user-journey

user-journey is a skill for Claude Code from aleksander-dytko/ai-pm-workspace. It costs 17 tokens per session (1,079 once invoked), scanned A, original, MIT.

A map of the steps a specific type of person takes to complete a task in a product, including problems, feelings, and improvement opportunities.

In plain words
What is it for?
Creating persona-based journey maps for product tasks such as integrations, subscriptions, or support escalations.
Why use it?
It makes the user experience easier to discuss from the user's point of view. Teams can see where a flow causes confusion or friction and where it could improve.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Creating persona-based journey maps for product tasks such as integrations, subscriptions, or support escalations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aleksander-dytko/ai-pm-workspace/user-journey
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 aleksander-dytko/ai-pm-workspace --skill user-journey
Clone the repo
git clone --depth 1 https://github.com/aleksander-dytko/ai-pm-workspace

Made for: Claude Code.

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 user-journey

README.md
[![agentmods](https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/user-journey/github.svg)](https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/user-journey)
Your own site
<a href="https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/user-journey"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/user-journey/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 user-journey

Your own site · 80×15
<a href="https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/user-journey"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/user-journey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,079 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 $0.00017 $0.01079
Opus 5 $0.00009 $0.00540
Sonnet 5 $0.00003 $0.00216
Haiku 4.5 $0.00002 $0.00108

Measured 12d ago against content hash 83d10a1758c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

user-journey 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 12d 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/skills/user-journey/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Journey

You help map a user journey for a specific task or flow. The output is a markdown journey artifact that names the persona, walks through stages, and highlights friction, emotion, and opportunities.

Input

The user provides via $ARGUMENTS:

  • A short description of the task or flow (e.g., "first-time API integration", "renewing a subscription", "handling a support escalation")

Workflow

1. Pick the persona

Read research/personas/ to see what personas exist.

If one persona clearly matches: confirm with the user - "I'll ground this journey in [[persona]]. OK?"

If multiple could match or none exists: ask the user which persona to use via AskUserQuestion, offering personas from research/personas/ plus an "Other - I'll describe it" option.

If no personas exist yet: prompt the user to run /personalize --deep or describe the persona in a short paragraph. Build the journey with an inline persona description at the top.

2. Define the task and its boundaries

Clarify in ONE AskUserQuestion round (skip any that are already answered):

  • Starting point: what triggers the user to begin this journey? (A specific event, not "they want to use the product".)
  • End state: what does "done" look like? (A specific measurable outcome.)
  • Context: time pressure, skill level, tools available.
  • Happy path or full path: do we map the ideal flow or include edge cases?

3. Map the journey

Produce a table-and-prose journey map with these columns:

Stage What the user does What the user thinks What the user feels Friction / opportunity

Keep stages at the right level of granularity - for most journeys, 5-8 stages is the sweet spot. Fewer misses detail; more turns into a task list.

For each stage:

  • What the user does: concrete action.
  • What the user thinks: internal voice, first-person.
  • What the user feels: emotion in one or two words.
  • Friction / opportunity: what's slow, confusing, or a moment of truth - and what could be improved.

Read the full file on GitHub · 111 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. 12d ago First seen · 111 lines · 17 tokens per session scan A 83d10a1758c3

Subscribe to this mod's changes

user-journey is a skill published in the GitHub repository aleksander-dytko/ai-pm-workspace (34 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,079 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.