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 skills/nonlinear-xyz/factory-kit/factory-frontend-engineernpx skills add nonlinear-xyz/factory-kit --skill factory-frontend-engineergit clone --depth 1 https://github.com/nonlinear-xyz/factory-kitWrote 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/nonlinear-xyz/factory-kit/factory-frontend-engineer)<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-frontend-engineer"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-frontend-engineer.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 | $0.00098 | $0.01526 |
| Opus 5 | $0.00049 | $0.00763 |
| Sonnet 5 | $0.00020 | $0.00305 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
factory-frontend-engineer 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply the frontend-engineer specialist workflow. Scaffold UI surfaces grounded in the factory's CRUD conventions, not generic React. Load factory-frontend, factory-design, and factory-stack through the host's skill capability when needed. factory-design owns visual coherence; factory-frontend owns CRUD shape.
How to think (in order)
-
What surface is this? Restate the request in one sentence. Pick one:
- List (queue of entities; filter/sort/paginate)
- Detail (one entity's full view)
- Form (create/edit, including multi-step)
- Dashboard (rollup/chart heavy)
- Hybrid — name it and split into two surfaces if you can.
-
Is this CRUD? If yes, the default shape is DataTable + drawer with mode union. Don't deviate without naming why. The drawer mode is the tagged union
{kind:'closed'}|{kind:'create'}|{kind:'edit'; entity}. The drawer edits only the clicked target; relations open their own drawers. -
Which component library? Check the project's
CLAUDE.mdorDECISIONS.md. If unset:- Mantine when CRUD-heavy / internal tool / form-table dense. Pair with
@mantine/form+schemaResolver. - shadcn when there's a marketing site, design flexibility matters, or Tailwind muscle memory dominates. Pair with
react-hook-form+zodResolver. - Flag the choice in your output if you had to make it.
- Mantine when CRUD-heavy / internal tool / form-table dense. Pair with
-
What primitives already exist? Before writing anything new, check:
src/components/datatable/— DataTable, RowActions, ColumnDef, ValidationRulessrc/lib/format.ts— formatCurrency, formatInteger, formatPercentsrc/components/PageHeader.tsx/CardHeader.tsx/FormSection.tsx— heading tierssrc/features/<sibling>/— peer feature folders for the colocated shape- If a primitive is missing where it should exist, create it first — don't inline. Single source.
-
What's the schema shape? Three Zod variants for a CRUD entity:
- Input schema — server-side strict (UUIDs are UUIDs, no empty strings)
- Form schema — client-side lenient (empty-string defaults,
nullable().or(literal(''))) - Patch schema — partial input for updates (
input.partial()or.pick({})per field) - All three live in
features/<entity>/schema.ts.
-
What's the data path? Default: server action wrapped by TanStack Query mutation. tRPC only if the project already commits to it.
- Action in
features/<entity>/actions.tswith"use server"directive - Hook in
features/<entity>/hooks.tswrapping the action withuseMutation - Query keys:
['entity', 'list', filters]/['entity', 'detail', id] - Invalidate at
['entity']after mutations.
- Action in
-
What conventions must hold?
- Semantic tokens only — consume named tokens (
bg,surface,fg,fg-muted,accent,border, etc. — seefactory-design.md). No hex literals in components, ever. Nodark:variants on individual elements — let CSS-var swap handle modes. - Format helpers from
src/lib/format.ts— never inline currency math. - Tier components — PageHeader / CardHeader / FormSection. Never freeform
<h1>/<h2>. - Empty + error + loading states — required, not optional.
- Feature folders are peers — code in
features/cases/doesn't import fromfeatures/products/. Shared logic goes tolib/.
- Semantic tokens only — consume named tokens (
-
What's the smallest correct change? If asked for a table, build the table — don't redesign the whole space. If a change implies redesigning something else, name it and stop.
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 · 110 lines · 98 tokens per session scan A 5c0ba0671a51
factory-frontend-engineer is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,526 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
check-environment
Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.
doc-writer
Documentation templates and standards: README structure, API reference format, changelog (Keep a Changelog), and comment guidelines. Use when creating or updating documentation. Loaded automatically by the doc-writer agent.
smart-commit
Create clean Conventional Commits: inspect the diff, group related changes, run quality checks, and write type(scope) messages. Use when committing work, or when the user runs /smart-commit or asks to commit changes.