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/uselessspace/freedeepagents-activity-builder/activity-frontendnpx skills add uselessspace/freedeepagents-activity-builder --skill activity-frontendgit clone --depth 1 https://github.com/uselessspace/freedeepagents-activity-builderWrote 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/uselessspace/freedeepagents-activity-builder/activity-frontend)<a href="https://agentmods.dev/skills/uselessspace/freedeepagents-activity-builder/activity-frontend"><img src="https://agentmods.dev/badge/skills/uselessspace/freedeepagents-activity-builder/activity-frontend.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 | $0.00095 | $0.01417 |
| Opus 5 | $0.00048 | $0.00709 |
| Sonnet 5 | $0.00019 | $0.00283 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade A, and why
activity-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 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity Frontend
<builder-root> 指从本 SKILL.md 所在目录向上两级、包含根 SKILL.md 与
tools/ 的目录；不要假定它位于目标项目的 packages/ 下。
何时用：仅
frontend_axis = static-preview或用户明确要更丰富前端时；card-only 活动跳过本步，进入/activity-review，清零 CONFLICT 后验收目录。
Use only when frontend_axis is static-preview or the user explicitly asks
for a richer frontend. Do not vendor external frontend skill source into this
package.
Before deriving or building site/, follow
../../references/node-environment.md.
Reuse Node 20 or 22 with npm 10; prefer Node 20 to mirror the runtime. Do not
install Node for a Card-only activity. When Static Preview lacks a compatible
Node, announce the download and use the bundled domestic-mirror bootstrap from
that reference instead of asking the user to discover a platform installer.
UI Type Decision
Choose one primary UI type:
utilitarian dashboardfor operational review, comparison, queues, tables, filters, and repeated work.game-like interactivefor rules, turns, progress, score, animation, and direct manipulation.visual canvasfor spatial work, drawing, layout, whiteboard, maps, or inspectable generated media.timelinefor sequences, schedules, history, milestones, or replay.graphfor networks, trees, dependencies, flow, lineage, or knowledge maps.pet/avatarfor avatar state, mood, growth, routines, or embodiment.form workflowfor intake, review, approval, multi-step configuration, or structured decision capture.
Static Preview Contract
- Source lives under
activities/<activity_type_id>/site/. - Build output is
activities/<activity_type_id>/site/dist/. vite.config.tsmust setbase: './'so/preview/<activity_type_id>/<instance_id>/works.- The frontend reads private activity DSL from
/api/dsl.jsonand can subscribe to/api/dsl/streamfor refreshes. - Agent-driven semantic navigation arrives as a named
preview_navigateevent on that same stream; it may select an activity-private route, view, or business object, but must not encode clicks, focus, scrolling, or DOM targets. See../../references/preview-navigation.md. - SPA actions that need the normal Agent runtime use structured Preview Agent
turns plus an activity-root
preview_actions.json; see../../references/preview-agent-turns.md. Direct handlers remain appropriate for deterministic data writes that do not need the Agent. - A recording UI that declares
asrchooses one public ASR path: direct multipartPOST api/asrfor an immediate transcript, orapi/uploadplus the Agent turn'sattachment_refswhen the Agent must receive current-turnfile_0. See../../references/preview-asr.md. - Agent business actions call activity-owned tools, handlers, or backend APIs;
preview_navigatenever substitutes for the business operation. Persist state first, then let DSL fetch/SSE refresh the SPA. dsl_builder.pyowns the DSL shape and may read typed-KV or activity-maintained sidecar projections frominstance_dir. It receives no database handle; a SQLite-backed SPA loads and mutates queryable records through domain handlers.handlers.pyexposes deterministic SPA reads/writes;tools.pyexposes only the business operations the Agent must call. Shared operations use one plain implementation with thin adapters.- Activity data semantics stay in
dsl_builder.py,tools.py, and activity skills. Do not add activity-specific frontend branches toapp/; keep them in the activity'ssite/.
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 · 121 lines · 95 tokens per session scan A ff30e7fc0970
activity-frontend is a skill published in the GitHub repository uselessspace/freedeepagents-activity-builder (2 stars, last pushed 18d ago), licensed MIT. It adds 95 tokens to every session and 1,417 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…
vite
Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.