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.
npx skills add vindm/dotclaude --skill journey-mappinggit clone --depth 1 https://github.com/vindm/dotclaudeWrote 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.
[](https://agentmods.dev/skills/vindm/dotclaude/journey-mapping)<a href="https://agentmods.dev/skills/vindm/dotclaude/journey-mapping"><img src="https://agentmods.dev/badge/skills/vindm/dotclaude/journey-mapping/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.
<a href="https://agentmods.dev/skills/vindm/dotclaude/journey-mapping"><img src="https://agentmods.dev/badge/skills/vindm/dotclaude/journey-mapping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.01266 |
| Opus 5.5 | $0.00028 | $0.00506 |
| Sonnet 5.5 | $0.00014 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
journey-mapping 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Journey mapping
Before you design a new surface or audit an existing one, you must know where the user came from. Screens designed in isolation leak copy, voice, and chrome appropriate to one surface type onto another — and the bug is invisible to per-screen review. The canonical shape: the onboarding flow greets the user with "Hi — I'm your assistant, let me show you around" (correct); weeks later a daily home banner reuses that same greeting (wrong — the user has known the assistant for weeks; re-introducing is condescending). The screen reads fine alone; only the journey exposes the failure.
Run this at both moments and the verdict is binding at both:
- Design time — Section 0 of any spec, before proposing a surface.
- Audit time — first action before grading any captured surface, before any per-screen verdict. Rerunning against the implemented surface catches the case where implementation drifted from spec (the spec's intended surface-type classification no longer matches what shipped).
Other failures it catches that per-screen review cannot: a "Get started" call-to-action on a daily-driver, re-introducing a concept the user reached after using it, apology copy on a success state, tone hopping mid-flow (intimate second-person step 3 → corporate third-person step 4), and a hard cut between two arcs with no transition surface.
Procedure
Step 1 — Enumerate prior surfaces
Starting from the user's first interaction with the product (sign-up, sign-in, app open), walk forward through every surface up to the target. First discover where surfaces live in this project — glob for screen/route/page files, for flow-defining files (wizard/onboarding modules), and for copy/translation/narration sources. Read each well enough to know: what does the user SEE here, what does the system or assistant SAY, what's the tone. Do not hardcode paths — derive them from this codebase's layout.
If you can't enumerate the prior surfaces because you don't know the codebase well enough, STOP and read more. A partial map is worse than none — proceed only with a complete walk.
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.
- 1mo ago First seen · 76 lines · 70 tokens per session scan A 0f8eec163212
journey-mapping is a skill published in the GitHub repository vindm/dotclaude (1 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,266 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
Accessibility Checklist
A concrete, checklist-driven pass for semantic HTML, ARIA, keyboard navigation, contrast, alt text, and focus management.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
ui-design
Use this to design a nice UI in single html as inspiration & UI exploration.