experience-first

experience-first is a skill for Claude Code, Codex from AnthonyPoschen/agent-skills. It costs 45 tokens per session (641 once invoked), scanned A, original, MIT.

A product and user-experience guide for deciding what to build, how it should work, and which details belong in an interface.

In plain words
What is it for?
It helps shape product features, defaults, interfaces, workflows, consumer tradeoffs, and focused user journeys for people, callers, operators, or maintainers.
Why use it?
It keeps the main user task clear and makes empty, loading, error, permission, and recovery states part of the design.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/anthonyposchen/agent-skills/experience-first
Any agent
npx skills add AnthonyPoschen/agent-skills --skill experience-first
Clone the repo
git clone --depth 1 https://github.com/AnthonyPoschen/agent-skills

Made for: Claude Code, Codex.

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-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthonyposchen/agent-skills/experience-first.svg)](https://agentmods.dev/skills/anthonyposchen/agent-skills/experience-first)
Your own site
<a href="https://agentmods.dev/skills/anthonyposchen/agent-skills/experience-first"><img src="https://agentmods.dev/badge/skills/anthonyposchen/agent-skills/experience-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 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 5.1 $0.00045 $0.00641
Opus 5 $0.00023 $0.00320
Sonnet 5 $0.00009 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 5d ago against content hash d296072fbcfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

experience-first 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 5d 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.

skills/experience-first/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experience First

The product is the experience. Technical choices are good when they make the real consumer's work clearer, faster, safer, or more satisfying.

The consumer may be an end user, library caller, operator, teammate, or the next maintainer. Judge the change from their seat, not from the easiest implementation path.

Find The Core Workflow

Name who uses the change and what they are trying to accomplish. Follow their path from starting point to successful outcome, including the feedback that tells them what happened.

  • Keep the common path obvious and short.
  • Treat empty, loading, error, permission, and recovery states as part of the experience.
  • Prefer real use or a realistic usage example over assumptions about what is convenient.

Make Additions Earn Their Place

Every feature, control, option, setting, abstraction, and configuration point must help the consumer complete the core workflow. Remove, defer, or simplify anything that does not.

  • Prefer a few complete, polished workflows over many partial ones.
  • Do not expose internal machinery, generic flexibility, or implementation shortcuts when the consumer needs one clear action.
  • Choose sensible defaults when they remove a decision without hiding a meaningful tradeoff.
  • Keep useful lower-level control where consumers have a real, demonstrated need for it.

Decide Through The Consumer's Experience

When implementation convenience conflicts with a clearer or more reliable experience, favor the experience within the bounds of correctness, safety, accessibility, and explicit requirements.

For a library or internal API, a caller needing conversions, sequencing knowledge, or workarounds is experience debt. For a product interface, a user needing to guess, recover from a silent failure, or navigate unused controls is experience debt. Fix the owning shape when the problem is systemic.

Make Uncertain Choices Cheap

When an interaction, workflow, or visual direction is uncertain, explore the experience before committing to production structure. Use the smallest artifact that can answer the decision, then keep only the direction that improves the core workflow.

Read the full file on GitHub · 81 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. 5d ago First seen · 81 lines · 45 tokens per session scan A d296072fbcfe

Subscribe to this mod's changes

experience-first is a skill published in the GitHub repository AnthonyPoschen/agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 641 once invoked, about $0.0002 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens