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 agility/mcp-server --skill build-frontendgit clone --depth 1 https://github.com/agility/mcp-serverWrote 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/agility/mcp-server/build-frontend)<a href="https://agentmods.dev/skills/agility/mcp-server/build-frontend"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/build-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/agility/mcp-server/build-frontend"><img src="https://agentmods.dev/badge/skills/agility/mcp-server/build-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 | $0.00083 | $0.01004 |
| Opus 5.5 | $0.00033 | $0.00402 |
| Sonnet 5.5 | $0.00017 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
build-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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a front end on Agility CMS
Ground yourself first
- Read the project's
AGENTS.mdorCLAUDE.mdif it has one. It holds the project's conventions and instance facts. - For SDK and API details, search Agility's documentation (the Agility
Knowledgebase MCP's
search_docsandfetch_doc, if connected, or https://agilitycms.com/docs). Do not guess method names or parameters. - For a new Next.js site, start from the Agility Next.js Starter (https://github.com/agility/agilitycms-nextjs-starter) and extend its patterns.
- Before writing code against a model, read it with the Agility CMS tools
(
get_component_model_details,get_content_model_details) and use the real field names.
Add a component end to end
- List existing models (
get_component_models,get_content_models) and reuse one if it fits. - Create or update the model with the
content-modelingskill, then read it back. - Write the component following the project's existing pattern. In the Next.js starter: an async server component receives its content ID, fetches its own fields through the project's data layer, and fetches linked lists separately by reference name.
- Register it in the component registry under the model's reference name, or it renders as "not found".
- Add sample content (saved as drafts) and check it in development.
Data rules that fail silently
- List limits: content list calls return 10 items by default and at most 250
per request. Always pass
take, and page withskipuntil you have readtotalCount. - Field names arrive with only the first letter lowercased:
Titleisfields.title, butURLisfields.uRL. - Values can arrive as strings: numbers and booleans may come back as
"12"and"false"(which is truthy). Convert them in the data layer and type the converted shape. Test date fields with a time near midnight; they can shift by the instance's time zone. - Linked content depth: a field that links to a whole list can come back as a stub with only the list's reference name. Fetch the list separately, or set the link depth, according to the docs for your SDK.
- Reference names: reads return container reference names lowercased. Use the
exact case from
get_containerswhen writing. - Missing items: a deleted component can stay listed on a published page until the page is republished. Make components render nothing when their item is missing instead of throwing.
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.
- 2d ago First seen · 82 lines · 83 tokens per session scan A 16482e6c1672
build-frontend is a skill published in the GitHub repository agility/mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,004 once invoked, about $0.0003 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 2026-11-06.
build-frontend compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-frontendagility/mcp-server | Skill | 0 | 2d ago | Apache-2.0 | A | 83 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |