wefa: Skill for Codex

.agents/skills/wefa-vue-cookbook/SKILL.md

wefa-vue-cookbook is a skill for Codex from n-side-dev/wefa. It costs 109 tokens per session (1,249 once invoked), scanned A, original, Apache-2.0.

A shared set of conventions for building Vue interfaces in the WeFa ecosystem, a component library built on PrimeVue and Tailwind CSS. It covers component reuse, layout, translation, and related frontend choices.

In plain words
What is it for?
Use it when building or maintaining Vue features with @nside/wefa, choosing between WeFa, PrimeVue, and native HTML, or handling translated interface text.
Why use it?
It gives consuming applications and the WeFa library consistent decisions about which components and patterns to use.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is n-side-dev/wefa's own configuration. It tells Codex how to work on wefa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wefa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to n-side-dev/wefa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/n-side-dev/wefa/main/.agents/skills/wefa-vue-cookbook/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/n-side-dev/wefa

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wefa-vue-cookbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/n-side-dev/wefa/wefa-vue-cookbook/github.svg)](https://agentmods.dev/skills/n-side-dev/wefa/wefa-vue-cookbook)
Your own site
<a href="https://agentmods.dev/skills/n-side-dev/wefa/wefa-vue-cookbook"><img src="https://agentmods.dev/badge/skills/n-side-dev/wefa/wefa-vue-cookbook/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for wefa-vue-cookbook

Your own site · 80×15
<a href="https://agentmods.dev/skills/n-side-dev/wefa/wefa-vue-cookbook"><img src="https://agentmods.dev/badge/skills/n-side-dev/wefa/wefa-vue-cookbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,249 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.01249
Opus 5.5 $0.00044 $0.00500
Sonnet 5.5 $0.00022 $0.00250
Haiku 4.5 $0.00011 $0.00125

Measured 2mo ago against content hash 3313c70db1eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wefa-vue-cookbook scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/wefa-vue-cookbook/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WeFa Vue Cookbook

This is the shared Vue skill for WeFa.

Use it in two situations:

  1. In consuming Vue projects that use @nside/wefa.
  2. Inside the WeFa vue/ package for the shared conventions that also apply to the library itself.

When the task is inside the WeFa vue/ package, pair this skill with wefa-vue-frontend, which is the maintainer skill for repo-specific export, docs, demo, generated-artifact, and quality-gate work.

Use this skill in two layers:

  1. Keep this SKILL.md loaded for the always-on rules.
  2. Load only the matching reference file when the task needs deeper checks.

Always-Loaded Rules

  1. Treat @nside/wefa as a PrimeVue superset styled through Tailwind 4 with tailwindcss-primeui.
  2. Follow the reuse hierarchy strictly: WeFa component/container -> PrimeVue composition -> native HTML fallback.
  3. Start by mirroring the nearest existing local pattern before inventing a new abstraction, prop API, fetch flow, or styling approach.
  4. Before adding helpers or infrastructure, check whether the current app, WeFa, or PrimeVue already provides the needed building block.
  5. Keep user-facing text translated through i18n keys, including labels, placeholders, validation copy, aria-label, and title.
  6. Prefer Tailwind utilities for routine styling. Use flex by default for layout, reach for grid when it clearly fits better, and do not add new CSS imports or routine <style> blocks.
  7. For server state, prefer typedApiClient when an OpenAPI-generated callable exists, then apiClient for straightforward URL-based GET or POST flows, then direct TanStack Query hooks only when the wrappers cannot model the behavior cleanly, then raw axiosInstance only for lower-level infrastructure or non-query-managed calls.
  8. TanStack Query already covers most fetch lifecycle, caching, retries, invalidation, and mutation state. Prefer built-in query and cache features over hand-rolled refs, watches, loading flags, or manual cache synchronization.
  9. Treat TanStack query data as immutable. Copy it before binding to v-model or mutating it locally.
  10. Put every changing query dependency into the query key, and avoid unwrapping reactive inputs too early if the query should react to them.
  11. Parent components own external layout and sizing context. Reusable children should not assume fill behavior or decorative outer chrome unless that is part of their explicit contract.
  12. When shared or public-facing behavior changes, update the surrounding tests, docs, and usage examples expected by that codebase.
  13. Run the validation commands that match the host project and the risk of the change. If working inside the WeFa repo, wefa-vue-frontend adds the exact repo gate.

Read the full file on GitHub · 79 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 79 lines · 109 tokens per session scan A 3313c70db1eb

Subscribe to this mod's changes

wefa-vue-cookbook is a skill published in the GitHub repository n-side-dev/wefa (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,249 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

wefa-vue-cookbook compared with skills from other repositories

wefa-vue-cookbook next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wefa-vue-cookbookn-side-dev/wefaSkill112d agoApache-2.0A109Codex
shadcn-sveltevercel-labs/json-renderSkill19kyesterdayApache-2.0A63Claude Code, Codex
add-localizationmicrosoft/power-platform-skillsSkill1.1kyesterdayMITA69Claude Code
vue-router-best-practicesvuejs-ai/skillsSkill3.3k14d agoMITA25Claude Code, Codex
moai-domain-uiuxmodu-ai/moai-adkSkill1.3k3d agoApache-2.0A49Claude Code
moai-domain-frontendmodu-ai/moai-adkSkill1.3k3d agoApache-2.0A54Claude Code
frontend-conventionsfpindej/netrockSkill2354d agoMITA27Claude Code