experience-baseline

experience-baseline is a skill for Claude Code from handarbeit/fabrik. It costs 132 tokens per session (5,232 once invoked), scanned A, original, Apache-2.0.

A guided project-planning add-on that interviews the product owner, technical architect, and experience lead, then records their decisions as buildable specifications.

In plain words
What is it for?
Use it to define project goals, feature requirements, technical architecture, and user experience rules before development begins.
Why use it?
It helps teams turn business goals, technical constraints, and user needs into one shared set of documents instead of leaving important decisions scattered across conversations.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Document**: [../experience.md](../experience.md).

Part of the entwurf plugin — 6 skills shipped together

Good fit Use it to define project goals, feature requirements, technical architecture, and user experience rules before development begins.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/handarbeit/fabrik
agentmods
npx agentmods add skills/handarbeit/fabrik/experience-baseline

Made for: Claude Code.

Or install entwurf, the plugin that ships this one along with the rest of its 6 skills.

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 experience-baseline

README.md
[![agentmods](https://agentmods.dev/badge/skills/handarbeit/fabrik/experience-baseline.svg)](https://agentmods.dev/skills/handarbeit/fabrik/experience-baseline)
Your own site
<a href="https://agentmods.dev/skills/handarbeit/fabrik/experience-baseline"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/experience-baseline.svg" alt="Measured on agentmods" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,232 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00132 $0.05232
Opus 5 $0.00066 $0.02616
Sonnet 5 $0.00026 $0.01046
Haiku 4.5 $0.00013 $0.00523

Measured 8d ago against content hash 6fc933eba91e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

experience-baseline 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.

plugin/entwurf/skills/experience-baseline/SKILL.md · 437 lines

How it starts

The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experience Baseline

Decide once, for the whole product, what someone sees and what they can be asked to do — so that eleven features do not become eleven products.

Read ../../CONVENTIONS.md first. It carries the shared rules — stages, where work is saved, the tree, markers, interview rules, precedence, gates, decision records and the baseline status footer. This skill does not repeat them.

This is stage 4 of 5. What you produce is the input the architecture baseline needs.

Why this tier carries the weight

A component defined for one feature is reused by six others; a state defined once applies everywhere; a word chosen here appears on forty screens.

Note the honest limit: the per-feature experience document this is meant to be inherited by does not exist yet (see the tree in ../../CONVENTIONS.md). Today this baseline is consumed by stage 5 and by whoever builds. Say that rather than promising an assembly step nobody has built.

Text is what gets built from

The output of design work is visual. The thing that builds this product reads files.

Text is authoritative for behaviour; the design file is authoritative for appearance.

Where the two meet — a state's signal is appearance that carries behaviour — record the distinguishing dimension and its floor, not the rendering:

"Sync state is distinguished by icon plus word, never colour alone. Legible at arm's length in poor light. Survives a screen reader and translation."

That is implementable, it is a real design decision, and it leaves the rendering to the file. "Saved offline is signalled" is not a decision.

What this is not

Not per-feature flows. Not visual design — no colour values, type scales or spacing systems. If the lead volunteers them as binding, record a pinned reference to the design file rather than transcribing them.

Before starting

Establish the project root as ../../CONVENTIONS.md describes.

If there are no specs, say so and stop. This skill's entire method is derivation from them, and an experience baseline invented from a blank page is the failure this method exists to prevent. If there are specs but no constitution, carry on, say so, and record the absence in the document.

Read the full file on GitHub · 437 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. 8d ago First seen · 437 lines · 132 tokens per session scan A 6fc933eba91e

Subscribe to this mod's changes

experience-baseline is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed today), licensed Apache-2.0. It adds 132 tokens to every session and 5,232 once invoked, about $0.0007 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.