Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add YuDefine/nuxt-supabase-starter --skill clade-frontendgit clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote 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.
[](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/clade-frontend)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/clade-frontend"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/clade-frontend/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.
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/clade-frontend"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/clade-frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01448 |
| Opus 5.5 | $0.00014 | $0.00579 |
| Sonnet 5.5 | $0.00007 | $0.00290 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
clade-frontend 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 8d 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.
What it actually says
clade-frontend
逐條對照你接下來要做的事；條件成立才讀那一份，NEVER 先把整批讀進來。
- READ 若要讀或改
nuxt.config.*、pnpm-workspace.yaml，讀取rules/agent-devtools.md - READ 若要讀或改
app/**/*.{vue,ts}、packages/*/app/**/*.{vue,ts}、server/**/*.ts、packages/*/server/**/*.ts、test/**/*.ts、packages/*/test/**/*.ts等 9 處（全表見 rules/_index.md），讀取rules/development.md - READ 若要讀或改
server/**/*.ts、packages/*/server/**/*.ts、app/composables/**/*.ts、packages/*/app/composables/**/*.ts，讀取rules/display-value-integrity.md - READ 若要讀或改
**/composables/**rag*.ts、**/composables/**ove*.ts、**/composables/**esize*.ts、**/composables/**ort*.ts、**/components/**rag*.vue、**/composables/*schedule*/**等 7 處（全表見 rules/_index.md），讀取rules/drag-interaction.md - READ 若要讀或改
DESIGN.md、docs/decisions/**、app/**/*.{vue,ts,tsx,jsx}、packages/*/app/**/*.{vue,ts,tsx,jsx}、components/**/*.{vue,ts,tsx,jsx}、packages/*/components/**/*.{vue,ts,tsx,jsx}等 14 處（全表見 rules/_index.md），讀取rules/i18n-boundary.md - READ 若要讀或改
**/*.vue、app/**/*.ts、packages/*/app/**/*.ts、server/**/*.ts、packages/*/server/**/*.ts、composables/**等 13 處（全表見 rules/_index.md），讀取rules/nuxt-data-perf.md - READ 若要讀或改
nuxt.config.*、vite.config.*、package.json、scripts/dev-session*、vendor/scripts/dev-session*，讀取rules/nuxt-dev-watch.md - READ 若要讀或改
app/**/*.vue、packages/*/app/**/*.vue、components/**/*.vue、packages/*/components/**/*.vue、pages/**/*.vue、packages/*/pages/**/*.vue，讀取rules/nuxt-error-localization.md - READ 若要讀或改
app/**/*.vue、packages/*/app/**/*.vue、components/**/*.vue、packages/*/components/**/*.vue、pages/**/*.vue、packages/*/pages/**/*.vue，讀取rules/nuxt-form-validation.md - READ 若要讀或改
app/**/*.vue、packages/*/app/**/*.vue、components/**/*.vue、packages/*/components/**/*.vue、layouts/**/*.vue、packages/*/layouts/**/*.vue等 8 處（全表見 rules/_index.md），讀取rules/nuxt-overlay-slot.md - READ 若要讀或改
app/**/*.vue、packages/*/app/**/*.vue、pages/**/*.vue、packages/*/pages/**/*.vue、components/**/*.vue、packages/*/components/**/*.vue等 12 處（全表見 rules/_index.md），讀取rules/nuxt-review-bans.md - READ 若要讀或改
nuxt.config.ts，讀取rules/nuxt-security.md - READ 若要讀或改
app/**/*.vue、packages/*/app/**/*.vue、pages/**/*.vue、packages/*/pages/**/*.vue、components/**/*.vue、packages/*/components/**/*.vue等 8 處（全表見 rules/_index.md），讀取rules/nuxt-ui-conventions.md - READ 若要讀或改
app/**/*.{vue,ts}、packages/*/app/**/*.{vue,ts}、pages/**/*.vue、packages/*/pages/**/*.vue、components/**/*.vue、packages/*/components/**/*.vue等 15 處（全表見 rules/_index.md），讀取rules/nuxt-ui-mcp.md - READ 若要讀或改
app/**/*.{vue,ts}、packages/*/app/**/*.{vue,ts}、pages/**/*.vue、packages/*/pages/**/*.vue、components/**/*.vue、packages/*/components/**/*.vue等 8 處（全表見 rules/_index.md），讀取rules/nuxt-ui-native-picker-ban.md - READ 若要讀或改
