Add Icon Mapping
lobehub/lobe-icons
Add or modify icon keyword mappings for providers, models, or agents in lobe-icons.
Apply cultural mapping — using shared conventions (icons, colors, gestures, metaphors) to convey what a control does when natural spatial mapping isn't available.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill mapping-cultural -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mapping-cultural --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/interaction-and-control-principles/skills/mapping-cultural .claude/skills/mapping-cultural && 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 "mapping-cultural" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural into .claude/skills/mapping-cultural/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mapping-cultural", 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/interaction-and-control-principles/skills/mapping-culturalType 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 mapping-cultural -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mapping-cultural --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/interaction-and-control-principles/skills/mapping-cultural .agents/skills/mapping-cultural && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mapping-cultural" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural into .agents/skills/mapping-cultural/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mapping-cultural", 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 mapping-cultural -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mapping-cultural --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/interaction-and-control-principles/skills/mapping-cultural .cursor/skills/mapping-cultural && 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 "mapping-cultural" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural into .cursor/skills/mapping-cultural/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mapping-cultural", 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/interaction-and-control-principles/skills/mapping-cultural--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 mapping-cultural -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mapping-cultural --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/interaction-and-control-principles/skills/mapping-cultural .gemini/skills/mapping-cultural && 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 "mapping-cultural" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural into .gemini/skills/mapping-cultural/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mapping-cultural", 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 mapping-culturalInstalls 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 mapping-cultural -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/interaction-and-control-principles/skills/mapping-cultural .github/skills/mapping-cultural && 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 "mapping-cultural" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural into .github/skills/mapping-cultural/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mapping-cultural", 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 mapping-cultural -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 mapping-cultural --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/interaction-and-control-principles/skills/mapping-cultural .opencode/skills/mapping-cultural && 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 "mapping-cultural" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural into .opencode/skills/mapping-cultural/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mapping-cultural", 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.
mapping-culturalApply cultural mapping — using shared conventions (icons, colors, gestures, metaphors) to convey what a control does when natural spatial mapping isn't available.
Mapping Cultural is an agent skill from hashgraph-online/awesome-codex-plugins. Apply cultural mapping — using shared conventions (icons, colors, gestures, metaphors) to convey what a control does when natural spatial mapping isn't available. Use when designing icon-based UIs, choosing colors for status indicators, picking gestures for touch interfaces, or selecting metaphors to make abstract operations concrete (the trash can, the gear, the magnifying glass). Cultural mappings are weaker than spatial ones — they require prior learning — but they're the workhorse of icon-driven interfaces…
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/icon-vocabulary.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.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 9e7b281. 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.
Mapping Cultural loads about 2.9k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 154 tokens; SKILL.md has 1,653 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 9e7b281, republished under its Apache-2.0 licence (© hashgraph-online). 1,653 words, ~2,862 tokens.
.claude/skills/mapping-cultural/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Cultural mapping carries meaning through shared convention. The user knows the gear means "settings" because they've seen it a thousand times before. They know red means stop, green means go, yellow means slow. They know the trash can means delete and the magnifying glass means search. None of these mappings is innate — they all had to be learned somewhere — but within a culture that recognizes them, they're effectively free.
Cultural mapping is the workhorse of icon-driven interfaces, because the spatial form of mapping is rarely available for software UI. You can't physically place a "settings" control next to "the settings"; settings are abstract. So you reach for a metaphor — a gear, a wrench, a sliders icon — and rely on the user's prior exposure to interpret it.
A cultural mapping works when three conditions are met.
The convention is genuinely universal in your audience. A red stop sign is universal in driving cultures. A floppy disk for "save" is recognizable to most adults in industrialized cultures, though weakening as a generation that never used floppies grows up. A mortarboard hat for "education" is universal in cultures with that academic tradition.
The convention is the dominant convention, not one of several. A magnifying glass for "search" is dominant. A gear for "settings" is dominant. But a globe icon could mean "internet," "international," "translation," or "external link" — none of those is the dominant interpretation, so the icon needs a label. When two conventions compete, you need disambiguation.
The cost of misinterpretation is low or recoverable. If a user clicks the gear thinking it's settings and it turns out to be "advanced filtering," the cost is one click and a moment of recalibration. If a user clicks the trash can thinking it deletes the current item and it actually empties their entire account, the cost is catastrophic. Strong conventions can carry low-stakes operations; high-stakes operations need explicit labels even when conventions exist.
Cultural mappings draw on four kinds of prior knowledge.
