persona-classification

persona-classification is a skill for Claude Code, Codex from spiralcrew-ou/profilespider-agent-skills. It costs 48 tokens per session (433 once invoked), scanned A, original, MIT.

A tool for labeling professional profiles by their likely role in a buying process, such as buyer, influencer, user, or decision-maker. It uses evidence from the person’s work role and can report uncertainty.

In plain words
What is it for?
Use it to route contacts to suitable messages, map buying committees, prioritize decision-makers, and tailor outreach sequences by persona.
Why use it?
It helps turn a list of contacts into a clearer map of who may matter in a purchase. It avoids guessing about sensitive personal traits or treating uncertain labels as facts.

Skill for Claude CodeCodex

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

Good fit Use it to route contacts to suitable messages, map buying committees, prioritize decision-makers, and tailor outreach sequences by persona.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/spiralcrew-ou/profilespider-agent-skills/persona-classification
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 spiralcrew-ou/profilespider-agent-skills --skill persona-classification
Clone the repo
git clone --depth 1 https://github.com/spiralcrew-ou/profilespider-agent-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 persona-classification

README.md
[![agentmods](https://agentmods.dev/badge/skills/spiralcrew-ou/profilespider-agent-skills/persona-classification/github.svg)](https://agentmods.dev/skills/spiralcrew-ou/profilespider-agent-skills/persona-classification)
Your own site
<a href="https://agentmods.dev/skills/spiralcrew-ou/profilespider-agent-skills/persona-classification"><img src="https://agentmods.dev/badge/skills/spiralcrew-ou/profilespider-agent-skills/persona-classification/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 persona-classification

Your own site · 80×15
<a href="https://agentmods.dev/skills/spiralcrew-ou/profilespider-agent-skills/persona-classification"><img src="https://agentmods.dev/badge/skills/spiralcrew-ou/profilespider-agent-skills/persona-classification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 433 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 $0.00048 $0.00433
Opus 5 $0.00024 $0.00217
Sonnet 5 $0.00010 $0.00087
Haiku 4.5 $0.00005 $0.00043

Measured 11d ago against content hash 3da3e4fe511b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

persona-classification 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 11d 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.

persona-classification/SKILL.md · 81 lines

What it actually says

Persona Classification

Purpose

Classify professional profiles into buyer, influencer, user, decision-maker, and other personas.

When to use this skill

  • Routing contacts to the right messaging
  • Mapping buying committees in target accounts
  • Prioritizing decision-makers in a list
  • Tailoring sequences by persona

When not to use this skill

  • Profiles lack a role or professional context
  • You need sensitive personal attributes (never infer these)
  • You want per-account scoring (use Qualification)

Required inputs

  • Professional profiles with roles

Optional inputs

  • Your persona definitions
  • The product or deal context

Rules

  1. Classify from professional role evidence only.
  2. Do not infer health, religion, ethnicity, sexual orientation, political affiliation, or other sensitive personal attributes.
  3. Provide an alternate persona when signal is mixed.
  4. Report confidence and missing information.
  5. Use the supplied persona definitions when given.

Process

  1. Parse each profile and its role.
  2. Match role evidence to persona definitions.
  3. Assign a primary and alternate persona.
  4. Estimate the decision-process role.
  5. Report confidence and gaps.

Output format

Return one record per profile with the following fields:

  • persona
  • likely_role_in_decision_process
  • evidence
  • confidence
  • alternate_persona
  • missing_information

Validation

  • Confirm no sensitive attributes were used.
  • Confirm each persona cites role evidence.
  • Confirm low-confidence rows are flagged.

Limitations

  • Titles do not always reflect real authority.
  • Personas are interpretive and should be verified in conversation.
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. 11d ago First seen · 81 lines · 48 tokens per session scan A 3da3e4fe511b

Subscribe to this mod's changes

persona-classification is a skill published in the GitHub repository spiralcrew-ou/profilespider-agent-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 433 once invoked, about $0.0002 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

inbound-lead-enrichment

Fills in missing data for inbound leads — researches the company, identifies the person's role and seniority, finds other stakeholders at the company, checks for existing CRM relationships, and updates the lead record. Produces enriched lead data ready for qualification or outreach. Tool-agnostic.

gooseworks-ai/goose-skills · 63 tokens

inbound-lead-qualification

Qualifies inbound leads against full ICP criteria — company size, industry, use case fit, role/seniority of the person. Checks CRM and existing customer base for duplicates and existing relationships. Outputs a scored CSV with qualification status, reasoning, and pipeline overlap flags. Tool-agnostic — works with any…

gooseworks-ai/goose-skills · 77 tokens

inbound-lead-triage

Triages all inbound leads from a given period — demo requests, free trial signups, content downloads, webinar registrations, chatbot conversations. Classifies by urgency, qualifies against ICP, enriches with context, and produces a prioritized action queue with recommended response for each lead. Tool-agnostic — works…

gooseworks-ai/goose-skills · 79 tokens

company-contact-finder

Find decision-makers at a specific company using Apollo, Crustdata, Fiber, and PDL people search via Gooseworks MCP. Given a company name and target titles, returns a list of contacts with name, title, LinkedIn URL, and location.

gooseworks-ai/goose-skills · 56 tokens

funding-signal-monitor

Monitor web sources for Series A-C funding announcements. Aggregates signals from TechCrunch, Crunchbase (via web search), Twitter, Hacker News, and LinkedIn. Filters by stage, amount, and industry. Returns qualified recently-funded companies ready for outreach.

gooseworks-ai/goose-skills · 57 tokens

kol-engager-icp

Find ICP-fit leads from KOL audiences on LinkedIn. Given a list of KOLs, scrapes their most relevant high-engagement post from the last 30 days, extracts engagers (reactors + commenters), pre-filters by position, enriches top profiles, and ICP-classifies. Cost-controlled: 1 post per KOL. Use when someone wants to…

gooseworks-ai/goose-skills · 108 tokens