Cloudflare
hodgef/apiker
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF…
Put a Homie studio's site and games online on the studio's OWN Cloudflare account (Worker, D1 and public-room Durable Objects, all on the free plan with no payment method; R2 storage only when…
$ npx skills add hashgraph-online/awesome-codex-plugins --skill publish -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins publish --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/homie-rocks/homie/skills/publish .claude/skills/publish && 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 "publish" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/homie-rocks/homie/skills/publish into .claude/skills/publish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish", 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/homie-rocks/homie/skills/publishType 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 publish -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins publish --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/homie-rocks/homie/skills/publish .agents/skills/publish && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "publish" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/homie-rocks/homie/skills/publish into .agents/skills/publish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish", 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 publish -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins publish --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/homie-rocks/homie/skills/publish .cursor/skills/publish && 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 "publish" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/homie-rocks/homie/skills/publish into .cursor/skills/publish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish", 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/homie-rocks/homie/skills/publish--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 publish -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins publish --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/homie-rocks/homie/skills/publish .gemini/skills/publish && 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 "publish" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/homie-rocks/homie/skills/publish into .gemini/skills/publish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish", 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 publishInstalls 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 publish -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/homie-rocks/homie/skills/publish .github/skills/publish && 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 "publish" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/homie-rocks/homie/skills/publish into .github/skills/publish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish", 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 publish -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 publish --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/homie-rocks/homie/skills/publish .opencode/skills/publish && 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 "publish" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/homie-rocks/homie/skills/publish into .opencode/skills/publish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish", 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.
publishPut a Homie studio's site and games online on the studio's OWN Cloudflare account (Worker, D1 and public-room Durable Objects, all on the free plan with no payment method; R2 storage only when…
Publish is an agent skill from hashgraph-online/awesome-codex-plugins. Put a Homie studio's site and games online on the studio's OWN Cloudflare account (Worker, D1 and public-room Durable Objects, all on the free plan with no payment method; R2 storage only when added), run its site (the hub's sections in the studio's own look, a landing for every game, news posts with feeds, and what the studio's site/ folder overrides), list them in the homie.rocks directory, and read the studio's own stats (visits, plays, rooms, rounds, players, songs, videos, where people came from); ask an…
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`). Compatibility notes: Node 22 and the studio's own pinned Wrangler, signed in to the studio's Cloudflare account. Cloudflare's own plugin (cloudflare/skills) and docs MCP are…
It works with Cloudflare, Cloudflare Durable Objects, Cloudflare Workers and Model Context Protocol. 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.
Shell commands in SKILL.md call:
npxnpmFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
docs.mcp.cloudflare.comAlso links to:
github.comFrom 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.
Node 22 and the studio's own pinned Wrangler, signed in to the studio's Cloudflare account. Cloudflare's own plugin (cloudflare/skills) and docs MCP are optional helpers.
From compatibility in the SKILL.md frontmatter.
Publish loads about 3.8k tokens when it runs. Until then it costs about 200 tokens; SKILL.md has 2,239 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). 2,239 words, ~3,814 tokens.
.claude/skills/publish/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.A studio's site runs on the studio's own Cloudflare account; homie.rocks only lists it.
npx wrangler whoami.npx wrangler login. Tell the person in one line that Cloudflare
opened in their browser and they approve once (a free account works, no payment
method). Wait, then
whoami again. Never ask for, paste or store an API key. Where no browser can open on
this computer (a remote or cloud session), npx wrangler login --device prints a code the
person approves on any device.studio.json
(cloudflare.accountId).https://docs.mcp.cloudflare.com/mcp, no sign-in) or any developers.cloudflare.com
page with /index.md added for Markdown.wrangler, workers-best-practices,
durable-objects and more) and its API MCP server. Offer it when the person wants that
help, and they approve the install: in Claude Code /plugin marketplace add cloudflare/skills, then /plugin install cloudflare@cloudflare (it is also in Claude's
plugin directory as cloudflare@claude-plugins-official); in Codex codex plugin marketplace add cloudflare/skills, then codex plugin add cloudflare@cloudflare.npm run deploy and homie-studio, which record what they create in studio.json and never
touch what they did not create. Never create, change or delete them with Cloudflare's
MCP (its execute, a bindings or connector tool) or a bare wrangler command. The Homie
mod (Claude Code) and Homie's hooks (Codex) hold such a change inside a studio (a
delete, a secret, a hand rollout, a write to the live database) until the person says
Proceed.npm run deploy
npx --no-install homie-studio check <id> --url <the live site it printed>Before the first deploy, tell the person what it creates and what it costs:
npx --no-install homie-studio deploy --plan prints it and changes nothing (one Worker,
one D1 database, two SQLite-backed Durable Objects; free on the Workers Free plan; no R2).
deploy builds every game, creates the Worker and D1 database named in studio.json,
applies migrations, deploys, and reads the live site once (the site then claims itself
in the homie.rocks directory; nothing is stored by hand). It never creates R2. It refuses
to use a Worker, database or bucket of the same name that this studio did not create;
then rename it in studio.json and wrangler.jsonc (an older studio's is
site/wrangler.jsonc). Never
delete, rename or redeploy anything the studio did not create. When it answers with a
needs step (a new account verifies its email address; an account with no workers.dev
address picks one), say that step to the person and wait. The deploy itself is held for the
person's Proceed, with where it goes and what changed since the last one: by the Homie mod in
Claude Code, and by Homie's hooks in Codex and Grok Build (studio-setup says how a hold is answered there).
Where nothing holds it (Codex or Grok Build before the hooks are trusted: the setup status says "Homie's
holds: off"), say what the deploy would do in a sentence and wait for the person's yes.
Storage for songs and videos (npx --no-install homie-studio storage add, an R2 bucket) is
separate and optional: Cloudflare asks for a payment method before R2 works, so only
when the person wants it, after saying so (R2 has no egress fees; storage is free up to
10 GB-month, then US$0.015 per GB-month).
Published entries of music/manifest.json and videos/manifest.json become pages at
/music/<slug>/ and /videos/<slug>/ with every deploy (the music and video skills write
them and redeploy). Without storage the site serves each file itself, up to 25 MiB a file. Once
the studio has storage, big media lives in its R2 by default: every deploy moves each public file
over 1 MiB, or left out of git, into R2 (uploaded, read back, checked by SHA-256) before the site
stops carrying it, and serves it at the same address; the file stays in the studio folder.
npx --no-install homie-studio media move --dry-run says what would move; media list shows what
the site will show, where each file is served from, and why anything is left out. A studio with
songs or videos and no games can still deploy.
An existing studio (made before @homie-rocks/studio 0.18.0) moving its media: upgrade (it
lists the big media and moves nothing), npm install, media move --dry-run, media move, then
npm run deploy, then curl one moved file with a byte range: a 206 with the file's full size in
content-range, at the address it always had. Never delete the local files.
Every deploy builds the studio's site from the studio (node_modules/@homie-rocks/studio/site/SITE.md has
all of it): Home, Games, Music, Videos, Rooms and Posts, each only when the studio has something in it (a
section with nothing has no tab and answers 404), and a landing for every game (the game skill's "Its
landing page" makes one epic). Every page ends with "Made with Homie"; restyle it, keep it.
posts/<YYYY-MM-DD>-<slug>.md (posts/README.md): frontmatter title:, summary: (one line: the
cards and the feeds), image: (a /path on the site, like a game's cover), and game:, song: or
video: to link one of the studio's own; then the body in markdown. Say something real: what is new,
why it is fun, how to play, what is next. Posts are at /posts/, on Home, in /posts/feed.xml (Atom)
and /posts/feed.json (JSON Feed), and in the directory's copy of the studio.site/theme.json (colours, fonts, corner radius, a logo in site/public/) and
site/theme.css for anything more. studio.json "tagline" is the studio's line; "site": { "featured": "<game id>" } picks Home's game.site/pages/<path>/index.html (an About page, or a
hand-made landing at site/pages/<id>/index.html), a piece of every page in site/partials/ (footer,
header, home, game, game-<id>, post, head), files in site/public/. site/README.md in the
studio lists them./robots.txt, /sitemap.xml, /llms.txt and
/llms-full.txt from what is public (SITE.md, "Search engines and AI agents"). The studio's links elsewhere
go in studio.json "site": { "schema": { "sameAs": [...] } }; a hand-made page takes <!-- homie:schema -->
in its <head>. Ratings, reviews and prices are never added by hand.npx --no-install homie-studio look --url <site> (the local dev address,
then the live one) shoots every page on a computer and a phone and names what is wrong.Going online never lists a studio. Listing is this separate step, public, and the person's to ask for: do it when they asked to be listed or said yes to your offer, never as part of a deploy.
