persona

persona is a skill for Claude Code, Codex from VGrss/Acumen. It costs 28 tokens per session (769 once invoked), scanned A, original, Apache-2.0.

A tool for describing users by the behavior patterns they show, based on observed research and feedback rather than demographics such as age or job title.

In plain words
What is it for?
Use it to create or update user personas, review existing personas for stale information, and identify missing behavior patterns.
Why use it?
It helps prevent teams from relying on invented or outdated assumptions about who uses a product and what they need.

Skill for Claude CodeCodex

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 skills/vgrss/acumen/persona
Any agent
npx skills add VGrss/Acumen --skill persona
Clone the repo
git clone --depth 1 https://github.com/VGrss/Acumen

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/vgrss/acumen/persona.svg)](https://agentmods.dev/skills/vgrss/acumen/persona)
Your own site
<a href="https://agentmods.dev/skills/vgrss/acumen/persona"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/persona.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 769 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 $0.00028 $0.00769
Opus 5 $0.00014 $0.00385
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 4d ago against content hash 4c825f06d3d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

persona 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 4d 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.

.agents/skills/persona/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY PREPARATION

Invoke /product-thinking — it contains product principles and the Context Gathering Protocol. Follow the protocol before proceeding — if no product context exists yet, you MUST run /teach-acumen first.


Mindset: A persona is a behavior pattern, not a demographic profile. "Batch-processes weekly reports and breaks when export stalls" is a persona. "Sarah, 32, marketing manager" is not.

Behavior

When called with a specific persona or user segment: Build or update that persona. Ask the user what behaviors they've observed, what triggered this, and what signals they're reading.

When called without argument: Review all personas for staleness and gaps. Flag personas that feel assumed rather than observed. Identify missing behavior patterns.

Research Process

  1. Read .acumen.md for product context — users, job to be done, feedback source, metrics
  2. Read .acumen/personas.md for existing personas
  3. If a feedback source is configured in .acumen.md, ask the user to share recent feedback or pull from the configured source to ground personas in real signals
  4. For each persona (new or updated), build from behavior outward:
    • What job are they hiring the product to do?
    • What's the context when they use it? (time pressure, environment, emotional state)
    • What's their actual behavior pattern? (frequency, workflow, workarounds)
    • What's the pain that drives them to the product?
    • What does success look like for them? (not for you — for them)
    • What triggers them to start a session?
    • What's their value sensitivity? (price, time, reliability, flexibility)
    • What feedback signal would tell you this persona is happy or churning?

Output

Write to .acumen/personas.md:

# Personas

_Last updated: [date]_

## [Persona Name — a behavior, not a demographic]

- **Job**: [What they hire the product to do]
- **Context**: [When, where, under what pressure]
- **Behavior**: [Usage pattern, frequency, workflow]
- **Pain**: [What drove them here, what breaks for them without it]
- **Success**: [What winning looks like from their perspective]
- **Trigger**: [What starts a session — event, schedule, frustration]
- **Value sensitivity**: [What they'd pay for, what they'd leave over]
- **Feedback signal**: [How you'd detect satisfaction or churn for this persona]

## [Next persona...]

## Prioritization
[Which personas matter most right now and why. Not all personas are equal — be explicit about who you're building for first and who you're consciously underserving.]

Read the full file on GitHub · 77 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. 4d ago First seen · 77 lines · 28 tokens per session scan A 4c825f06d3d7

Subscribe to this mod's changes

persona is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 29d ago), licensed Apache-2.0. It adds 28 tokens to every session and 769 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 2026-08-30.