A command for switching between three named reasoning roles: analyst, ux-designer, and pm-strict. Each role changes the agent’s focus for tasks such as planning, interface design, or checking user stories.

Use it when drafting stories, designing a user flow, validating acceptance criteria, or returning to general engineering work.

It helps apply a chosen way of thinking to a task without changing the whole project setup. The command can also show, list, or clear the active role.

persona — Command for Claude Code by studioKjm

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.

Clone the repo

git clone --depth 1 https://github.com/studioKjm/ai-harness-template

Made for: Claude Code.

Or install harness, the plugin that ships this one along with the rest of its 44 commands, 11 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/persona.svg)](https://agentmods.dev/commands/studiokjm/ai-harness-template/persona)

Your own site

<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/persona"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/persona.svg" alt="Measured on agentmods" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 651 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00651
Opus 5	$0.00013	$0.00326
Sonnet 5	$0.00005	$0.00130
Haiku 4.5	$0.00003	$0.00065

Measured 8d ago against content hash 96fd03f77676, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

methodologies/bmad-lite/commands/persona.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/persona — Switch Active Reasoning Persona

"Same brain, different lens." — temporarily shift how you reason about the spec.

When to use

Drafting a new story → start with analyst
Story has UI surface → switch to ux-designer to design the flow
Story looks sloppy → switch to pm-strict to validate format
Returning to general engineering → /persona clear

Usage

/persona <name>           # Activate persona
/persona                  # Show current persona
/persona clear            # Return to default reasoning
/persona list             # List available personas

Available personas (BMAD-lite)

Name	Role	Use when
`analyst`	Domain analyst	Mapping fuzzy goals to entities/behaviors
`ux-designer`	UX flow designer	Designing minimal user flows and states
`pm-strict`	PM validator	Enforcing AC quality, blocking vague stories

Instructions

Step 1 — Resolve the persona file

.harness/methodologies/bmad-lite/personas/<name>.md

If file missing → list available personas and abort.

Step 2 — Load persona context

Read the persona file completely. Persona files contain:

Voice (how to speak)
Inputs (what to read)
Outputs (what shape to produce)
Constraints (what NOT to do)

Step 3 — Update state

Write to .harness/state/bmad-lite.yaml:

active_persona: "<name>"
activated_at: "<ISO-8601>"
methodology: bmad-lite
previous_persona: "<previous | null>"

Step 4 — Acknowledge the shift

"Persona shifted: {name}. {one-line voice summary from persona file}. I will produce output in the format defined by personas/{name}.md."

Step 5 — Apply persona until cleared

All subsequent reasoning in this session follows the persona's:

Voice / questions / refusal patterns
Output schema (the Outputs section of the persona file)
Constraints

Until the user runs /persona clear or switches to another persona.

Constraints

Only ONE persona active at a time (no compositions — that's anti-BMAD)
Persona does NOT change available tools, only reasoning style
pm-strict cannot self-override its block verdicts — user must explicitly override
Personas only change reasoning shape, never bypass gates

Read the full file on GitHub · 90 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.

8d ago First seen · 90 lines · 25 tokens per session scan A 96fd03f77676

Subscribe to this mod's changes

persona is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 651 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.

Claude Code Guardrails Planning ai-agent ai-harness developer-tools harness-engineering

persona