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 gul-labs/craftsman-marketplace --skill craft-frontendgit clone --depth 1 https://github.com/gul-labs/craftsman-marketplaceWrote 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/gul-labs/craftsman-marketplace/craft-frontend)<a href="https://agentmods.dev/skills/gul-labs/craftsman-marketplace/craft-frontend"><img src="https://agentmods.dev/badge/skills/gul-labs/craftsman-marketplace/craft-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/gul-labs/craftsman-marketplace/craft-frontend"><img src="https://agentmods.dev/badge/skills/gul-labs/craftsman-marketplace/craft-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 | $0.00137 | $0.02506 |
| Opus 5 | $0.00068 | $0.01253 |
| Sonnet 5 | $0.00027 | $0.00501 |
| Haiku 4.5 | $0.00014 | $0.00251 |
Grade A, and why
craft-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 12d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Craft
This skill encodes one engineer's standard for structuring frontend application code, applied the same way across every repo. The method and opinions live here; the project specifics (which framework, which data library, which router) are discovered from the repo — never hardcoded or assumed.
Operating principle — discover before you build
Different repos already have different conventions. Before adding anything, spend two minutes mapping what exists so you extend rather than duplicate:
package.json/ lockfile → which framework (Next.js, React, Vue, Remix)? Which data layer (@tanstack/react-query,swr, RTK Query)? Which form lib (react-hook-form, Formik)? Which state approach (Zustand, Jotai, Context, URL-as-state)?grepfor an existing API client, query key factory, or base hook — wire into it, don't fork it.- Find the routing convention (file-based, config, nested layouts) and the client/server split strategy before deciding where new code lives.
State what you found, then propose the smallest set of additions that closes the gap.
The frontend layers (build in this order)
-
Component architecture — decide the composition shape first: where are the boundaries, what is server-rendered vs client-interactive, what gets co-located vs shared. Composition over configuration: a component that accepts children and slots is more reusable than one with 20 props. See
references/architecture.md. -
State — start local (
useState), lift only when two siblings genuinely share it, reach for a global store only as a last resort. Server state (remote data) belongs in a query cache, not a store. Seereferences/state.md. -
Data fetching — use a typed client that matches the repo's existing pattern. Every fetch needs a loading state, an error state, and an empty state, all co-located with the component that owns the data. Avoid waterfall fetches: parallelize or prefetch where the router allows. See
references/data-fetching.md.
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.
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.
- 12d ago First seen · 170 lines · 137 tokens per session scan A 8e98c35f4456
craft-frontend is a skill published in the GitHub repository gul-labs/craftsman-marketplace (1 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 2,506 once invoked, about $0.0007 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
frontend-ai-guide
Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.
recipe-front-design
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-front-adjust
Adjust an already-implemented UI in-session with verification against the design source.
recipe-fullstack-implement
Orchestrate full-cycle implementation across backend and frontend layers.
recipe-front-plan
Create frontend work plan from design document and obtain plan approval.