Licences first: publish refuses to list a studio while a public game ships an asset with no licence record, a
licence that forbids a web game, or a credit it owes but does not show (npx --no-install homie-studio assets check <id> names each one and its fix; the models skill has the rules). Fix them, deploy, then publish.
Call the Homie MCP tool studio_publish with the live site (or run
npx --no-install homie-studio publish). It answers with each listed game's Play link, and
with anything it did not list and why. The directory is in beta: at most 12 games per
studio are listed, names and blurbs are checked (plain text, no links), and its owner can
unlist a listing. Anyone can report a listing; only the directory's owner acts on
reports, never an AI.
The beta also caps how many times a studio may publish in a day. publish (and studio_publish) says how many are
left when the directory gives the number, and before it sends, how many this computer has sent today; the local
tool's before: true says that without publishing. A refusal for the cap is not a broken studio: say when it ends
and stop, never retry in a loop. A deploy that closes or opens a game's source asks the directory to read an
already-listed studio again by itself (that uses one of the day's publishes); it never lists an unlisted one.
deploy prints the live address. A workers.dev address names the person's Cloudflare
account (often after them), so deploy keeps it in .studio/local.json, which git ignores:
never copy it into a committed file (README, posts, manifests). When the studio has its own
domain, it goes in studio.json as cloudflare.domain (e.g. "night-owls.example"); deploy
never replaces it, and the directory claim, publish, check and stats use it.
A studio's domain usually shares its Cloudflare zone with other things. Never touch a route the studio does not
own: not in wrangler.jsonc, not with Wrangler, not in the Cloudflare dashboard. deploy keeps the studio's own
routes in wrangler.jsonc (its custom domain, an exact-host route) and never changes or removes any other route. On a
custom domain the plan and the deploy read the domain's Worker routes first, and warn when another site's catch-all
(*/*) or wildcard covers the studio's hostname: that route answers the hostname before the studio does, and editing
or removing it takes the other site down. Say the warning to the person as it is. The one safe fix is the line it
gives, the studio's own exact-host route ({ "pattern": "<host>/*", "zone_name": "<domain>" } in "routes"), which
npx --no-install homie-studio deploy --own-route (studio_deploy with ownRoute: true) adds for you once the
person agrees; never a wildcard or a catch-all, which deploy refuses because it would take over the zone's other
sites. When it says the routes could not be read, that is unmeasured, not fine: if the domain answers as something
else after the deploy, the same one line is the fix. Only one deploy of a studio runs at a time; each prints which games changed since the last
deploy from this computer with the game's build hash (the one build printed, and the one the live site says in
/.well-known/homie-studio.json as games[].build.hash), so "is my build live" is a comparison of two hashes. "Network preflight failed" means this computer could not look the
site's name up (a browser may still open it): test against the local dev site, and do not report the game as broken.
Every studio counts, in its own Cloudflare (D1, free plan): pages opened, Play presses,
rooms opened, the most people playing at once and right now, rounds finished, songs played,
videos watched, and which site sent each visitor (homie.rocks, another studio, search, the
web, a ?via= link). It counts and never tracks: no cookie on a visitor, no person
identified, nothing sent anywhere; prefetches, crawlers and house QA are not counted.
