Modal
K-Dense-AI/scientific-agent-skills
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs.
Agent skill
by hashgraph-online in hashgraph-online/awesome-codex-plugins
Apply figure-ground separation specifically for overlays — modals, dialogs, drawers, popovers, dropdowns, toasts.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figure-ground-overlays-and-modals --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals .claude/skills/figure-ground-overlays-and-modals && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "figure-ground-overlays-and-modals" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals into .claude/skills/figure-ground-overlays-and-modals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figure-ground-overlays-and-modals", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modalsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figure-ground-overlays-and-modals --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals .agents/skills/figure-ground-overlays-and-modals && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "figure-ground-overlays-and-modals" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals into .agents/skills/figure-ground-overlays-and-modals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figure-ground-overlays-and-modals", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figure-ground-overlays-and-modals --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals .cursor/skills/figure-ground-overlays-and-modals && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "figure-ground-overlays-and-modals" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals into .cursor/skills/figure-ground-overlays-and-modals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figure-ground-overlays-and-modals", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hashgraph-online/awesome-codex-plugins.git --path plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figure-ground-overlays-and-modals --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals .gemini/skills/figure-ground-overlays-and-modals && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "figure-ground-overlays-and-modals" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals into .gemini/skills/figure-ground-overlays-and-modals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figure-ground-overlays-and-modals", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hashgraph-online/awesome-codex-plugins figure-ground-overlays-and-modalsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals .github/skills/figure-ground-overlays-and-modals && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "figure-ground-overlays-and-modals" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals into .github/skills/figure-ground-overlays-and-modals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figure-ground-overlays-and-modals", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figure-ground-overlays-and-modals --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals .opencode/skills/figure-ground-overlays-and-modals && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "figure-ground-overlays-and-modals" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals into .opencode/skills/figure-ground-overlays-and-modals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figure-ground-overlays-and-modals", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
figure-ground-overlays-and-modalsApply figure-ground separation specifically for overlays — modals, dialogs, drawers, popovers, dropdowns, toasts.
Figure Ground Overlays And Modals is an agent skill from hashgraph-online/awesome-codex-plugins. Apply figure-ground separation specifically for overlays — modals, dialogs, drawers, popovers, dropdowns, toasts. Use when designing or auditing the moments when a UI element appears over the underlying page and needs to clearly come forward. The most common figure-ground design problem; getting it right means users naturally focus on the overlay, getting it wrong means modals blur into the page or feel jarring.
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/overlay-recipes.md`).
The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 3e1456a. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Figure Ground Overlays And Modals loads about 2.5k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 1,414 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 1,414 words, ~2,488 tokens.
.claude/skills/figure-ground-overlays-and-modals/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.The most common figure-ground design problem in modern UI: an element appears over the underlying page and needs to clearly come forward. Modals, dialogs, drawers, popovers, dropdowns, toasts, tooltips, lightboxes — all are overlays that need to win the figure-ground sorting against the page beneath.
When the figure-ground separation is clear, users naturally focus on the overlay; the page recedes. When it's unclear, users may not notice the overlay, or they may be uncertain about whether to focus on the overlay or the page.
A modal that wins figure-ground separation typically uses several cues together:
1. Scrim. A semi-transparent overlay (40–60% opacity black, typically) between the modal and the page. The scrim does several jobs: visually separates the modal from the page, mutes the page's color and detail, and indicates that the page is currently inactive.
2. Elevation (shadow). The modal has a prominent drop shadow (16–24px blur, low opacity), suggesting it's sitting above everything else.
3. Background. The modal's background is sharp and solid (typically white in light mode, slightly elevated dark gray in dark mode), in clear contrast with the scrim.
4. Close affordance. A clear way to dismiss (X in the corner, button, escape key, click outside on the scrim). Users need to know how to return to the page.
5. Focus trap. Keyboard focus is contained within the modal until it closes. Tab key cycles through the modal's interactive elements; tab doesn't escape to the page beneath.
