Cline is an open-source coding agent that runs in terminals and code editors, where it can create files, execute commands, browse the web, and use tools with human approval. It is used through a CLI, VS Code extension, JetBrains plugin, web task board, or SDK for building agent integrations. The catalogue add-ons extend Cline with skills, agents, commands, instructions, settings, and hooks.
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 skills add cline/cline --skill desktop-whats-newgit clone --depth 1 https://github.com/cline/clineWrote 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/cline/cline/desktop-whats-new)<a href="https://agentmods.dev/skills/cline/cline/desktop-whats-new"><img src="https://agentmods.dev/badge/skills/cline/cline/desktop-whats-new/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/cline/cline/desktop-whats-new"><img src="https://agentmods.dev/badge/skills/cline/cline/desktop-whats-new.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 | $0.00095 | $0.01424 |
| Opus 5.5 | $0.00038 | $0.00570 |
| Sonnet 5.5 | $0.00019 | $0.00285 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade A, and why
desktop-whats-new 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 15d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desktop "What's new" catch-up
Use this skill when the user asks to show desktop users what's new, catch users up on recent updates, publish a what's-new modal, or refresh the highlights in Settings → About.
Working directory: run every command below from the repository root.
The desktop app ships every couple of days, so individual releases are never announced in-app; Settings → About always lists the bundled release notes. A catch-up is the exception: once enough notable features have accumulated, one dialog shows them, once, on the first launch after the update that carries it. Publishing one is a content change in a single file plus a preview, nothing else.
How it works
- Content lives in
apps/examples/desktop-app/webview/lib/whats-new-content.tsasWHATS_NEW_RELEASES, newest first. Each entry has a stableid, atitle, and 3–4highlights(title,description, lucideicon). webview/lib/whats-new.tsstores the last seenidin localStorage (cline.code.whats-new.v1). The app shell (webview/app/page.tsx) showsWhatsNewDialogwhen the newest id differs from the stored one; closing it, or clicking "See all changes", stores the id.- Fresh installs never see a catch-up: completing onboarding marks the newest entry seen.
- Settings → About has a "Show what's new" button that replays the newest entry without marking it seen. That is the preview path.
- The dialog (
webview/components/whats-new-dialog.tsx) is fixed: violet hero with an eyebrow and headline, a 2×2 grid of highlights, footer with "See all changes" and "Get Started". Do not add per-entry layout options, images, or extra buttons; keep it a content change. The one exception is aspotlightentry (currently only"connectors"): a launch big enough to carry the dialog alone, with its own body and call to action in the dialog. Only add a new spotlight when the team explicitly asks for one.
Workflow
- Decide whether a catch-up is warranted.
git log --oneline -1 -- apps/examples/desktop-app/webview/lib/whats-new-content.ts
sed -n '1,80p' apps/examples/desktop-app/CHANGELOG.md
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.
- 15d ago Changed d3047d575bd7
- 22d ago First seen · 74 lines · 95 tokens per session scan A 87f2509fd70b
desktop-whats-new is a skill published in the GitHub repository cline/cline (70,487 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 1,424 once invoked, about $0.0004 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 2026-09-26.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.