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 glebis/humane-agentic-design --skill nielsen-heuristicsgit clone --depth 1 https://github.com/glebis/humane-agentic-designWrote 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/glebis/humane-agentic-design/nielsen-heuristics)<a href="https://agentmods.dev/skills/glebis/humane-agentic-design/nielsen-heuristics"><img src="https://agentmods.dev/badge/skills/glebis/humane-agentic-design/nielsen-heuristics/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/glebis/humane-agentic-design/nielsen-heuristics"><img src="https://agentmods.dev/badge/skills/glebis/humane-agentic-design/nielsen-heuristics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.02270 |
| Opus 5 | $0.00059 | $0.01135 |
| Sonnet 5 | $0.00024 | $0.00454 |
| Haiku 4.5 | $0.00012 | $0.00227 |
Grade A, and why
nielsen-heuristics 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 11d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nielsen Heuristics Validator
Mascot:
assets/jakob-nielsen.png— a line-art portrait of Jakob Nielsen. Surface it (embed or attach) when producing a rendered/HTML report or a shareable summary, as the evaluation's signature. It is an output asset, not context to read while evaluating.
Announce at start: "I'm using the humane:nielsen-heuristics skill to evaluate this against Nielsen's 10 usability heuristics."
Run a rigorous, evidence-disciplined heuristic evaluation against Jakob Nielsen's 10 usability heuristics (Nielsen & Molich 1990, refined 1994). The value over an ad-hoc "critique this UI" prompt is a consistent rubric plus honesty guards: sharp per-heuristic probes, a per-finding severity scale, a mandatory evidence-locator requirement, and correct handling of artifacts that have no observable interface.
Scope guard (read first)
This skill does ONE thing: a formal heuristic inspection. It does NOT run a parallel accessibility (WCAG) audit, performance audit, or general design critique. Flag an accessibility issue only when it is also a heuristic violation (e.g., an invisible focus state violates H1: visibility of system status). If the user wants comprehensive multi-dimension auditing, defer to humane:review, which orchestrates this skill alongside layout-rules, ux-writing, walkthrough, and design-tokens contrast — and marks the domains it cannot cover rather than improvising them. For post-build polish specifically, impeccable:audit is the right tool if installed.
Step 1 — Detect artifact type and select a mode
Heuristic evaluation is an inspection of an interface. Some inputs have one to observe; some only describe one that does not yet exist. Detect the input type, then announce the mode and why.
Evaluation mode (observable interface → findings are severity-scored):
- Screenshot / image — read it visually.
- Live URL — drive it to observe states and flows, following
walkthrough'sreferences/driven.mdfor the tool ladder, device matrix, and screenshot evidence contract (that file is the single owner of the driving procedure). A heuristic only observable on a tier that was not driven is N/A at that tier, not silently assessed from desktop. - Codebase / HTML page — grep and read the UI source.
What ships with it
7 files 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.
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.
- 11d ago First seen · 120 lines · 118 tokens per session scan A 71d2e9a91795
nielsen-heuristics is a skill published in the GitHub repository glebis/humane-agentic-design (28 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 2,270 once invoked, about $0.0006 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.
Other skills, from other repositories
figma-extract-design-system
Extract a design system from vibe-coded production apps that never had one: inventory components, mine de-facto styling into DTCG tokens, scaffold a Storybook package, port components, and optionally round-trip tokens/components into Figma. Use when the user wants to 'extract a design system', 'create a design system…
figma-blame-node
Find which Figma version introduced a specific change — a component property or a child node — via a binary search over version history (log2(N) API calls instead of N). Answers 'who added this and when'. Use when the user wants git-blame-style attribution for a Figma design — triggers: 'when was this component…
figma-generate-component-doc
Generate complete Markdown documentation for a Figma component — anatomy/layer tree, design tokens (colors, spacing, typography), states/variants matrix, accessibility notes, content guidelines, and optional code-parity + YAML frontmatter. Use when the user wants a docs page or handoff spec for a component or…
figma-version-history
List a Figma file's version history, snapshot the file at any past version, and diff two versions (added/removed/renamed pages plus deep per-component changes). Use when the user wants to inspect Figma history — triggers: 'list Figma versions', 'what versions does this file have', 'show version history', 'snapshot…
figma-comments
Read, post, reply to, and delete comments on a Figma file via the REST API — including pinning a comment to a specific node and threading replies. Use when the user wants to work with Figma comments programmatically — triggers: 'get Figma comments', 'read comments on this file', 'post a comment in Figma', 'leave a…
figma-export-tokens
Export Figma variables to design token files in DTCG, CSS custom properties, Tailwind v4/v3, SCSS, TypeScript, JSON, Style Dictionary, or Tokens Studio. Use when the user wants to pull design tokens OUT of Figma into code — triggers: 'export tokens', 'export Figma variables', 'generate CSS variables from Figma', 'turn…