6. ARIA roles and labels. The modal is announced as a modal; screen readers know to focus on it.
When all these align, the modal is clearly figure, the page clearly ground, and the user can interact with the modal without confusion.
No scrim. The modal floats over the page with no visual separation. The page is still visible at full strength; the figure-ground separation is weak.
Scrim too light. A scrim at 10% opacity that's barely perceptible. The visual cue isn't strong enough to push the page into ground.
Modal too subtle. A modal with no shadow, no border, light gray background that blends with surrounding gray UI. The modal doesn't read as elevated.
No clear close. Users can't figure out how to dismiss the modal. They click around looking for the exit. The modal becomes an interruption rather than a focus point.
Focus not trapped. Tab key escapes the modal and starts cycling through the page beneath, leading to confusion about where focus is.
Multiple modals stacked. A modal opens, then another opens on top of it. The figure-ground sorting becomes ambiguous (which modal is figure?), and users can lose track of state.
Inconsistent modal styles. Different modals in the same product use different scrim opacities, different shadows, different close patterns. Users can't form expectations.
Different overlay types have different figure-ground requirements.
Drawers (side panels). Slide in from one edge of the screen. The page beneath is partially visible (drawer doesn't cover the whole screen). Use scrim to push the visible page area into ground. Drawer itself uses elevation (shadow on the inner edge) to come forward.
Popovers (small overlays attached to a trigger). Smaller than modals, attached to a specific UI element (a button, a link). Scrim is usually unnecessary — the popover is small and obviously associated with its trigger. Use elevation (shadow) to come forward.
Dropdowns (menus expanded from a control). Similar to popovers but specifically a list of options. Elevation cue alone is usually enough; no scrim. The dropdown should clearly close when the user clicks outside or selects an option.
Toasts (transient notifications). Brief overlays that appear and dismiss themselves. High elevation (shadow) makes them clearly above other content. No scrim — the page beneath should remain interactive. Toast colors usually distinct (success green, error red, info blue).
Tooltips (very transient overlays on hover). Lowest elevation among overlays — they're informational, not action-requiring. Subtle shadow or border is sufficient.
Lightbox (full-screen image viewer). Maximum scrim (often pure black) because the image needs full attention. The image is the only figure; everything else is hidden.
Each type has its own figure-ground recipe based on its purpose.
User clicks "Delete account." A modal opens:
Figure-ground is unambiguous. The modal commands attention; the page is clearly inactive. The user can make the decision without distraction.
User clicks "User settings" in the nav. A dropdown opens below the trigger:
The dropdown clearly comes forward through elevation but doesn't dominate; the user can dismiss easily and continue with the page.
User clicks "Settings" icon. A side drawer slides in from the right:
The drawer is figure within its layer; the visible page area is clearly secondary; the user knows where to focus.
User saves a document. A toast appears:
The toast is figure briefly, then disappears. The page never becomes ground; the user can continue working uninterrupted.
A modal opens but no scrim is added. The page is fully visible behind the modal. Users see the modal but also see the page; figure-ground is ambiguous. They sometimes click on the page (thinking they're interacting) and miss the modal entirely.
The fix: add a scrim. Even a light one (40% opacity) dramatically improves figure-ground separation.
Modals without scrim. As above, the modal blurs into the page.
Modals that auto-dismiss while user is reading. A modal that times out is an interruption that ended before users could engage.
Stacked modals. Modal A opens; from Modal A, the user triggers an action that opens Modal B. Now there are two modals; figure-ground is ambiguous; state is hard to track. Avoid stacking modals; replace one modal with another or use a non-modal pattern.
Modal animations that are too slow or too theatrical. A modal that takes 800ms to slide in feels sluggish; a modal with elaborate effects feels distracting. Quick (200–300ms) and clean is best.
Click-outside dismissal that loses user data. A user has typed in a form modal and accidentally clicks outside; the modal dismisses and their input is lost. Either confirm dismissal when there's unsaved input, or don't allow click-outside to dismiss for input-containing modals.
