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 agentmods add skills/aneja5/forge-skills/component-librarynpx skills add aneja5/forge-skills --skill component-librarygit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/component-library)<a href="https://agentmods.dev/skills/aneja5/forge-skills/component-library"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/component-library.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01637 |
| Opus 5 | $0.00022 | $0.00818 |
| Sonnet 5 | $0.00009 | $0.00327 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
component-library 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Component Library
Overview
Catalog every component the product needs before the build sprint — props, states, responsive behavior, accessibility, composition rules, and microcopy. Output is .forge/component-library.md. Inherits tokens from design-system, behaviors from interaction-patterns, and voice + icons from brand-and-identity. Consumed by page-composition, data-visualization, and every UI build task.
When to Use
- A major UI build sprint is starting and no component catalog exists
- Two engineers are about to build a
Button/Card/Modalindependently - The codebase has 3 different
Buttoncomponents with different APIs - A new domain-specific component (
ScoreCard,RepCard,CallTimeline) is being designed - A redesign is replacing shadcn defaults with domain-shaped components
When NOT to Use
- A single one-off component for one screen —
incremental-implementation - Backend-only services
- The product genuinely doesn't have a UI yet — establish
design-systemandinteraction-patternsfirst
Common Rationalizations
| Thought | Reality |
|---|---|
| "We'll extract components as we go" | Extraction after the fact means 3 versions of Button with different APIs. Catalog first, build once. |
| "This is premature abstraction" | A component catalog is not abstraction. It's a vocabulary. You define words before writing sentences. |
| "Just use shadcn and move on" | shadcn gives generic components. ScoreCard, RepCard, CallTimeline are domain-specific — those need defining. |
| "Props can evolve" | Props that evolve without a catalog diverge. One engineer adds size, another adds isLarge. The catalog prevents this. |
| "We don't need a loading state for that component" | Every async component lies about readiness without a loading state. |
Red Flags
- Two components doing the same job under different names (
ButtonandActionButton,CardandPanel) - A component with 15+ props — it's two components fused
- A component without a
loadingoremptystate - Hardcoded strings inside a component instead of prop-driven microcopy
- No accessibility attributes (
role,aria-*) on interactive components - A component accepting
classNameas a token-override escape hatch
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.
- yesterday First seen · 110 lines · 43 tokens per session scan A c360901e49d2
component-library is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,637 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
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.