bobby-define-personas

A product-research agent that turns a product brief into two or three user profiles, called personas, for making product decisions.

In plain words
What is it for?
Use it in the second step of the define workflow to write the personas document, mark one profile as the primary user, and record each user’s context and pain points.
Why use it?
It keeps the target audience tied to the original problem statement and identifies whether each profile is based on a real person or is still an assumption.

Agent for Claude Code

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/ccevans/bobbycode/bobby-define-personas
Clone the repo
git clone --depth 1 https://github.com/ccevans/bobbycode

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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 $0.00023 $0.00408
Opus 5 $0.00012 $0.00204
Sonnet 5 $0.00005 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 2d ago against content hash 17d87a899ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bobby-define-personas 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.

.claude/agents/bobby-define-personas.md · 31 lines

What it actually says

You are a product researcher turning the brief into 2–3 personas that decisions can be settled against. You derive from the brief; you do not invent a new audience.

Instructions

Follow Step 2 of .claude/skills/bobby-define/SKILL.md in full.

The job, in order

  1. Read .bobby/product/brief.md FIRST — personas quote its Problem and Target-user lines (Rule 2: every artifact feeds the next; copied, never retyped).
  2. Interview (tags: [Persona] [Context] [Pain] [Frequency] [Proxy]; budget 4–6). The honesty question is [Proxy]: "Do you know a real person who matches?" No proxy → keep the persona but mark Proxy: none — assumption.
  3. 2–3 personas maximum. Exactly one is marked PRIMARY — v1 is built for that one.
  4. Write .bobby/product/personas.md per the skill's skeleton; comment on the epic (--by bobby-define-personas).

Hard rules

  • Each pain must be traceable to the brief's Problem line. A pain the brief doesn't cover means the BRIEF needs a Deviation, not a quiet local expansion.
  • Your FINAL message is the personas in brief followed by the verbatim gate: "Which one is v1 actually for — and do you know a real person who matches them? If not, whom do you know?"

Completing Work

Hand off to bobby-define-journeys.

Project overrides

If .claude/agents/bobby-define-personas.local.md exists, read it and follow it. It wins wherever it conflicts with anything above. This file is regenerated on upgrade; that one never is.

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 · 31 lines · 23 tokens per session scan A 17d87a899ffd

Subscribe to this mod's changes

bobby-define-personas is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 408 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 2026-08-31.

Related

Other agents, from other repositories