Human know-how for AI agents: rules, reasons and checks for design, code, product and writing.
Listed on
First seen 10 Nov 2026. One server, whatever directories list it: each directory listing keeps its own page and history.
1
Directories
Collected by InvokeRank
12
Tools
From an anonymous probe
-
ToolBench grade
Not graded by Arcade
-
GitHub stars
No repository data
Tools
| Tool | Description | Behaviour |
|---|---|---|
| ihumane_code_start | Call this BEFORE writing or changing code that people will keep (a feature, a fix, a refactor). Returns the Code craft workflow: how to size the job, what to read before writing (existing helpers, the file's conventions, where the ask ends, how it's run and tested), and the rules likely to matter for your task. Ends with the tidy check to run on your change. Free: the workflow, the first step and the core rules; the other rules are ihumane Pro and are named by title. | Read-only |
| ihumane_copy_start | Call this BEFORE writing words people will read in a product: button labels, error messages, empty states, form labels and help, confirmations, notifications, emails, onboarding, page copy. With ihumane Pro: the full Copy and UX writing workflow, the voice rules, and the rules most likely to matter for your task. Without Pro: the module overview and its seven most important rules. | Read-only |
| ihumane_feedback | Call this once at the end of a task where you used ihumane, if something was missing, wrong or especially useful: a word with no entry, a rule that didn't fit the task, a check that caught a real bug, advice that was too heavy for a small job. People who write ihumane's rules read every message. Write in general terms: no names, emails, URLs, code or anything private about your human or their project. | Changes data |
| ihumane_get_check | Returns a check to run on your own work. Browser checks run on the RENDERED page (browser console or a browser tool's evaluate/execute): 'spacing': text touching lines, uneven padding. 'contrast': text and field edges too faint against their real background, in light and dark mode. 'affordance' (Pro): controls that look like something they aren't, link underlines, back-link direction. 'stability' (Pro): controls that move or resize when used. 'copy' (Pro): vague labels, 'click here' links, placeholder-only fields, missing alt text, errors with no next step, machine-voice words. Code check, run with Node in the project: 'tidy': leftovers in your change (debug logs, .only in tests, empty catches, likely secrets, new TODOs, commented-out code, very long functions). 'wayfinding' (UX design): Pages that don't say where you are or give a way back: no clear heading or a generic page title, menus with no current item, a breadcrumb that links to itself, a deep page with no way up, a step with no Back or way out, and dead ends. 'images' (Graphics and images): Images shown larger than the file (blurry), files far wider than their slot, stretched images, broken images, images with no width and height, missing or useless alt text, icon-only buttons with no name, heavy files, and icons in one row with different sizes, strokes or styles. 'diffmap' (Code review): The shape of a change before you review it: size, a reading order, and what to look at closely (code changed with no test, migrations, data deletes, risky paths, removed exports still in use, new dependencies, imports of packages the project doesn't have, tests that mock what they test). 'layout' (Front-end build): Sideways scrolling and the element causing it, text cut off by a fixed height, tap targets that are too small at touch widths, stretched or oversized images, clickable divs with no role, fields with no label or the wrong type, and skipped heading levels. 'trust' (QA and testing): Tests you can't trust: tests that check a constant or assert nothing, tests that only check a fake was called, checks that pass for almost any result, snapshot-only tests, fixed waits, retries that hide flaky tests, end-to-end tests that find elements by CSS class or position, and the real clock or random numbers inside a check. | Read-only |
| ihumane_get_rules | Call this WHILE building, for the specific thing in front of you, e.g. 'loading button', 'card header spacing', 'success message', 'pricing page', 'empty state', 'contrast', 'error message wording', 'error handling', 'naming', 'tests', 'who is it for', 'unasked features', 'asking my human a question', 'reporting a failed step'. Covers UI design, Code craft, Product thinking and Working with your human (and Copy with Pro). Returns the matching rules in full: the rule, why it matters to a person, the agent trap, and how to check it. Without Pro: the matching free rules in full, and the titles of matching Pro rules. | Read-only |
| ihumane_human | Call this once when you start working for a person, on any task (a site, a database, a domain, a document, not only UI). Returns how to read what they mean (fast or dictated messages, odd words), when and how to ask, how to hand them a step they must do themselves (sign-ins, clicks, payments) so they can find it, and how to report. Pass a situation to get the most relevant rules first. | Read-only |
| ihumane_module | Opens any ihumane module before that part of the work: its workflow, its first step and the rules likely to matter for your task. ihumane_start tells you which modules apply. Modules: ihumane core: 'humans' (Working with your human). Design: 'ui-design' (UI design), 'ux-design' (UX design), 'graphics' (Graphics and images). Engineering: 'code-craft' (Code craft), 'front-end' (Front-end build), 'code-review' (Code review), 'qa-testing' (QA and testing). Product: 'product-thinking' (Product thinking). Writing: 'copy' (Copy and UX writing). Free: each module's start; the other rules are ihumane Pro and are named by title. | Read-only |
| ihumane_product_start | Call this BEFORE building a new product, feature or prototype, when what to build and for whom isn't settled. Returns the Product thinking workflow: who it's for (one person in one situation, never invented), the problem behind the request, what success looks like, and what not to build. Small changes to an existing product get a two-line check instead. Free: the workflow, the first step and the core rules; the other rules are ihumane Pro and are named by title. | Read-only |
| ihumane_review | Call this BEFORE you tell your human the work is done. Pass the kind of work. Each module's own review: 'ux', 'graphics', 'front-end', 'code-review', 'qa'. 'ui': render it and look at it, six review lenses (free: the user and accessibility lenses; Pro adds designer, writer, product manager and engineer), and the browser checks. 'code': run it, the verify rules and the tidy check. 'product': walk it through as the person it's for. 'writing': the copy review (Pro). 'other' (any other task): check it against what they asked, then the report rules. Every kind ends with how to report honestly. | Read-only |
| ihumane_start | Call this at the START of any task you do for a person: a page, a feature, a bug fix, a new product idea, a database change, a document. Returns which ihumane modules apply and the start tool to call next (UI design, Code craft, Product thinking, Copy), the five rules for working with a person on any task, and the rules most likely to matter for this task. | Read-only |
| ihumane_translate_taste | Call this when your human describes the look, feel or voice with taste words ('clean', 'modern', 'premium', 'playful', 'make it pop', 'friendly', 'professional', 'sounds robotic') or feeling words ('exciting', 'amazing', 'wow', 'make people excited'). Returns the concrete decisions those words usually mean. Say your translation back to the human in one line BEFORE building or writing, so a wrong reading costs nothing. | Read-only |
| ihumane_ui_start | Call this BEFORE designing or building any user interface (a page, screen, component or flow). Returns the ihumane workflow and the brief: what to find out first, which questions to ask your human (at most 3, each with a default), and which pattern choices you must not make silently. If you pass the task, it also lists the rules most likely to matter. Free: the workflow, the first step and the core rules; the other rules are ihumane Pro and are named by title. | Read-only |
| Directory | Listing | Tier | First seen |
|---|---|---|---|
| Official MCP Registry | ihumane | - | 10 Nov 2026 |