Openpets
OpenPetsHQ/openpets
A skill your agent uses whenever the user wants to build, extend, debug, test, validate, locally load, package, or publish an OpenPets plugin; work with the OpenPets Plugin SDK v3, plugin manifest…
Scaffold a Claude Code mod (a plugin with a function-hooks module) from ruflo's governed template — hybrid hooks.json with a classic fallback, a host adapter over literal $ calls, userConfig…
Install Create Mod
$ npx skills add ruvnet/ruflo --skill create-mod -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ruvnet/ruflo create-mod --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/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ruflo-plugin-creator/skills/create-mod .claude/skills/create-mod && 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 "create-mod" agent skill from https://github.com/ruvnet/ruflo/tree/main/plugins/ruflo-plugin-creator/skills/create-mod into .claude/skills/create-mod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-mod", 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/ruvnet/ruflo/tree/main/plugins/ruflo-plugin-creator/skills/create-modType 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 ruvnet/ruflo --skill create-mod -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ruvnet/ruflo create-mod --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/ruflo-plugin-creator/skills/create-mod .agents/skills/create-mod && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "create-mod" agent skill from https://github.com/ruvnet/ruflo/tree/main/plugins/ruflo-plugin-creator/skills/create-mod into .agents/skills/create-mod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-mod", 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 ruvnet/ruflo --skill create-mod -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ruvnet/ruflo create-mod --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/ruflo-plugin-creator/skills/create-mod .cursor/skills/create-mod && 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 "create-mod" agent skill from https://github.com/ruvnet/ruflo/tree/main/plugins/ruflo-plugin-creator/skills/create-mod into .cursor/skills/create-mod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-mod", 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/ruvnet/ruflo.git --path plugins/ruflo-plugin-creator/skills/create-mod--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 ruvnet/ruflo --skill create-mod -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ruvnet/ruflo create-mod --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/ruflo-plugin-creator/skills/create-mod .gemini/skills/create-mod && 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 "create-mod" agent skill from https://github.com/ruvnet/ruflo/tree/main/plugins/ruflo-plugin-creator/skills/create-mod into .gemini/skills/create-mod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-mod", 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 ruvnet/ruflo create-modInstalls 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 ruvnet/ruflo --skill create-mod -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/ruflo-plugin-creator/skills/create-mod .github/skills/create-mod && 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 "create-mod" agent skill from https://github.com/ruvnet/ruflo/tree/main/plugins/ruflo-plugin-creator/skills/create-mod into .github/skills/create-mod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-mod", 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 ruvnet/ruflo --skill create-mod -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ruvnet/ruflo create-mod --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/ruflo-plugin-creator/skills/create-mod .opencode/skills/create-mod && 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 "create-mod" agent skill from https://github.com/ruvnet/ruflo/tree/main/plugins/ruflo-plugin-creator/skills/create-mod into .opencode/skills/create-mod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-mod", 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.
Facts
- Skill name
create-mod- GitHub stars
- 74k
- Token cost
- ~984 tokens
- SKILL.md length
- 407 words
- Files
- 1
- Skills in repo
- 264
- Repo updated
- First seen
- Licence
- MIT
At a glance
Scaffold a Claude Code mod (a plugin with a function-hooks module) from ruflo's governed template — hybrid hooks.json with a classic fallback, a host adapter over literal $ calls, userConfig…
- Works in 8 steps: Name it. kebab-case . Commands it… → Copy the template… → Keep the status contract.… → …
- The user asks for a mod
- Calls claude and npx
- A function hook
What it does
Create Mod is an agent skill from ruvnet/ruflo. Scaffold a Claude Code mod (a plugin with a function-hooks module) from ruflo's governed template — hybrid hooks.json with a classic fallback, a host adapter over literal $ calls, userConfig options, engine-kit tests and a tsconfig — then validate and test it. Use when the user asks for a mod, a function hook, or wants Claude Code to modify itself.
Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Hooks and plugins. It works with TypeScript. The repository describes itself as: 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory…. The licence is MIT.
