component-registry

component-registry is a skill for Claude Code, Codex from bitovi/convey. It costs 39 tokens per session (476 once invoked), scanned A, original, MIT.

A living inventory of reusable user-interface components and repeated design patterns in a test application.

In plain words
What is it for?
Use it to record component locations, review patterns that could be extracted, and guide incremental refactoring.
Why use it?
It helps developers find existing components before creating duplicates and identify repeated code that should be shared.

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/bitovi/convey/component-registry
Any agent
npx skills add bitovi/convey --skill component-registry
Clone the repo
git clone --depth 1 https://github.com/bitovi/convey

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 component-registry

README.md
[![agentmods](https://agentmods.dev/badge/skills/bitovi/convey/component-registry.svg)](https://agentmods.dev/skills/bitovi/convey/component-registry)
Your own site
<a href="https://agentmods.dev/skills/bitovi/convey/component-registry"><img src="https://agentmods.dev/badge/skills/bitovi/convey/component-registry.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 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 $0.00039 $0.00476
Opus 5 $0.00019 $0.00238
Sonnet 5 $0.00008 $0.00095
Haiku 4.5 $0.00004 $0.00048

Measured 5d ago against content hash 5ab2b38a974d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

component-registry 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 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.

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.

.github/skills/component-registry/SKILL.md · 73 lines

What it actually says

Component Registry Skill

Purpose

Maintain a living inventory of UI components and patterns in the test-app to:

  • Track what components exist and where to find them
  • Identify repeated patterns that should be extracted
  • Enable incremental refactoring - each new feature cleans up before adding
  • Prevent duplication - check registry before creating new components

Registry Location

.github/skills/component-registry/REGISTRY.md


Registry Structure

Extracted Components

Components that exist as reusable, shared implementations:

### Button
- **Path**: `/test-app/src/components/Button.tsx`
- **Description**: Reusable button with variants (primary, secondary) and Tailwind classes

Potential Components (Not Yet Extracted)

Patterns that might need extraction:

### Card
- **Name**: Card
- **Description**: Container with white background, border, rounded corners, and shadow
- **Found in**: `/test-app/src/components/Card.tsx`

How to Use This Skill

When Starting a New Feature

  1. Check Registry for Existing Components - Read .github/skills/component-registry/REGISTRY.md
  2. Check for Potential Components - Review "Potential Components" section

After Implementing a Feature

  1. Add New Components - Add any new reusable components you created
  2. Note Potential Components - If you used the same inline pattern 2+ times, add it

Maintenance Commands

Scan for Repeated Patterns

grep -r 'className=".*bg-white.*rounded.*shadow' test-app/src/ -n

Count Component Usages

grep -r "import.*from.*components/" test-app/src/ | wc -l

Benefits

  • Find before creating: Check what exists before building something new
  • Spot duplication: Identify patterns that appear multiple times
  • Incremental improvement: Registry grows organically with each feature
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. 5d ago First seen · 73 lines · 39 tokens per session scan A 5ab2b38a974d

Subscribe to this mod's changes

component-registry is a skill published in the GitHub repository bitovi/convey (46 stars, last pushed 19d ago), licensed MIT. It adds 39 tokens to every session and 476 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 2026-08-30.