Inconsistent overlay patterns. Different drawers in the same product behave differently; some have scrim, others don't; some close on click-outside, others don't. Codify the patterns.
Tooltips that act like modals. A tooltip that requires the user to click to dismiss, blocks page interaction, or contains a lot of content. Tooltips should be lightweight; if you need more, use a popover or modal.
For every overlay you ship, ask: Does it have appropriate figure-ground separation from the underlying page? Test by glancing — what stands forward? Are the cues (scrim, elevation, shadow) calibrated to the overlay type? Modals get more; toasts get less. Is the close path clear? Users should always know how to dismiss. Is focus managed correctly? Tab should be trapped in modals; not in toasts. Does the overlay match the patterns established elsewhere in the product? Inconsistency confuses users.
figure-ground-relationship — parent principle on figure-ground perception.figure-ground-cues — sibling skill on the specific visual cues.forgiveness — modal dismissal patterns interact with forgiveness (don't lose user input on accidental dismiss).feedback-loop — toasts are feedback; their figure-ground supports their feedback role.accessibility — overlays have specific accessibility requirements (focus trap, ARIA, escape key).references/overlay-recipes.md — specific design recipes for each overlay type.© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 3e1456a
Figure Ground Overlays And Modals next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Figure Ground Overlays And Modals this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| ModalK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~4.5k | Automated safety check: Notes | Apache-2.0 | |
| Imperative Modal APIlobehub/lobehub | 83k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Law Of Figure GroundOwl-Listener/designer-skills | 2.9k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Figurevectorize-io/hindsight | 48k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Modaldavila7/claude-code-templates | 33k | 7 repos | ~2.6k | Automated safety check: Pass | MIT |
K-Dense-AI/scientific-agent-skills
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs.
lobehub/lobehub
Shows how to build modals, dialogs and confirmations in LobeHub with the base-ui imperative API (createModal, confirmModal, ModalHost) instead of declarative Modal components.
Owl-Listener/designer-skills
Apply the Law of Figure-Ground — establish which layer is foreground and actionable versus background.
vectorize-io/hindsight
Draw an animated figure (boxes, arrows, moving data) as one self-contained SVG for a GitHub README, PR, issue or blog post.
davila7/claude-code-templates
Run Python code in the cloud with serverless containers, GPUs, and autoscaling.
RtlZeroMemory/Rezi
Add modal dialogs and overlay UI with focus trapping. An agent skill from RtlZeroMemory/Rezi.
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Apply figure-ground separation specifically for overlays — modals, dialogs, drawers, popovers, dropdowns, toasts. Figure Ground Overlays And Modals is an agent skill from hashgraph-online/awesome-codex-plugins. Apply figure-ground separation specifically for overlays — modals, dialogs, drawers, popovers, dropdowns, toasts.
Figure Ground Overlays And Modals fits situations like: auditing the moments when a UI element appears over the underlying page and needs to clearly come forward.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals in hashgraph-online/awesome-codex-plugins) into .claude/skills/figure-ground-overlays-and-modals in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-overlays-and-modals in hashgraph-online/awesome-codex-plugins) into .agents/skills/figure-ground-overlays-and-modals in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-overlays-and-modals -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/figure-ground-overlays-and-modals, .gemini/skills/figure-ground-overlays-and-modals, .github/skills/figure-ground-overlays-and-modals and .opencode/skills/figure-ground-overlays-and-modals in your project.
SKILL.md names no scripts, command-line tools or credentials: Figure Ground Overlays And Modals is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Figure Ground Overlays And Modals is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Figure Ground Overlays And Modals: Modal (K-Dense-AI/scientific-agent-skills, 48k stars), Imperative Modal API (lobehub/lobehub, 83k stars), Law Of Figure Ground (Owl-Listener/designer-skills, 2.9k stars) and Figure (vectorize-io/hindsight, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.