When your agent uses it
- The user asks for a mod
- A function hook
- Wants Claude Code to modify itself
Example prompts
- “/create-mod”
Requirements
- Node.js
- Pre-approved tools (allowed-tools): Bash, Read, Write, Edit
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Name it. kebab-case . Commands it registers are namespaced -; never register a built-in's name (/diff, /help) or another plugin's (/ruos*…
- Copy the template plugins/ruflo-plugin-creator/templates/mod/ to the target folder. Replace my-mod everywhere (plugin.json name, the…
- Keep the status contract. hooks/status.ts writes .claude-flow/-mod/status.json, the file the console's Mods section reads. The folder must…
- Write the behaviour in pure functions taking the Host (see hooks/host.ts). In register.ts, build the host from literal $.noun.method(...)…
- Keep the rules
- Keep the fallback honest. hooks.json is hybrid: the classic command hook runs everywhere, the module only where function hooks are on…
- Validate and test
- Ship it in a plugin marketplace (marketplace.json entry), installed with /plugin install @ and picked up with /reload-plugins. If…
What it can do on your machine
Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadWriteEdit
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
claudenpx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Create Mod loads about 984 tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 407 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.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, Write, Edit
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.
SKILL.md
The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 407 words, ~984 tokens.
Download SKILL.mdSave it as
.claude/skills/create-mod/SKILL.md (or your agent's skills folder).- name
- create-mod
- description
- Scaffold a Claude Code mod (a plugin with a function-hooks module) from ruflo's governed template — hybrid hooks.json with a classic fallback, a host adapter over literal $ calls, userConfig options, engine-kit tests and a tsconfig — then validate and test it. Use when the user asks for a mod, a function hook, or wants Claude Code to modify itself.
- allowed-tools
- Bash, Read, Write, Edit
- argument-hint
- <mod-name>
Create Mod
Scaffold a mod the governed way, instead of an ad-hoc one: the template already follows the rules ruflo's own mod (ADR-404) was reviewed against.
Steps
- Name it. kebab-case
<name>. Commands it registers are namespaced<name>-<verb>; never register a built-in's name (/diff,/help) or another plugin's (/ruos*,ruflo-*). - Copy the template
plugins/ruflo-plugin-creator/templates/mod/to the target folder. Replacemy-modeverywhere (plugin.jsonname, the command,MY_MOD_ACTIVE→<NAME>_ACTIVEin bothhooks/register.tsandhooks/classic.cjs). - Keep the status contract.
hooks/status.tswrites.claude-flow/<name>-mod/status.json, the file the console's Mods section reads. The folder must be<name>-mod(lowercase, digits, hyphens, at most 41 characters): replacemy-modinSTATUS_PATHwith<name>-mod. Fields:version: 1(required, anything else is ignored),summary(one line),modVersion,guard(boolean),calls(a number, not a per-tool object),blocked(number),lastDenied(a short reason, only once the mod has refused something), plusupdatedMs/startedMs. Other fields are not shown.tests/status.test.tsasserts the shape. - Write the behaviour in pure functions taking the
Host(seehooks/host.ts). Inregister.ts, build the host from literal$.noun.method(...)calls only — the engine reads a module's$uses off its source, andclaude plugin validaterefuses$passed around, computed ($[noun]), or deeper than$.noun.method(input). - Keep the rules:
- Observe with
const r = await next(e); …; return r; rewrite withnext({ ...e, … }); answer ({ deny }) only when you mean to stop the chain. - On
tool.check, only ever tighten (the stricter ofawait next(e)and yours); never answerallowof your own. - Wrap every
$call so a refusal degrades instead of failing the turn (admins can withhold any$affordance). - No
$.process.run/$.http.fetchbuilt from event input. Nothing slow on the hot path (about 10 s per dispatch). - Anything that must survive a hot reload goes in
$.store/$.state, not module variables. - Options come from
userConfigin plugin.json, not environment variables.
- Observe with
- Keep the fallback honest.
hooks.jsonis hybrid: the classic command hook runs everywhere, the module only where function hooks are on (Claude Code >= 2.1.287; 2.1.277+ withCLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1). The module sets<NAME>_ACTIVEatsession.start; the classic script exits early when it sees it, so nothing fires twice. - Validate and test:
bash claude plugin validate <dir> # lists hooked events, $ calls, env reads/writes claude plugin test <dir> # tests/*.test.ts on the engine kit claude -p --plugin-dir <dir> "/<name>-status" # writes .claude-plugin/types/ and proves a live load npx tsc -p <dir> # against those generated types - Ship it in a plugin marketplace (
marketplace.jsonentry), installed with/plugin install <name>@<marketplace>and picked up with/reload-plugins. If ruflo-mods is installed withmodTrust: refuse-risky, a mod usingprocess.run,http.fetch,env.setorfs.write, or hookingtool.check/tool.call/*, is refused unless its plugin id (<name>@<marketplace>) is inmodTrustAllow— the template setsenv.set(the fallback handshake), so allow-list it by id.
© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/ruflo-plugin-creator/skills/create-mod of ruvnet/ruflo.
Open the folder on GitHubat commit de590e1
Compare with similar skills
Create Mod 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 |
|---|---|---|---|---|---|---|
| Create Mod this skillruvnet/ruflo | 74k | — | ~984 | Automated safety check: Notes | MIT | |
| OpenpetsOpenPetsHQ/openpets | 1.3k | — | ~2.1k | Automated safety check: Pass | MIT | |
| OpenCode Plugin CreatorDevin-AXIS/iPolloWork | 6.7k | 1 repos | ~1.3k | Automated safety check: Pass | Custom licence | |
| Build Pluginopentabs-dev/opentabs | 967 | — | ~190 | Automated safety check: Pass | MIT | |
| Opencode Plugin Developmentsandgardenhq/sgai | 137 | — | ~1.2k | Automated safety check: Notes | Custom licence | |
| Typescript Hook Writerpr-pm/prpm | 122 | — | ~8.6k | Automated safety check: Notes | MIT |
Similar skills
OpenCode Plugin Creator
Devin-AXIS/iPolloWork
Scaffolds an OpenCode plugin for iPolloWork with the right async factory shape, zod-based tool definitions and hook registration, and explains where to place and register it.
Build Plugin
opentabs-dev/opentabs
Complete plugin development workflow: build, test, icon, troubleshoot, and setup.
Opencode Plugin Development
sandgardenhq/sgai
Guide for creating and implementing plugins to extend OpenCode functionality, including hooks, custom tools, and event handling.
Typescript Hook Writer
pr-pm/prpm
Expert guidance for developing Claude Code hooks in TypeScript with shared utilities, esbuild compilation, and Vitest testing - distributes compiled JS while maintaining TypeScript development…
Logseq Plugin SDK
logseq/logseq
Build, debug, or review Logseq plugins with the @logseq/libs SDK (TypeScript/JavaScript, iframe/shadow sandboxed).
More from ruvnet/ruflo
All 264 skills in this repoAgentDB Pattern Memory
ruvnet/ruflo
Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.
Security Audit Scanner
ruvnet/ruflo
Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.
SPARC Development Methodology
ruvnet/ruflo
Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.
Swarm Orchestration
ruvnet/ruflo
Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.
Ruflo Multi-Agent Orchestration
ruvnet/ruflo
Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.
Agent Coordination
ruvnet/ruflo
Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.
Related
Works with
Categories
Questions about Create Mod
What does Create Mod do?
Scaffold a Claude Code mod (a plugin with a function-hooks module) from ruflo's governed template — hybrid hooks.json with a classic fallback, a host adapter over literal $ calls, userConfig…. Create Mod is an agent skill from ruvnet/ruflo.json with a classic fallback, a host adapter over literal $ calls, userConfig options, engine-kit tests and a tsconfig — then validate and test it.
When should I use Create Mod?
Create Mod fits situations like: the user asks for a mod; A function hook; wants Claude Code to modify itself.
How do I install Create Mod in Claude Code?
Run `npx skills add ruvnet/ruflo --skill create-mod -a claude-code`. Or copy the skill folder (plugins/ruflo-plugin-creator/skills/create-mod in ruvnet/ruflo) into .claude/skills/create-mod in your project. Claude Code loads it when a task matches its description.
How do I install Create Mod in Codex?
Run `npx skills add ruvnet/ruflo --skill create-mod -a codex`. Or copy the skill folder (plugins/ruflo-plugin-creator/skills/create-mod in ruvnet/ruflo) into .agents/skills/create-mod in your project. Codex loads it when a task matches its description.
Can I use Create Mod in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/ruflo --skill create-mod -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-mod, .gemini/skills/create-mod, .github/skills/create-mod and .opencode/skills/create-mod in your project.
What does Create Mod need to run?
Going by SKILL.md and its folder, Create Mod needs the command-line tools its instructions call (claude and npx). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit.
Does Create Mod access the network?
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Create Mod safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Create Mod use?
Create Mod is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Create Mod use?
About 984 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Create Mod?
Skills that share tags, products or a category with Create Mod: Openpets (OpenPetsHQ/openpets, 1.3k stars), OpenCode Plugin Creator (Devin-AXIS/iPolloWork, 6.7k stars), Build Plugin (opentabs-dev/opentabs, 967 stars) and Opencode Plugin Development (sandgardenhq/sgai, 137 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Create Mod?
ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,012 GitHub stars. The repository holds 264 skills in this directory. The repository was last updated on October 7, 2026.
Source: ruvnet/ruflo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.