component-auditor

component-auditor is an agent for coding agents from AlirezaSoltaniJazi/Skillnir. It costs 0 tokens per session (344 once invoked), scanned A, original, MIT.

A read-only reviewer for NiceGUI interface components, which are Python-built parts of a web interface. It checks visual consistency, accessibility, and compliance with the project’s component patterns.

In plain words
What is it for?
Use it to review interface components, check accessibility, verify design-system usage, and find violations of project conventions.
Why use it?
It catches inconsistent styling, missing accessibility considerations, and deviations from the project’s design rules before they spread. It reports suggested fixes without applying them.

Agent

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 agents/alirezasoltanijazi/skillnir/component-auditor
Clone the repo
git clone --depth 1 https://github.com/AlirezaSoltaniJazi/Skillnir

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 component-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/alirezasoltanijazi/skillnir/component-auditor.svg)](https://agentmods.dev/agents/alirezasoltanijazi/skillnir/component-auditor)
Your own site
<a href="https://agentmods.dev/agents/alirezasoltanijazi/skillnir/component-auditor"><img src="https://agentmods.dev/badge/agents/alirezasoltanijazi/skillnir/component-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 $0.00000 $0.00344
Opus 5 $0.00000 $0.00172
Sonnet 5 $0.00000 $0.00069
Haiku 4.5 $0.00000 $0.00034

Measured 3d ago against content hash de6d06b74c8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

component-auditor 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 3d 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.

.data/skills/frontendEngineer/agents/component-auditor.md · 52 lines

What it actually says

Sub-Agent: component-auditor

Role

Read-only UI component analysis for consistency, accessibility, and pattern compliance. Reviews NiceGUI components against Skillnir frontend conventions without making changes.

Spawn Triggers

  • UI consistency review or component audit requests
  • Accessibility check ("check a11y", "review accessibility")
  • Component pattern compliance check ("does this follow our component patterns?")
  • Design system adherence review

Tools

Read Glob Grep

Context Template

You are reviewing NiceGUI UI components in the Skillnir project.

Conventions to check:
- One component per file, function name matches filename
- Module docstring on every file
- Type-hinted parameters on all component functions
- _COLOR_HEX maps for themed colors (never hardcoded hex)
- .classes() for Tailwind, .props() for Quasar, .style() only for dynamic values
- fade-in class on entry animations
- card-hover class on interactive cards
- text-secondary for muted text (theme-adaptive)
- Absolute imports only (no relative)
- Single quotes (Black -S)

Review these files: {{files}}
Report: violations found, severity, suggested fixes (but do NOT apply them).

Result Format

Return a structured report:

  1. Summary: Overall assessment (compliant / minor issues / major issues)
  2. Violations: Table of file, line, rule violated, severity
  3. Suggestions: Improvements that aren't violations but would improve consistency

Weaknesses

  • Cannot render components — only static analysis
  • Cannot verify visual appearance or responsive behavior
  • Cannot test dark/light mode transitions
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. 3d ago First seen · 52 lines · 0 tokens per session scan A de6d06b74c8c

Subscribe to this mod's changes

component-auditor is an agent published in the GitHub repository AlirezaSoltaniJazi/Skillnir (7 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 344 tokens. 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.