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 tamnguyendinh/Anvien --skill ui-be-binding-skillgit clone --depth 1 https://github.com/tamnguyendinh/AnvienWrote 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/tamnguyendinh/anvien/ui-be-binding-skill)<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/ui-be-binding-skill"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/ui-be-binding-skill/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/tamnguyendinh/anvien/ui-be-binding-skill"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/ui-be-binding-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.03256 |
| Opus 5 | $0.00017 | $0.01628 |
| Sonnet 5 | $0.00007 | $0.00651 |
| Haiku 4.5 | $0.00003 | $0.00326 |
Grade A, and why
ui-be-binding-skill 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 8d 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 — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Bind backend data into an already-approved frontend/UI without changing the approved visual output, layout, copy, component hierarchy, interaction contract, or brand presentation.
This skill exists to prevent AI coding agents from turning a polished approved UI into a cheap MVP-looking interface during backend integration.
The approved prototype is the visual authority. Backend integration is only allowed to supply data to approved UI slots.
Core Principle
Backend integration must not become UI redesign.
The agent must treat the frontend as a locked product surface. The backend may provide values, URLs, lists, flags, and actions, but it may not cause new visible UI text, new layout blocks, new explanation panels, new helper notes, new MVP/demo labels, or unapproved states to appear.
Execution Rules
- Write the UI-BE Binding Plan before coding.
- Use Anvien as the primary code-intelligence tool when working in an Anvien-indexed repo.
- Choose the Anvien command that fits the task: query, context, file-detail, impact, route-map, tool-map, shape-check, api impact, graph-health, file-hotspots, detect-changes, or other relevant commands.
- Minimum required use: refresh/analyze before graph-based work, impact before editing shared/runtime surfaces, and detect-changes before handoff or commit.
- Code only after the approved UI slots, backend fields, fallback behavior, and forbidden states are mapped.
Authority Order
In this skill, <active-plan-dir> means docs/plans/YYYY-MM-DD-<plan-name>.
Plan-owned authority artifacts live in that directory and use YYYY-MM-DD-* names.
When instructions conflict, follow this order:
- Direct user instruction for the current task
<active-plan-dir>/YYYY-MM-DD-ui-authority.md- Approved prototype HTML / approved screenshot / approved design source
<active-plan-dir>/YYYY-MM-DD-actual-wiring-status.md<active-plan-dir>/YYYY-MM-DD-ui-slot-map.md<active-plan-dir>/YYYY-MM-DD-state-map.md<active-plan-dir>/YYYY-MM-DD-visible-text.lock.json- Backend API contract / OpenAPI / schema
- Existing frontend architecture
- Existing backend architecture
- Agent implementation judgment
What ships with it
14 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.
- checklists/final-verification-checklist.md 995 B
- checklists/pre-coding-checklist.md 1.4 KB
- docs/actual-wiring-status.template.md 15 KB
- docs/backend-contract-map.template.md 1.4 KB
- docs/state-map.template.md 1.4 KB
- docs/ui-authority.template.md 1.5 KB
- docs/ui-slot-map.template.md 2.2 KB
- docs/visible-text.lock.example.json 1.1 KB
- prompts/codex-ui-be-binding-task.md 3.0 KB
- prompts/codex-ui-port-pixel-lock-task.md 1.1 KB
- README.md 3.0 KB
- reports/ui-be-binding-report.template.md 697 B
- tests/playwright/approved-ui.guard.spec.ts 1.6 KB runs code
- tests/playwright/slot-binding.guard.spec.ts 1.3 KB runs code
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.
- 8d ago First seen · 484 lines · 35 tokens per session scan A ca73672ff373
ui-be-binding-skill is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 3,256 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
supabase-nextjs
Next.js with Supabase and Drizzle ORM.
design-patterns
Agents should invoke this skill when choosing patterns, designing traits/interfaces/components, deciding abstraction boundaries, evaluating dependency injection/callbacks, or comparing implementation approaches in Rust, TypeScript/React, or Django/Python.
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
widget-coherence
Build Service Portal widgets (spwidget) with synchronized server/client/HTML — data. initialization, ng-click + controller method matching, c.server.get action handlers, and Angular directive usage.
spa-orchestrator
Orchestrates Single-Page Application (SPA) architecture, integrating frontend state management with API-driven backends / Mengorkestrasi arsitektur Single-Page Application (SPA), mengintegrasikan state management frontend dengan backend berbasis API.
fullstack-expert
Expert-level fullstack development guide covering multi-language (TypeScript, Python, Go, Rust), API design (OpenAPI 3.1, gRPC), microservices, system design patterns, and polyglot architecture / Panduan fullstack tingkat ahli mencakup multi-bahasa, desain API, microservices, dan arsitektur polyglot.