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 infohata/mind-vault --skill django-frontendgit clone --depth 1 https://github.com/infohata/mind-vaultWrote 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/infohata/mind-vault/django-frontend)<a href="https://agentmods.dev/skills/infohata/mind-vault/django-frontend"><img src="https://agentmods.dev/badge/skills/infohata/mind-vault/django-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/infohata/mind-vault/django-frontend"><img src="https://agentmods.dev/badge/skills/infohata/mind-vault/django-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 | $0.00067 | $0.12317 |
| Opus 5 | $0.00034 | $0.06159 |
| Sonnet 5 | $0.00013 | $0.02463 |
| Haiku 4.5 | $0.00007 | $0.01232 |
Grade A, and why
django-frontend scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use a `{% query_string %}` template tag wrapping `urllib.parse.urlencode()`: How it starts
The opening of the file, as written. The whole thing — 627 lines — stays where its author put it; the contents beside it link to each section on GitHub.
django-frontend
Production frontend patterns for Django using HTMX for server-driven partial swaps, Alpine.js for local client state, Bulma for styling, and Django Crispy Forms for server-rendered form markup. Philosophy: server renders HTML, HTMX swaps fragments, Alpine holds UI state, Bulma provides components — progressive enhancement, minimal JavaScript.
Pairs with: django for backend conventions. Load both on full-stack HTMX features (e.g. a view returning kb/partials/_article_list.html on HX-Request and the full page otherwise).
Stack:
| Tool | Version | Role |
|---|---|---|
| HTMX | 1.9+ (most 2.x patterns compatible) | Server-driven AJAX, partial swaps |
| Alpine.js | 3.x | Lightweight reactive components |
| Bulma CSS | 0.9+ | CSS-only component framework |
| Django Crispy Forms | 2.x+ | Server-side form rendering |
| FontAwesome | 6.x | Icons via {% fa_icon %} template tag |
Compatibility: Django 4.2+ (tested through 5.2 LTS), any database.
When to use
TRIGGER when: editing templates (*.html) in a Django project; wiring an HTMX partial endpoint; adding a Bulma modal / form / table / widget; writing an Alpine.js component; debugging htmx.process or URL-encoding issues in hx-* attributes; converting Django messages to Bulma notifications.
SKIP for: backend-only work (use django); real-time collaborative editing (WebSockets + React/Vue territory); offline-first PWAs; heavy client-side data processing; mobile native apps.
Critical hazards (read these first)
Three high-blast-radius traps that ship as user-visible regressions if you skim past them. Each has a full section below — but you need to know they exist before writing the next template line:
What ships with it
43 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.
- references/ACTIVE_STATE_TRACKING.md 3.9 KB
- references/ADVANCED_COMPONENTS.md 16 KB
- references/ALPINE_HTMX_GOTCHAS.md 38 KB
- references/ALPINE_STORE_COORDINATORS.md 12 KB
- references/APP_SHELL_LAYOUT.md 10 KB
- references/BASE_TEMPLATE.md 8.2 KB
- references/CLIENT_MARKDOWN_RENDERING.md 3.0 KB
- references/COLLAPSIBLE_PATTERNS.md 14 KB
- references/COTTON.md 34 KB
- references/CSP_INLINE_HANDLER_DELEGATION.md 7.2 KB
- references/CSS_DISPLAY_CONTENTS_SELECTOR_TRAPS.md 7.0 KB
- references/DATA_ATTR_NAV_CONVENTION.md 14 KB
- references/DELEGATED_HANDLER_STOPPROPAGATION_TRAP.md 4.1 KB
- references/DIAGNOSTIC_INSTRUMENTATION_HYGIENE.md 7.6 KB
- references/DRAWER_FORM_STATE_PRESERVATION.md 10.0 KB
- references/FILTER_FORM_TRIGGER_SINGLE_SOURCE.md 7.2 KB
- references/FORM_RENDERING_PATTERNS.md 11 KB
- references/FORMS_INDEX.md 3.6 KB
- references/HTMX_ALPINE_WAITS.md 10 KB
- references/HTMX_PATTERNS.md 24 KB
- references/HTMX_SCROLL_PRESERVATION.md 16 KB
- references/HTMX_WIDGET_LIFECYCLE.md 11 KB
- references/HTMX_WIDGETS.md 13 KB
- references/HYPHENATE_NARROW_LABELS.md 4.2 KB
- references/LAZY_LOAD_HEAVY_ASSETS_ON_HTMX_NAV.md 11 KB
- references/LISTENER_REBIND_ON_SWAP.md 7.4 KB
- references/MODAL_SYSTEM.md 6.9 KB
- references/MULTI_TENANT_PLAYWRIGHT.md 16 KB
- references/NAV_CHROME_CONSOLIDATION.md 3.4 KB
- references/PREVIEW_DRAWER_URL_STACK.md 34 KB
- references/ROUTER_ACTION_VOCABULARY.md 7.3 KB
- references/SCRIPT_TAG_JSON_ESCAPING.md 3.5 KB
- references/SCROLL_SPY_PATTERNS.md 6.4 KB
- references/SCSS_RESPONSIVE_PATTERNS.md 11 KB
- references/SCSS_VENDOR_IMPORT.md 3.6 KB
- references/SESSION_FILTER_PERSISTENCE.md 21 KB
- references/SHELL_NOTIFICATIONS.md 8.3 KB
- references/SUB_ENTITY_PRESENTATION_TIER.md 3.6 KB
- references/TEMPLATE_COMMENT_SYNTAX.md 4.9 KB
- references/VENDORING_JS_BUNDLES.md 8.2 KB
- references/VISUAL_ACUITY_TESTS_VIA_PLAYWRIGHT.md 8.4 KB
- references/VISUAL_BASELINE_BUMPS.md 8.4 KB
- VERSION 4 B
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.
- 5d ago Changed f5d2fab01976
- 9d ago First seen · 627 lines · 67 tokens per session scan A 2610eec29977
django-frontend is a skill published in the GitHub repository infohata/mind-vault (2 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 12,317 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.
tailwindcss
Tailwind CSS v4 conventions — semantic design tokens for theme-safe styling, mobile-first responsive layouts, and v4-first utilities. Use when styling components or writing className utilities with Tailwind. Don't use for plain CSS, CSS-in-JS (styled-components, emotion), or other utility frameworks.