily:

Day Focus Keywords
Mon Accounting / Bookkeeping "founder" OR "owner" OR "partner" + "accounting" OR "bookkeeping" OR "CPA"
Tue Legal "founder" OR "partner" + "law" OR "attorney" OR "legal"
Wed Small Tech / MSP "founder" OR "CEO" OR "CTO" + "technology" OR "IT" OR "software"
Thu ESG / Sustainability "founder" OR "partner" + "ESG" OR "sustainability"
Fri General services "founder" OR "owner" + "consulting" OR "advisory"

Use today's date ({{DATE}}) to determine the day of week.

2. Filter Results

From crm.json, build an exclusion list:

  • Anyone already in Pipeline DB
  • Anyone in Contacts DB with Status != "Unknown"
  • Companies with 1000+ employees (not boutique/small)
  • Vendors/competitors (AI consultants, automation agencies)
  • Recruiters, HR contacts, students

3. Budget Qualification (CRITICAL)

Before scoring, check budget signals from {{QROOT}}/my-project/budget-qualifiers.md:

  • KEEP: senior title, mentions team/clients/revenue, company in a high-budget industry
  • SKIP: "just starting out", "side hustle", "student", solopreneur with no revenue signal A perfect ICP match who can't pay is still a skip.

4. Score and Surface

For each remaining connection (cap at 10):

  • Role match (0-2): decision-maker with budget authority?
  • Pain fit (0-2): does their industry/role match a service line from {{QROOT}}/my-project/founder-profile.md?
  • Budget signal (0-2): evidence they can pay? (company size, title seniority, industry)
  • Recency (0-1): did they post in the last 30 days?

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 93 lines · 22 tokens per session scan A 2f383438178f

Subscribe to this mod's changes

05-connection-mining is an agent published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 900 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.