backlog-ui-framework

backlog-ui-framework is a skill for Claude Code, Codex from gkoreli/backlog-mcp. It costs 74 tokens per session (2,068 once invoked), scanned A, original, MIT.

Coding rules for reactive web components in the backlog viewer, using `@nisli/core` to update interface elements when their state changes.

In plain words
What is it for?
Creating, reviewing, migrating, and testing viewer components, including signals, templates, dependency injection, data queries, typed events, and error handling.
Why use it?
They help developers follow the viewer’s established patterns and avoid problems such as stale displays, unsafe templates, memory leaks, or broken data loading.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gkoreli/backlog-mcp/backlog-ui-framework
Any agent
npx skills add gkoreli/backlog-mcp --skill backlog-ui-framework
Clone the repo
git clone --depth 1 https://github.com/gkoreli/backlog-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for backlog-ui-framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/gkoreli/backlog-mcp/backlog-ui-framework.svg)](https://agentmods.dev/skills/gkoreli/backlog-mcp/backlog-ui-framework)
Your own site
<a href="https://agentmods.dev/skills/gkoreli/backlog-mcp/backlog-ui-framework"><img src="https://agentmods.dev/badge/skills/gkoreli/backlog-mcp/backlog-ui-framework.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,068 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.02068
Opus 5 $0.00037 $0.01034
Sonnet 5 $0.00015 $0.00414
Haiku 4.5 $0.00007 $0.00207

Measured 4d ago against content hash d6646c67ddd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backlog-ui-framework 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 4d 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.

.agents/skills/backlog-ui-framework/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backlog UI Framework — Agent Skill

Comprehensive guide for building reactive web components using @nisli/core. Contains rules across 9 categories covering component authoring, reactivity, templates, dependency injection, events, data loading, error handling, migration, and testing.

When to Apply

Reference these guidelines when:

  • Creating new web components in viewer/components/
  • Migrating existing HTMLElement-based components to the reactive framework
  • Writing or reviewing signal-based reactive state
  • Implementing html tagged templates with bindings and @event handlers
  • Using inject() / provide() for dependency injection
  • Setting up query() for declarative data loading
  • Wiring typed Emitter events between components
  • Reviewing code for memory leaks, XSS, or lifecycle issues
  • Writing tests for framework components

Rule Categories by Priority

Priority Category Impact Prefix
1 Component Authoring CRITICAL comp-
2 Signals & Reactivity CRITICAL signal-
3 Template Engine HIGH tmpl-
4 Dependency Injection HIGH di-
5 Typed Emitters MEDIUM-HIGH emitter-
6 Declarative Data Loading MEDIUM-HIGH query-
7 Error Handling & Resilience MEDIUM error-
8 Migration & Interop MEDIUM migration-
9 Testing LOW-MEDIUM test-

Quick Reference

1. Component Authoring (CRITICAL)

  • comp-setup-sync - Setup function MUST be synchronous; capture services sync, use them async
  • comp-props-signals - All props are Signal<T> in setup; factories accept T | Signal<T> inputs
  • comp-factory-composition - ALL custom elements MUST use factory composition; HTML tag syntax is ONLY for native elements (div, span, button)
  • comp-html-for-vanilla - HTML tag syntax (<tag>) is ONLY for native HTML elements; never for custom elements
  • comp-no-this - No this in components; use pure functions with props and host
  • comp-no-innerhtml - Never use innerHTML; use html tagged templates for targeted DOM patching
  • comp-host-escape-hatch - host is the second param; use it only for imperative DOM access
  • comp-no-class-authoring - Never extend HTMLElement directly for new components; use component()
  • comp-host-attrs - Use second factory arg { class: '...' } for host-level CSS classes (ADR 0009)
  • comp-prop-input - Factory props accept T | Signal<T> — plain values are auto-wrapped (ADR 0009)

Read the full file on GitHub · 141 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 4d ago First seen · 141 lines · 74 tokens per session scan A d6646c67ddd2

Subscribe to this mod's changes

backlog-ui-framework is a skill published in the GitHub repository gkoreli/backlog-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,068 once invoked, about $0.0004 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.