npx --no-install homie-studio stats (add --range 30d,
or --game <id>, --song <slug>, --video <slug>) and say the numbers plainly.npx --no-install homie-studio stats key gives a read key that ends in an hour;
pass it to studio_stats { site, key, range }. The key only reads; never paste it
anywhere else, and stats revoke ends every key.npx --no-install homie-studio stats link gives a one-time
link (30 minutes) to the private page /_studio/stats. Give it to the person to open
themselves; it keeps that browser signed in for 30 days. It is theirs: never post it.npx --no-install homie-studio stats share on (then npm run deploy) lets the directory
show "played this week" (Play presses and rounds with people, over 7 days). Only when the
person wants it; it is off by default.npm run deploy (D1 migration
0002_studio_stats.sql); nothing before then was counted.office skill (npx --no-install homie-studio office). An office
key (office key) also reads these stats.After a studio's first publish (its games are listed and playable), or when a deploy or a listing failed in a way
you could not fix, you may offer, once in the session, to send the people who make Homie a short note about it:
homie_feedback with offered: true and the step (step: "publish"). A draft sends nothing; show it exactly as it
would go and send it only after the person says yes (in Claude Code, Claude Code itself asks them with the exact
note; in Codex, Homie's hooks hold the send for their proceed <code>). A no is final for the session. No keys, logs, files, code, site addresses that name the account, or anyone's
name in it.
Homie for studios is in beta. When something breaks, tell the person it can go to
https://github.com/homie-rocks/homie/issues/new/choose (bug, port request or question),
without keys, tokens or private addresses in it. Or, with their yes, send a short note
from here (homie_feedback, above).
© 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 in plugins/homie-rocks/homie/skills/publish of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 9e7b281
Publish 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 |
|---|---|---|---|---|---|---|
| Publish this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Cloudflarehodgef/apiker | 127 | 7 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Agents SDKcloudflare/skills | 3k | 2 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Durable Objectscloudflare/skills | 3k | 2 repos | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Durable Objectshodgef/apiker | 127 | 4 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Prepare Cloudflare Production DeploymentLubomirGeorgiev/cloudflare-workers-nextjs-saas-template | 786 | — | ~5.9k | Automated safety check: Notes | MIT |
hodgef/apiker
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF…
cloudflare/skills
Build, debug, or review Cloudflare Agents SDK applications using the agents package.
cloudflare/skills
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
hodgef/apiker
Create and review Cloudflare Durable Objects. An agent skill from hodgef/apiker.
LubomirGeorgiev/cloudflare-workers-nextjs-saas-template
Source-of-truth runbook for preparing this Vinext Cloudflare Workers SaaS template for production deployment.
every-app/open-seo
Triage OpenSEO production errors in Cloudflare Workers Observability — verified query recipes, counting gotchas, and a known-noise filter list applied automatically.
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.
Put a Homie studio's site and games online on the studio's OWN Cloudflare account (Worker, D1 and public-room Durable Objects, all on the free plan with no payment method; R2 storage only when…. Publish is an agent skill from hashgraph-online/awesome-codex-plugins.
Publish fits situations like: someone asks to deploy; share a studios games; write a news post; announce a drop.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill publish -a claude-code`. Or copy the skill folder (plugins/homie-rocks/homie/skills/publish in hashgraph-online/awesome-codex-plugins) into .claude/skills/publish in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill publish -a codex`. Or copy the skill folder (plugins/homie-rocks/homie/skills/publish in hashgraph-online/awesome-codex-plugins) into .agents/skills/publish 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 publish -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/publish, .gemini/skills/publish, .github/skills/publish and .opencode/skills/publish in your project.
Going by SKILL.md and its folder, Publish needs the command-line tools its instructions call (npx and npm). Our summary lists: Node.js. Compatibility (from SKILL.md): Node 22 and the studio's own pinned Wrangler, signed in to the studio's Cloudflare account. Cloudflare's own plugin (cloudflare/skills) and docs MCP are optional helpers..
SKILL.md names 2 domains. In commands or code: docs.mcp.cloudflare.com; the agent is likely to contact it when it follows the instructions. As links in the text: github.com. 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.
Publish 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 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Publish: Cloudflare (hodgef/apiker, 127 stars), Agents SDK (cloudflare/skills, 3k stars), Durable Objects (cloudflare/skills, 3k stars) and Durable Objects (hodgef/apiker, 127 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.