search-strategy

search-strategy is a skill for Claude Code, Codex from Ken-Technology/cold-email-skills. It costs 93 tokens per session (1,886 once invoked), scanned A, original, MIT.

A skill that turns an ideal customer profile, or ICP—the description of the companies and people a campaign wants to reach—into search filters. The filters can be used in prospecting tools such as Apollo, Sales Navigator, Clay, ZoomInfo, LinkedIn, or a manually built list.

In plain words
What is it for?
Use it when deciding who to target for a cold-email campaign. It helps define job roles, seniority, company type, industry, size, business model, intent signals, and exclusions.
Why use it?
It creates reusable targeting guidance without tying the campaign to one prospecting provider. It also prevents the system from inventing a target audience when key information is missing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when deciding who to target for a cold-email campaign. It helps define job roles, seniority, company type, industry, size, business model, intent signals, and exclusions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ken-technology/cold-email-skills/search-strategy
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.

Any agent
npx skills add Ken-Technology/cold-email-skills --skill search-strategy
Clone the repo
git clone --depth 1 https://github.com/Ken-Technology/cold-email-skills

Made for: Claude Code, Codex.

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 search-strategy

README.md
[![agentmods](https://agentmods.dev/badge/skills/ken-technology/cold-email-skills/search-strategy/github.svg)](https://agentmods.dev/skills/ken-technology/cold-email-skills/search-strategy)
Your own site
<a href="https://agentmods.dev/skills/ken-technology/cold-email-skills/search-strategy"><img src="https://agentmods.dev/badge/skills/ken-technology/cold-email-skills/search-strategy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for search-strategy

Your own site · 80×15
<a href="https://agentmods.dev/skills/ken-technology/cold-email-skills/search-strategy"><img src="https://agentmods.dev/badge/skills/ken-technology/cold-email-skills/search-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00093 $0.01886
Opus 5 $0.00046 $0.00943
Sonnet 5 $0.00019 $0.00377
Haiku 4.5 $0.00009 $0.00189

Measured 10d ago against content hash 02b3b5cb6f12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

search-strategy 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 10d 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.

search-strategy/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Strategy Skill

Purpose

Turn an ideal customer profile into portable prospect-search filters the user can run in any list tool (Apollo, Sales Navigator, Clay, ZoomInfo, LinkedIn, or a hand-built list). Do not bind the work to a single vendor. Write the result to search-strategy.md so the rest of the campaign workflow has a clear, reusable targeting brief.

Inputs

  1. Read research.md from the campaign workspace when it exists. Pull ICP details, buyer roles, company attributes, competitors, and any named example prospects.
  2. Read the offer / ICP from plan.md or the user's brief when present (who you sell to, what you sell, and the problem the offer solves).
  3. If either is missing, ask the user for:
    • Target role (title or function + seniority)
    • Company type (industry, size, and business model)
    • The problem the offer solves (used to choose intent signals and exclusions)

Do not invent an ICP. Prefer short clarifying questions over guessing.

Define filters

Work through every category below. For each, pick concrete values tied to the ICP and keep 1-2 examples in mind as calibration. Use a checklist and fill only the categories that apply; leave a category blank rather than force a weak filter.

  • Job titles and seniority
    • Prefer a short primary title list plus seniority when the role is clear.
    • Examples: VP Marketing, Head of Growth; seniority Director, VP, C-level.
  • Departments / functions
    • Use function when titles vary a lot across companies.
    • Examples: Marketing, Revenue Operations, Engineering.
  • Industries / verticals
    • Name the verticals that actually buy; avoid overly broad buckets unless volume is too low.
    • Examples: B2B SaaS, healthcare software, commercial real estate.
  • Company size (headcount bands) and revenue bands
    • Pick headcount and/or revenue ranges that match buying power and sales motion.
    • Examples: headcount 51-200, 201-500; revenue $10M-$50M.
  • Geography
    • Person location and/or company HQ, depending on how the offer is sold.
    • Examples: United States, United Kingdom, DACH, remote-US only.
  • Technographics (tools they use)
    • Include stack signals only when they change fit or the pitch.
    • Examples: uses Salesforce, uses HubSpot, runs on AWS.
  • Intent / timing signals
    • Hire, funding, launches, expansion, and similar triggers that make outreach timely.
    • Examples: hiring for SDRs, raised Series A/B in last 12 months, opened a new market.
  • Keywords (positive)
    • Phrase or profile keywords that pull the right people in when title alone is weak.
    • Examples: "demand gen", "plg", "outbound".
  • Exclusions (negative filters)
    • Competitors, current customers, agencies-as-end-customers, wrong business models, and other bad-fit segments.
    • Examples: exclude competitor brands; exclude consulting / agency when selling to product companies; exclude companies already on the customer list.

Read the full file on GitHub · 154 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. 10d ago First seen · 154 lines · 93 tokens per session scan A 02b3b5cb6f12

Subscribe to this mod's changes

search-strategy is a skill published in the GitHub repository Ken-Technology/cold-email-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 93 tokens to every session and 1,886 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

outbound-strategy

Build your own in-house cold email / outbound infrastructure instead of renting Smartlead, Instantly or Lemlist. Use when someone wants to set up self-hosted cold outreach: connecting their own SMTP/IMAP inboxes, sourcing and segmenting B2B leads, writing multi-step sequences, sending at scale with deliverability-safe…

gquthier/autonomous-cold-email · 144 tokens

cold-email-onboarding

First-run interactive setup for the cold-email skill pack. Walks the operator through brand-config.json (ICP, PSP, EVP, tone, infrastructure) and SOUL.md (voice fingerprints, banned phrases, stories you lean on) in 10 minutes. Refuses to let the operator skip — generic output is worse than no output. Loaded…

cmj-hub/claude-cold-email · 91 tokens

cold-email-kickoff

Adaptive router for the cold-email skill pack. Detects the operator's current state (brand-config present? SOUL.md present? infrastructure ready? PSP defined? EVP locked? first campaign run?) and picks the next-best step. Loaded by the main cold-email skill on bare invocation ("/cold-email") or when the operator asks…

cmj-hub/claude-cold-email · 99 tokens

cold-email-list-quality

Score a cold-email prospect list 0-100 across dedup, role-fit (vs brand-config.icp), signal freshness, email-validity heuristics, exclusion-criteria match, and company-stage match. Returns the score, list of rows to remove, and a fix recommendation. Loaded by cold-email-weekly-rhythm on Monday's list refresh. Operates…

cmj-hub/claude-cold-email · 88 tokens

cold-email-reply-scoring

Classify replies to cold email into 4 categories — buy-signal, positive, neutral, not-interested — using deterministic features (intent keywords, time-to-reply, length, question count, calendar/asset asks). Routes each reply per brand-config.operations.replyrouting. Backed by a Python script that uses regex + features…

cmj-hub/claude-cold-email · 94 tokens

cold-email-weekly-rhythm

Operational cadence playbook for the cold-email program. Defines what happens on Monday (PSP signals + list refresh), Wednesday (sequence ship + reply triage), Friday (reply scoring + adjust). Surfaces this week's queue, drift signals, and the metric review against last week. Inspired by coldoutboundskills'…

cmj-hub/claude-cold-email · 92 tokens