app/app.vue、packages/*/app/app.vue、app/pages/**/*.vue、packages/*/app/pages/**/*.vue、pages/**/*.vue、packages/*/pages/**/*.vue等 12 處（全表見 rules/_index.md），讀取rules/page-loading-golden-path.md - READ 若要讀或改
tasks/**、specs/plans/**、app/**/*.vue、packages/*/app/**/*.vue、shared/types/**/*.ts、packages/*/shared/types/**/*.ts等 7 處（全表見 rules/_index.md），讀取rules/runtime/ux-completeness.md - READ 若要讀或改
app/**/*.vue、packages/*/app/**/*.vue、app/**/*.ts、packages/*/app/**/*.ts、components/**、packages/*/components/**等 15 處（全表見 rules/_index.md），讀取rules/ui-copy-tone.md - READ 若要讀或改
tasks/**、specs/plans/**、app/**/*.vue、packages/*/app/**/*.vue、shared/types/**/*.ts、packages/*/shared/types/**/*.ts等 7 處（全表見 rules/_index.md），讀取rules/ux-completeness.md
rule 內文只經本 skill 載入；清單不能代替內文。
What ships with it
20 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.
- rules/_index.md 5.4 KB
- rules/agent-devtools.md 4.0 KB
- rules/development.md 7.1 KB
- rules/display-value-integrity.md 7.3 KB
- rules/drag-interaction.md 4.7 KB
- rules/i18n-boundary.md 2.5 KB
- rules/nuxt-data-perf.md 22 KB
- rules/nuxt-dev-watch.md 5.4 KB
- rules/nuxt-error-localization.md 1.6 KB
- rules/nuxt-form-validation.md 1.6 KB
- rules/nuxt-overlay-slot.md 3.9 KB
- rules/nuxt-review-bans.md 7.0 KB
- rules/nuxt-security.md 7.7 KB
- rules/nuxt-ui-conventions.md 4.3 KB
- rules/nuxt-ui-mcp.md 14 KB
- rules/nuxt-ui-native-picker-ban.md 4.9 KB
- rules/page-loading-golden-path.md 6.2 KB
- rules/runtime/ux-completeness.md 994 B
- rules/ui-copy-tone.md 9.0 KB
- rules/ux-completeness.md 19 KB
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.
- 8d ago Changed · +1 lines f84dd7f89baf
- 15d ago Changed 9ceaa3040b20
- 17d ago Changed · +21 lines 78a48f39feac
- 1mo ago First seen · 9 lines · 36 tokens per session scan A be5166a7ceea
clade-frontend is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,448 once invoked, about $0.0001 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 2026-09-13.
Other skills, from other repositories
prd-v07-implementation-loop
Execute implementation within EPICs following test-first development, continuous SoT updates, and code traceability during PRD v0.7 Build Execution. Triggers on requests to start building, implement an epic, begin coding, or when user asks "start building", "implement epic", "coding", "development", "build execution"…
prd-v07-test-planning
Define test cases BEFORE implementation, ensuring every API, business rule, and user journey has verifiable acceptance criteria during PRD v0.7 Build Execution. Triggers on requests to define tests, plan test coverage, create test cases, or when user asks "define tests", "test planning", "what to test?", "test cases"…
localization-pipeline
Prepare the project for translation, cultural adaptation, text expansion, and voice or subtitle variability.
the-i18n-kit
Manage translations with the-i18n-kit MCP tools — find missing or dead keys, translate, rename across locales. Use when working with i18n, translations, locale files, or translation keys in a project configured for the-i18n-kit.
i18n
A guide to preparing software for multiple languages and regional settings. This includes translated text, date and number formats, plural rules, and right-to-left layouts.
i18n
Audit Flutter code for hardcoded strings, write clear user-friendly text following UX guidelines, and migrate strings to i18n files. Use when checking localization, finding hardcoded text, improving string clarity, writing error messages, button labels, or any user-facing text.