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/cline/sdk-skill/cline-sdknpx skills add cline/sdk-skill --skill cline-sdkgit clone --depth 1 https://github.com/cline/sdk-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/cline/sdk-skill/cline-sdk)<a href="https://agentmods.dev/skills/cline/sdk-skill/cline-sdk"><img src="https://agentmods.dev/badge/skills/cline/sdk-skill/cline-sdk.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 5.1 | $0.00060 | $0.02566 |
| Opus 5 | $0.00030 | $0.01283 |
| Sonnet 5 | $0.00012 | $0.00513 |
| Haiku 4.5 | $0.00006 | $0.00257 |
Grade A, and why
cline-sdk 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 6d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cline SDK Skill
Consolidated skill for building AI agents with the Cline SDK. Use the decision trees below to find the right entry point and API surface, then load detailed references.
Critical Rules
Follow these rules in all Cline SDK code:
- Install with
npm install @cline/sdk. The@cline/sdkpackage re-exports@cline/core, not every sub-package directly. Core re-exports the public SDK surface such asClineCore,Agent,createAgentRuntime,createTool, built-in tool helpers, provider helpers, and theLlmsnamespace. Import from@cline/agents,@cline/llms, or@cline/sharedonly when you need APIs that core does not re-export, such asAgentRuntime,createAgent, or some low-level types. - Requires Node.js 22 or later.
- Use
createTool()from@cline/sdk(or@cline/shared) to define tools. Tool names must besnake_case. - Prefer returning structured error data from tool
executefunctions when the agent can recover. DirectAgentconverts thrown tool errors into error tool results; ClineCore can also count repeated failed tool turns toward its mistake-limit handling. - Use
lifecycle: { completesRun: true }on tools that should end the agent loop (e.g. a "submit answer" tool). - When using
ClineCore, always calldispose()when done to clean up resources. - The direct
AgentandClineCorehave different event systems. ForAgent: useagent.subscribe()to getAgentRuntimeEventtypes, text streaming is"assistant-text-delta", and result text isresult.outputText. ForClineCore: usecline.subscribe()to getCoreSessionEventtypes. Render user-facing text, reasoning, and tool activity from"agent_event"payloads (content_start,content_update,content_end,done). Treat"chunk"events as raw transport chunks with{ stream, chunk, ts }, not as typed text deltas.ClineCoreresult text isresult.text. There is no top-levelonEventfield onAgentRuntimeConfig; useagent.subscribe()orhooks.onEventinstead. Do not use"content_update"or"content_start"withagent.subscribe(); those are host-facingAgentEventtypes carried inside ClineCoreagent_eventevents. - For direct
Agent,pluginsare simple runtime plugins withsetup(context)returning{ tools, hooks }. ForClineCore,extensionsareAgentPluginobjects withmanifest,setup(api, ctx), and optionalhooks. Do not use ClineCore plugin examples inside directAgent.plugins. - Plugin skills are file-based, not registered. There is no
registerSkill()and noapi.registerSkill. A plugin ships skills asSKILL.mdfiles under<package>/skills/<name>/SKILL.md(package shape required); the host discovers them and surfaces them as/slash-commandsautomatically -- do not callregisterCommandfor skills. Plugin MCP servers useapi.registerMcpServer()with the"mcp"capability. Configured agents (agent profiles) are YAML files in.cline/agents/loaded assubagent_<name>tools whenenableSpawnAgentis true.
What ships with it
15 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.
- references/agent/api.md 7.5 KB
- references/agent/gotchas.md 4.3 KB
- references/agent/patterns.md 5.8 KB
- references/agent/REFERENCE.md 3.7 KB
- references/clinecore/api.md 10 KB
- references/clinecore/gotchas.md 5.4 KB
- references/clinecore/patterns.md 6.7 KB
- references/clinecore/REFERENCE.md 5.5 KB
- references/events/REFERENCE.md 9.0 KB
- references/multi-agent/REFERENCE.md 7.7 KB
- references/plugins/REFERENCE.md 35 KB
- references/production/REFERENCE.md 6.7 KB
- references/providers/REFERENCE.md 6.5 KB
- references/scheduling/REFERENCE.md 6.0 KB
- references/tools/REFERENCE.md 11 KB
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.
- 6d ago First seen · 214 lines · 60 tokens per session scan A 9a239c63f13c
cline-sdk is a skill published in the GitHub repository cline/sdk-skill (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 2,566 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…