Pictographic — direct visual reference to a real-world object. The trash can looks like a trash can; the camera icon looks like a camera; the lock icon looks like a padlock. These are the most transparent kind of cultural mapping because they require only that the user has seen the object before. They survive across most cultures because the underlying object is widely known.
Indexical — visual reference to a sign or symbol whose meaning is established. A red octagon means stop because road signage has trained people to read it that way. The "@" symbol means email because email systems adopted it. The hash mark "#" means tag because Twitter and other platforms made it so. These conventions have to be learned, but once learned they're robust.
Metaphoric — borrowing the visual form of one domain to suggest the function of another. The "desktop" metaphor in operating systems borrows from physical desks and folders. The "cart" icon in e-commerce borrows from supermarket shopping carts. The "feed" icon (parallel curved lines like a radio antenna) borrows from broadcasting. These metaphors require both that the user knows the source domain and that they recognize the borrowing.
Arbitrary — purely conventional symbols with no inherent meaning. The hamburger menu (three horizontal lines) means "menu" because designers agreed it would. The kebab menu (three vertical dots) means "more options" by similar agreement. These are the most fragile mappings because they have no anchor in physical reality or other domains; they only work because users have been trained.
When you need an icon for a function, the order of preference is usually:
The decision often comes down to: how confident are you that your audience will recognize this convention? When in doubt, label.
Three competing conventions exist: an upward arrow out of a box (Apple's preferred), a node-and-edge graph (Android's preferred), and a chain link (sometimes used for "copy link"). None is universal. A user accustomed to one platform may not immediately recognize the other. The right approach in cross-platform software is often to use the platform-native icon — Apple's icon on Apple devices, Android's icon on Android — paired with a brief label on the first encounter.
Green = good, red = bad, yellow = warning. This convention is so strong it survives even in interfaces designed for color-blind users (where it's typically supplemented with shape: green check, red X, yellow triangle). But the convention is culture-specific in some details — in some Asian cultures red can mean "auspicious" or "celebration," not "stop." For globally deployed software, the safe path is to use the convention but reinforce it with a non-color cue.
Swipe down to dismiss a modal. Swipe up to dismiss a notification. Swipe right to archive. Swipe left to delete. All of these conventions exist in some apps. None is universal. New users typically need explicit onboarding to learn any of them, and once learned the conventions are sticky — changing them in a redesign generates user complaint disproportionate to the change.
The lesson: gesture-based cultural mappings are weaker than icon- or color-based ones, because the gesture itself is invisible. Provide a discoverable visual cue (an arrow, a swipe hint, a brief animation on first use) for any gesture you rely on.
Two icons compete: a funnel (filter) and an "A-to-Z" arrow or up-down arrows (sort). Many users confuse them, especially when both appear together in a toolbar. The fix is usually to label both — the icons alone are insufficient because the conventions are not strong enough to distinguish two related but different operations.
A circular arrow is the dominant convention for "refresh." It's strong enough that most users recognize it without a label. But in contexts where "refresh" is rarely used, or where the arrow could be confused with "undo" (also sometimes a curved arrow), a label removes ambiguity.
The kebab menu (three vertical dots) is now the dominant convention for "more options" or "context menu." It is recognized by most desktop and mobile users. But it's a relatively recent convention — it's purely arbitrary, and it took years of consistent use across major platforms to become dominant. New conventions of this kind take longer to spread than designers usually expect.
Using a domain-specific icon as if it were universal. A developer-tools icon (a wrench-and-screwdriver) for a non-developer audience. A database icon (a stack of cylinders) for a non-technical user. A musical-notation icon for a non-musician. These conventions exist within their domain and are nearly invisible outside it. Use only the conventions your actual audience shares.
Relying on color alone for status. Red borders, green check marks, yellow warnings — they all fail for the substantial fraction of users with color vision deficiencies. Always pair color with a second cue (shape, label, position).
Inventing a new convention and assuming it will catch on. Designers occasionally try to introduce a novel icon for a common function (a custom "search" icon that isn't a magnifying glass). Even if it's well-designed, users will struggle, because they don't know the convention and have no way to learn it except by trial. Stick with the dominant convention unless you have a very strong reason to deviate.
Cultural conventions assumed across regions. A mailbox icon shaped like a US-style flag-and-flag mailbox is meaningless in countries with different mail-collection conventions. A pound-symbol icon ("£") might mean "British currency," "weight in pounds," or "tag depending on region." International products need to verify regional recognition or default to language-localizable text.
