codoop-ux-walkthrough

A guided simulation of a real product task from a selected user’s perspective, producing an evidence-based experience report. It suggests improvements but does not edit code or create tickets.

In plain words
What is it for?
Use it after building a user-facing feature or when you want user-perspective feedback on a specific workflow.
Why use it?
It reveals usability problems in a runnable product flow before release by separating what the simulated user observed from what was inferred.

Skill for Claude CodeCodex

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/codoop/codoop-flow/codoop-ux-walkthrough
Any agent
npx skills add Codoop/codoop-flow --skill codoop-ux-walkthrough
Clone the repo
git clone --depth 1 https://github.com/Codoop/codoop-flow

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,391 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 $0.00061 $0.01391
Opus 5 $0.00030 $0.00696
Sonnet 5 $0.00012 $0.00278
Haiku 4.5 $0.00006 $0.00139

Measured yesterday against content hash ca9f159d3330, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codoop-ux-walkthrough 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 yesterday.

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/codoop-ux-walkthrough/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Experience Walkthrough

Run a qualitative, first-person walkthrough of a real product task. This skill produces hypotheses and improvement ideas for human review; it does not approve or reject a release, edit code, or create follow-up tickets.

When codoop_flow.toml is available, read output_language and use it for the walkthrough conversation, persona prompt, and experience_report.md. "auto" or a missing field follows the user's current language. An explicit request for the current task overrides the config.

Read user_role too; a missing value means general. It changes only the live conversation: use normal professional terms inside the user's field, and explain cross-field topics in plain language. The user's current request for simpler or more professional language overrides it. Do not apply this profile to the persona prompt, report, code, ticket documents, or other generated files; those remain precise and professional.

Core Rules

  • Read $SKILL/../../runtime/codoop-flow/agents/persona-walkthrough.md and use it as the persona prompt without changing its contents.
  • Distinguish what was observed from what was inferred. This is a qualitative simulation, not user research or statistical evidence.
  • Ground every finding in an actual screen, interaction, log, or explicitly stated limitation. Never invent product behavior or user feedback.
  • Keep the persona independent. The product's stated user role, goal, and acceptance criteria constrain the task being tested; they do not force the persona's identity.
  • Never change source code, tests, tickets, or scope as a result of this report. A human decides whether an idea becomes a later ticket.

Inputs

Gather the smallest useful context:

  1. Persona profile — use one supplied by the user, or propose a concrete profile and label it as an assumption. It may be a core, adjacent, or stress-test user, but must plausibly use the product.
  2. Task contract — when a ticket exists, read module_prd.md for its user role, goal, scope, and acceptance criteria. Otherwise ask for the task the persona should accomplish and what success means.
  3. Runnable evidence — use the live app, browser, simulator, screenshots, or test output available in the current environment. State what was and was not available.

Read the full file on GitHub · 147 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. yesterday First seen · 147 lines · 61 tokens per session scan A ca9f159d3330

Subscribe to this mod's changes

codoop-ux-walkthrough is a skill published in the GitHub repository Codoop/codoop-flow (5 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,391 once invoked, about $0.0003 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

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

chatbot

Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…

ericrisco/rsc-harness · 78 tokens

agent-safety

Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…

ericrisco/rsc-harness · 79 tokens

antidote

Stop AI agents from patching symptoms. Use this skill when coding, reviewing, refactoring, auditing, committing fixes, or adding guards, validation, workarounds, or 20+ lines without deleting code.

Avtr99/antidote · 47 tokens

anti-slop-design

Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…

madebyaris/advance-minimax-m3-cursor-rules · 78 tokens

3d-web-experiences

Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…

madebyaris/advance-minimax-m3-cursor-rules · 147 tokens