Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Just-Agent/just-progress-bar-skillnpx agentmods add skills/just-agent/just-progress-bar-skill/skillWrote 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/just-agent/just-progress-bar-skill/skill)<a href="https://agentmods.dev/skills/just-agent/just-progress-bar-skill/skill"><img src="https://agentmods.dev/badge/skills/just-agent/just-progress-bar-skill/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/just-agent/just-progress-bar-skill/skill"><img src="https://agentmods.dev/badge/skills/just-agent/just-progress-bar-skill/skill.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00039 | $0.01491 |
| Opus 5.5 | $0.00016 | $0.00596 |
| Sonnet 5.5 | $0.00008 | $0.00298 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
just-progress-bar-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 1mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
just-progress-bar-skill
Use this Skill when a user asks for a progress bar, loader, upload state, download button, checkout flow, media scrubber, circular metric, game loading UI, dashboard progress, or an accessibility audit for progressbar markup.
What this Skill does
- Selects a suitable progress bar pattern from the 24-item catalog.
- Generates React or HTML/CSS source from catalog IDs, prompts, or recipe JSON files.
- Explains design tokens and props.
- Audits accessibility: label, semantics, determinate values, indeterminate behavior, status text, and reduced motion.
- Helps other Agents integrate the catalog through MCP-style tools and resources.
- Uses Roadmap-driven iteration when modifying this repository: completed work must be checked in
ROADMAP.mdand recorded in logs.
When to use
Use this Skill for:
- loading, uploading, downloading, installing, processing, generating, checking out, onboarding, media playback, game loading, dashboard metrics, or status feedback;
- requests that mention creative progress bars,
progressbar,aria-valuenow,prefers-reduced-motion, React progress components, HTML/CSS snippets, recipes, CLI generation, or MCP tools; - repository iteration work for
Just-Agent/just-progress-bar-skill.
Do not use it for unrelated charts, full data dashboards, third-party visual asset copying, or copyrighted Dribbble/PSD replication.
Pattern selection
Use these defaults:
| User request | Preferred catalog ID | Reason |
|---|---|---|
| Upload/build progress | gradient-loading |
Clear determinate status with easy value display. |
| Download CTA | download-button |
Combines action and progress feedback. |
| Checkout/order flow | order-steps |
Step semantics are easier to understand than a raw bar. |
| Unknown wait time | gradient-loading with indeterminate: true |
Indeterminate progress should omit aria-valuenow. |
| Neon / sci-fi | neon-ring or lightsaber |
Strong visual identity for AI/generation flows. |
| Game loading | cute-game-loading |
Playful loading pattern. |
| Media playback | music-player or player-progress |
Timeline/scrubber model. |
| Dashboard metric | circular-dashboard |
Compact KPI ring. |
| Emotional waiting state | happy-heart |
Soft waiting state. |
| Vertical dashboard rail | vertical-progress |
Fits side panels and cards. |
What ships with it
10 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.
- package.json 949 B
- resources/accessibility-checklist.md 510 B
- resources/catalog.json 72 KB
- resources/catalog.md 1.4 KB
- resources/component-selection-guide.md 799 B
- resources/mcp-tooling.md 1.6 KB
- resources/prompt-recipes.md 1.3 KB
- scripts/audit-progressbar.mjs 1.6 KB runs code
- scripts/generate-progressbar.mjs 2.1 KB runs code
- scripts/smoke-package.mjs 610 B 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.
- 1mo ago First seen · 157 lines · 39 tokens per session scan A 954b88aafb85
just-progress-bar-skill is a skill published in the GitHub repository Just-Agent/just-progress-bar-skill (17 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,491 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
modern-site-engineering
Integrate systems after frontend direction.
cinematic-scroll
Design and build cinematic websites, 3D websites, interactive portfolios and product landing pages with scroll-driven storytelling, parallax, text animation and optional Three.js/WebGL scenes. Use for new experiences, motion improvements, scroll audits and storyboards in standalone HTML or an existing app. Includes…
react-responsive-components
Implement size-dependent behavior/geometry.
ui-forge
Build or improve visually distinctive, product-specific web interfaces, from brand pages to working apps and components. Use for frontend implementation, redesign, reference-led builds, or improving generic-looking UI. Preserve existing behavior and design systems. Review without editing when asked for an audit; skip…
product-motion-design
Design, implement, audit, or repair purposeful motion for React and web interfaces, including GSAP timelines, scroll choreography, micro-interactions, and optional Three.js scenes, with cleanup, responsive behavior, reduced-motion support, and browser verification.
frontend-code-review
Review React, Next.js App Router, TypeScript, Tailwind CSS, shadcn/ui, TanStack Query, and frontend UI code. Use when reviewing a PR, branch, diff, page, component, hook, Server Action, route handler, or API client; debugging frontend behavior; assessing production readiness; or checking runtime bugs, client/server…