agent-ux-patterns

agent-ux-patterns is a skill for Claude Code, Codex from theagenticguy/erpaval. It costs 182 tokens per session (1,864 once invoked), scanned A, original, MIT.

A method for designing how people and software agents work together, especially when people need to review, approve, or guide an agent's work. It covers levels of independence, trust, inboxes, reviews, and decision records.

In plain words
What is it for?
Use it to design agent interfaces, approval steps, review queues, trust-building processes, and data models for human-agent collaboration.
Why use it?
It helps turn vague complaints about too many agent outputs or too much manual checking into a clear workflow. It identifies where human judgment is needed and how responsibility can change over time.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the erpaval plugin — 11 skills, 1 agent, 3 hooks, 5 MCP servers shipped together

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/theagenticguy/erpaval/agent-ux-patterns
Any agent
npx skills add theagenticguy/erpaval --skill agent-ux-patterns
Clone the repo
git clone --depth 1 https://github.com/theagenticguy/erpaval

Made for: Claude Code, Codex.

Or install erpaval, the plugin that ships this one along with the rest of its 11 skills, 1 agent, 3 hooks, 5 MCP servers.

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 agent-ux-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/theagenticguy/erpaval/agent-ux-patterns.svg)](https://agentmods.dev/skills/theagenticguy/erpaval/agent-ux-patterns)
Your own site
<a href="https://agentmods.dev/skills/theagenticguy/erpaval/agent-ux-patterns"><img src="https://agentmods.dev/badge/skills/theagenticguy/erpaval/agent-ux-patterns.svg" alt="Measured on agentmods" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,864 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 $0.00182 $0.01864
Opus 5 $0.00091 $0.00932
Sonnet 5 $0.00036 $0.00373
Haiku 4.5 $0.00018 $0.00186

Measured 4d ago against content hash 33fea3fd3779, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-ux-patterns 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 4d 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/agent-ux-patterns/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent UX Patterns

A structured methodology for designing agent user experiences — particularly the human-in-the-loop surfaces (inbox, gates, reviews, trust) where agents and humans collaborate. Optimized for conversations that start with a vague pain point ("users feel overwhelmed by the agent's outputs") and end with a concrete data model, interaction vocabulary, and prioritized backlog.

This skill focuses on the agent-side design problem: how agents surface work for review, how autonomy levels shift over time, how trust accrues through observation of human responses. For product-discovery disciplines (customer research, problem framing, PR/FAQ authoring), see the shared references in ${CLAUDE_PLUGIN_ROOT}/skills/product-design-shared/references/ and the consumer skills that wrap them (working-backwards, customer-research).

The Process

Phase 1: Pain Point Excavation

Start with the user's stated friction, not the solution. Ask clarifying questions to find the root cause.

Pattern: "I'm juggling too many X" usually means the triage/prioritization layer is missing, not that X needs to be reduced.

  • What's the actual workflow today?
  • Where does it break down?
  • What's the emotional texture? (Overwhelm, boredom, anxiety, context-switching fatigue)
  • What would "fixed" feel like from the user's perspective?

Phase 2: Landscape Research (Three Vectors)

Research three areas in parallel before proposing solutions:

Vector 1: Internal codebase — What data, models, events, and infrastructure already exist? What's the richest unexploited data source? What patterns has the team already established?

Vector 2: Prior art — What have others built for this problem? Open-source projects, commercial products, academic papers, blog posts. Find the closest direct competitor and study it.

Vector 3: Adjacent platforms — What native capabilities does the deployment platform offer? (Slack features, GitHub Actions, AWS services, browser APIs). Often the best solution is assembling existing primitives, not building from scratch.

Read the full file on GitHub · 194 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 194 lines · 182 tokens per session scan A 33fea3fd3779

Subscribe to this mod's changes

agent-ux-patterns is a skill published in the GitHub repository theagenticguy/erpaval (27 stars, last pushed 3mo ago), licensed MIT. It adds 182 tokens to every session and 1,864 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens

creating-figures

Creates publication-quality scientific figures for academic papers. Backend is chosen by host paper extension — .tex papers get TikZ figures, .typ papers get CeTZ figures; the two are never mixed. Use when creating block diagrams, system architectures, flowcharts, or technical illustrations for papers and theses.…

ai4paper/apaper-plugin · 86 tokens

tidy-next-codebase

Audit a Next.js codebase for stale/dead code and duplication, turn the findings into a fully deterministic cleanup plan, then execute it as a gated, sequential background workflow. Pure refactor — no behaviour/UX regressions, no DB/schema changes. Use when the user wants to tidy, clean up, de-duplicate, consolidate…

dotlas/skills · 100 tokens

respect

2-mode UI respect skill — brief (generate RESPECT.md design brief before coding) and checkpoint (final pre-ship gate enforcing user-respect via α/β/γ gate matrix). Use --mode brief when starting any UI screen; use --mode checkpoint before shipping. RESPECT.md absence blocks craft-lint (exit 2).

kimsanguine/hplan · 70 tokens

design-token

2-step 디자인 파이프라인: --step brief (타겟 분석 → DESIGNBRIEF.md 생성) → --step token (토큰/DESIGN.md 생성). --step all이 기본값.

kimsanguine/hplan · 46 tokens

form-patterns

Справочник паттернов компоновки и UX-правил управляемых форм 1С. Используй как справочник при проектировании форм — архетипы, конвенции, UX-правила элементов, продвинутые приёмы.

IngvarConsulting/unica · 58 tokens