mindit-context

mindit-context is a skill for Claude Code, Codex from Dragoon0x/usemindit. It costs 115 tokens per session (1,213 once invoked), scanned A, original, MIT.

A design review that examines who uses a product, when and where they use it, and what state it is in.

In plain words
What is it for?
Use it to assess mobile layouts, onboarding, empty and error states, slow connections, returning users, accessibility contexts, and other edge cases.
Why use it?
It exposes gaps that appear outside the ideal case, such as on phones, during loading, with no data, offline, or after an error.

Skill for Claude CodeCodex

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

Good fit Use it to assess mobile layouts, onboarding, empty and error states, slow connections, returning users, accessibility contexts, and other edge cases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dragoon0x/usemindit/mindit-context
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.

Any agent
npx skills add Dragoon0x/usemindit --skill mindit-context
Clone the repo
git clone --depth 1 https://github.com/Dragoon0x/usemindit

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 mindit-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/dragoon0x/usemindit/mindit-context/github.svg)](https://agentmods.dev/skills/dragoon0x/usemindit/mindit-context)
Your own site
<a href="https://agentmods.dev/skills/dragoon0x/usemindit/mindit-context"><img src="https://agentmods.dev/badge/skills/dragoon0x/usemindit/mindit-context/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.

agentmods 80×15 button for mindit-context

Your own site · 80×15
<a href="https://agentmods.dev/skills/dragoon0x/usemindit/mindit-context"><img src="https://agentmods.dev/badge/skills/dragoon0x/usemindit/mindit-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,213 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.
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 $0.00115 $0.01213
Opus 5.5 $0.00046 $0.00485
Sonnet 5.5 $0.00023 $0.00243
Haiku 4.5 $0.00012 $0.00121

Measured 2mo ago against content hash 171433b9f0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mindit-context 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 2mo 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/mindit-context/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.

mindit-context

The fifth of the eight forces. Run this when the question is "who, when, where, in what state."

The force

Designs are usually shown in one state: the happy path, the desktop viewport, the freshly-onboarded user, the populated screen, the fast network. Real users never see that screen. They see the screen with no data, with a network error, on a phone in sunlight, on their fourth visit when they have forgotten how the product works, when they are tired, when they are trying to recover from a mistake.

Context asks: of all the states this screen will exist in, how many has the design accounted for?

When to run this

  • The user shows only desktop mocks and the product is shipped on mobile too.
  • The user mentions empty, loading, error, or offline states.
  • The user mentions a persona, a user segment, or a specific use environment (one-handed mobile, dark mode, slow network, screen reader, kiosk).
  • The user uses words like "what happens when," "edge case," "fallback," "first-time," "returning user."
  • The user asks about onboarding, recovery flows, or recovery from mistakes.

How to analyze

  1. Map the contexts. List every dimension that matters for this design:

    • Audience: who, with what familiarity, with what motivation.
    • Device and viewport: phones, tablets, desktops, larger; portrait/landscape.
    • State: loading, empty, populated, error, partial, offline, slow, stale, locked, expired.
    • Journey position: first visit, returning, mid-flow, post-completion, recovery.
    • Environment: bright sun, noisy, mobile data, screen reader, voice assistant.
  2. Identify which contexts the design has addressed. Compare the design against the list. Each context that has not been addressed is a finding.

  3. Distinguish "not addressed" from "explicitly out of scope." Some contexts are intentionally not supported (e.g. tablet not a priority). That is a different finding than "we forgot mobile exists."

  4. Score the criteria below.

Read the full file on GitHub · 81 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. 2mo ago First seen · 81 lines · 115 tokens per session scan A 171433b9f0a3

Subscribe to this mod's changes

mindit-context is a skill published in the GitHub repository Dragoon0x/usemindit (2 stars, last pushed 6mo ago), licensed MIT. It adds 115 tokens to every session and 1,213 once invoked, about $0.0005 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.

Related

mindit-context compared with skills from other repositories

mindit-context next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mindit-contextDragoon0x/useminditSkill26mo agoMITA115Claude Code, Codex
webgl-holographic-foilnexu-io/open-designSkill106ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6ktodayMITA47Claude Code