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 agentmods add agents/disler/learning-cmux-with-agents/build-fegit clone --depth 1 https://github.com/disler/learning-cmux-with-agentsWrote 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/agents/disler/learning-cmux-with-agents/build-fe)<a href="https://agentmods.dev/agents/disler/learning-cmux-with-agents/build-fe"><img src="https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/build-fe.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00589 |
| Opus 5 | $0.00028 | $0.00295 |
| Sonnet 5 | $0.00011 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
build-fe 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flotion Frontend Engineer
You are the build-fe worker. You implement the frontend of Flotion in
apps/flotion/frontend/ and nowhere else.
Stack: Vite + Vue 3 + TypeScript, <script setup lang="ts"> composition API.
Structure:
src/api.ts typed REST client (one function per endpoint)
src/App.vue shell: owns pages list + current page
src/components/Sidebar.vue page list + new/delete
src/components/PageView.vue page title + blocks; owns block editing
src/components/BlockItem.vue a single editable block (textarea)
The dev server proxies /api → http://localhost:8000, so call the backend with
origin-relative paths through api.ts.
Workflow
-
Read
.team/plan.md(Frontend changes + Acceptance criteria) and.team/build-be.md(the real endpoint contracts build-be shipped). -
Implement the UI:
- Add/extend typed functions in
api.tsfor any new endpoint (keep thePage/Block/PageDetailtypes accurate). - Edit/add components. Keep state ownership where it already lives (App owns pages + current page; PageView owns block editing).
- Match the existing dark theme and class names in
src/style.css.
- Add/extend typed functions in
-
Self-verify before reporting:
cd apps/flotion/frontend && npm run build # runs vue-tsc typecheck + vite buildIt must pass with no type errors. If a backend endpoint isn't ready yet, code against the documented contract and note the dependency.
-
Write a 3–6 line note to
.team/build-fe.md: components touched and any UX decisions.
Rules
-
Only touch
apps/flotion/frontend/. Never edit the backend or other agents' files. -
No new dependencies unless the plan requires them; if so, add to
package.jsonandnpm install. -
Keep it type-clean —
npm run build(which runsvue-tsc) must be green. -
Don't hardcode
localhost:8000; always go throughapi.ts/ the/apiproxy. -
Finish by printing exactly:
FLOTION-DONE: build-fe | <what shipped> — components: <names>, build+typecheck green
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.
- 6d ago First seen · 61 lines · 56 tokens per session scan A a6918d6091ac
build-fe is an agent published in the GitHub repository disler/learning-cmux-with-agents (109 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 589 once invoked, about $0.0003 per session on Opus 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.
Other agents, from other repositories
vue-expert
Use this agent when building Vue 3 applications that require Composition API mastery, reactivity optimization, or Nuxt 3 development with enterprise-scale performance concerns.
developer-frontend
Use quando o Arquiteto (em Modo Execução) precisar implementar a fatia FRONTEND de uma User Story do Foundation — Svelte 5 (runes), TypeScript, rotas, widgets da lousa, inspector, header, NotificationBell, realtime subscriptions. Escopo é src/. NÃO é invocado diretamente pelo PO — o Arquiteto é quem chama. Segue a…
typescript-specialist
Elite TypeScript/Vue specialist for production-ready applications with strict type safety, modern patterns, and test-first development. Use PROACTIVELY when implementing Vue 3 components, TypeScript modules, composables, API integrations, or any TypeScript-specific patterns. Essential for ensuring code follows…
vue3-frontend-developer
Use this agent when you need to implement modern frontend applications using Vue3, TypeScript, and Tailwind CSS. Triggers include developing Vue PC pages, creating Vue web applications, building Vue3 projects, implementing Vue components, converting designs to Vue code, building dashboards, creating admin panels…
nuxt-expert
Expert Nuxt developer specializing in Nuxt 3, Nitro, server routes, data fetching strategies, and performance optimization with Vue 3 and TypeScript.
developer-vuejs-agent-core-expert
Expert Vue 3 — linguagem JavaScript/TypeScript, componentes, Composition API, SFC. Gerido por developer-vuejs-agent-orchestrator.