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 Codoop/codoop-flow --skill codoop-ux-walkthroughgit clone --depth 1 https://github.com/Codoop/codoop-flowWrote 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/codoop/codoop-flow/codoop-ux-walkthrough)<a href="https://agentmods.dev/skills/codoop/codoop-flow/codoop-ux-walkthrough"><img src="https://agentmods.dev/badge/skills/codoop/codoop-flow/codoop-ux-walkthrough/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/codoop/codoop-flow/codoop-ux-walkthrough"><img src="https://agentmods.dev/badge/skills/codoop/codoop-flow/codoop-ux-walkthrough.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 | $0.00061 | $0.01421 |
| Opus 5.5 | $0.00024 | $0.00568 |
| Sonnet 5.5 | $0.00012 | $0.00284 |
| Haiku 4.5 | $0.00006 | $0.00142 |
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 28d 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 — 148 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 the session's explicit config, or the Git root's
.codoop-flow/codoop_flow.toml (legacy fallback: root 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.mdand 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:
- 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.
- Task contract — when a ticket exists, read
module_prd.mdfor its user role, goal, scope, and acceptance criteria. Otherwise ask for the task the persona should accomplish and what success means. - Runnable evidence — use the live app, browser, simulator, screenshots, or test output available in the current environment. State what was and was not available.
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.
- 28d ago Changed · +1 lines 3237e4c5010a
- 1mo ago First seen · 147 lines · 61 tokens per session scan A ca9f159d3330
codoop-ux-walkthrough is a skill published in the GitHub repository Codoop/codoop-flow (5 stars, last pushed 28d ago), licensed MIT. It adds 61 tokens to every session and 1,421 once invoked, about $0.0002 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
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…
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…
minimax-m3-multimodal-input
How to use MiniMax M3's native multimodal input (image, video) for grounded decisions in coding work. Covers reading attached images/frames, treating them as ground truth for visual claims, screenshot diffing, design parity from mockups, and routing visual evidence through reports and PRs. Load when the user attaches…
context-menu
Guide for creating and displaying context menus in Wave Terminal. Use when implementing right-click menus, adding context menu items, creating submenus, or handling menu interactions with checkboxes and separators.
design-to-code
Lanhu to Code workflow for Claude Code. Convert Lanhu design URLs into Vue/React frontend code with component reuse, design token mapping, TODO-safe business logic, and optional code review.
code-format
Convert Lanhu HTML/CSS output into project frontend code for Vue, React, or the detected stack, with component reuse and design token mapping.