Using a label-bearing icon and then duplicating the label. "[gear icon] Settings" with the icon and label adjacent is fine. "[Settings: gear icon and word]" with the gear inside the word redundantly is just clutter. If you have a label, the icon is decoration; if you have an icon, the label is reinforcement. Pick a primary and let the other support it.
Cultural conventions can supplement natural mappings rather than replace them. A volume slider that goes up for louder (natural mapping) and is shown with a speaker icon at one end (cultural mapping reinforcing the meaning) is stronger than either alone. A brightness slider that goes right for brighter (cultural convention) with a sun icon at the bright end (cultural reinforcement) is doubly clear. Stack mappings when you can afford the visual cost.
Before relying on a cultural mapping, ask: Is this convention dominant in my audience, or just one of several? If multiple competing conventions exist, label. Has my audience definitely been exposed to this convention? If you're unsure, label or test. What is the cost of misinterpretation? If high, label regardless of convention strength. Does the icon survive across cultures, regions, and abilities? If not, supplement.
mapping-natural — for the (rare, valuable) cases where you don't have to fall back to convention.iconic-representation — when and how iconic conventions form and stabilize.recognition-over-recall — cultural mappings work because users recognize, not recall.consistency — once a convention is established within your product, applying it consistently strengthens the mapping for your users specifically.references/icon-vocabulary.md — a working catalog of dominant icon conventions and where they come from.© 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/interaction-and-control-principles/skills/mapping-cultural of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 9e7b281
Mapping Cultural 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 |
|---|---|---|---|---|---|---|
| Mapping Cultural this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Add Icon Mappinglobehub/lobe-icons | 2.6k | — | ~1.5k | Automated safety check: Warn | MIT | |
| iOS Icon Generatoraffaan-m/ECC | 276k | — | ~1.4k | Automated safety check: Pass | MIT | |
| IconsJetBrains/intellij-community | 21k | — | ~3.1k | Automated safety check: Pass | Custom licence | |
| Color Expertnexu-io/open-design | 100k | — | ~331 | Automated safety check: Pass | Apache-2.0 | |
| Ecc Conventionsaffaan-m/ECC | 276k | — | ~2.8k | Automated safety check: Pass | MIT |
lobehub/lobe-icons
Add or modify icon keyword mappings for providers, models, or agents in lobe-icons.
affaan-m/ECC
Generates iOS icon PNG imagesets for Xcode asset catalogs from SF Symbols or the Iconify API, matching the size, color and weight of icons already in the project.
JetBrains/intellij-community
Create or review IntelliJ New UI SVG icons and theme variants.
nexu-io/open-design
Color science expert skill with 286K words of reference material covering OKLCH/OKLAB, palette generation, accessibility/contrast, color naming, pigment mixing, and historical color theory.
affaan-m/ECC
Development conventions and patterns for ECC. An agent skill from affaan-m/ECC.
nexu-io/open-design
Map an extracted Figma / source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.
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 cultural mapping — using shared conventions (icons, colors, gestures, metaphors) to convey what a control does when natural spatial mapping isn't available. Mapping Cultural is an agent skill from hashgraph-online/awesome-codex-plugins. Apply cultural mapping — using shared conventions (icons, colors, gestures, metaphors) to convey what a control does when natural spatial mapping isn't available.
Mapping Cultural fits situations like: designing icon-based UIs; choosing colors for status indicators; picking gestures for touch interfaces; selecting metaphors to make abstract operations concrete (the trash can.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill mapping-cultural -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural in hashgraph-online/awesome-codex-plugins) into .claude/skills/mapping-cultural in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill mapping-cultural -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/mapping-cultural in hashgraph-online/awesome-codex-plugins) into .agents/skills/mapping-cultural 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 mapping-cultural -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mapping-cultural, .gemini/skills/mapping-cultural, .github/skills/mapping-cultural and .opencode/skills/mapping-cultural in your project.
SKILL.md names no scripts, command-line tools or credentials: Mapping Cultural 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.
Mapping Cultural 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 2.9k tokens (SKILL.md is roughly 11k 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 Mapping Cultural: Add Icon Mapping (lobehub/lobe-icons, 2.6k stars), iOS Icon Generator (affaan-m/ECC, 276k stars), Icons (JetBrains/intellij-community, 21k stars) and Color Expert (nexu-io/open-design, 100k 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 1,255 GitHub stars. The repository holds 714 skills in this directory. The repository was last updated on October 9, 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.