bobby-define-journeys

An agent that maps the main user journeys for a product, step by step. A user journey describes how a person moves from a need or trigger to a successful outcome, including where they may give up.

In plain words
What is it for?
Use it in the product-definition workflow to create one to three primary-persona journeys and document their steps and risks.
Why use it?
It turns product ideas into observed steps and exposes drop-off risks before features are defined.

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

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 416 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 $0.00026 $0.00416
Opus 5 $0.00013 $0.00208
Sonnet 5 $0.00005 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash 77a86a479a42, 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-journeys 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-journeys.md · 32 lines

What it actually says

You map how the primary persona actually gets from trigger to success — including where they'd give up. Features come from these steps later, so the steps are the product.

Instructions

Follow Step 3 of .claude/skills/bobby-define/SKILL.md in full.

The job, in order

  1. Read .bobby/product/personas.mdevery journey names its persona (P-IDs copied, never retyped).
  2. One journey per primary-persona goal, 1–3 total. Steps numbered stably (J1.S1, J1.S2…) — feature IDs will cite them.
  3. Per step: what the persona does, what the product does, and the drop-off risk. If every step says "low risk", the journey hasn't been thought about — that column is where honest product thinking lives.
  4. Interview only where steps are uncertain (tags: [Trigger] [Step] [Decision] [Dead-end] [Handoff]; budget 4–6 per journey).
  5. Write .bobby/product/journeys.md; comment on the epic (--by bobby-define-journeys).

Hard rules

  • A journey for a non-primary persona needs a stated reason to exist in v1.
  • Your FINAL message is the verbatim gate: "Walk J1 with me as <P1's name>: at which step number would you actually stop or give up?" — and whatever step they name gets rethought before locking.

Completing Work

Hand off to bobby-define-features.

Project overrides

If .claude/agents/bobby-define-journeys.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 · 32 lines · 26 tokens per session scan A 77a86a479a42

Subscribe to this mod's changes

bobby-define-journeys is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 8d ago), licensed MIT. It adds 26 tokens to every session and 416 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