Skip to content
mcp/skillhub

Agent Skill

Update Harness Dependencies skill

update-harness-dependenciesvercel/aiskills/update-harness-dependencies/SKILL.md

Update the primary SDK dependencies of harness packages. Use when asked to update the harness SDKs or harness adapter dependencies.

27k

always on

29 tokname + description

once used

1,659 tokSKILL.md body

bundled files

0

repo stars

27kGitHub

Install the Update Harness Dependencies skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/vercel/ai --skill update-harness-dependencies

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/vercel/ai.git /tmp/ai
mkdir -p ~/.claude/skills
cp -R /tmp/ai/skills/update-harness-dependencies ~/.claude/skills/update-harness-dependencies

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description29 tok
When the agent uses itThe SKILL.md instructions1,659 tok
Only if openedNo bundled files—

Until it is used, update-harness-dependencies costs about 47× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 14 skills from vercel/ai would load 683 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Update the harness packages
  • Update the harness dependency packages
  • Update ACP and MCP SDKs everywhere
  • Align ACP npm-locked bridge manifests
  • Verification

More skills from vercel/ai

All skills in this repo
  1. ai-sdkvercel/ai

    Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

    65k155 tok idle · 1,188 in use
  2. Guide for adding new AI function examples, for testing specific features against the actual provider APIs.

    27k23 tok idle · 152 in use
  3. Guide for adding new AI SDK harness packages. Use when creating a new @ai-sdk/harness-<name> package that adapts a coding-agent runtime to HarnessV1.

    27k41 tok idle · 2,881 in use
  4. Guide for adding first-party AI provider packages to the AI SDK. Use when creating a provider package under packages/ to integrate an external AI service.

    27k33 tok idle · 2,502 in use
  5. adr-skillvercel/ai

    Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.

    27k389 tok idle · 3,701 in use
  6. Develop examples for AI SDK functions. Use when creating, running, or modifying examples under examples/ai-functions/src to validate provider support, demonstrate features, or create test fixtures.

    27k40 tok idle · 1,662 in use
  7. List the contents of an npm package tarball before publishing. Use when the user wants to see what files are included in an npm bundle, verify package contents, or debug npm publish issues.

    27k144 tok idle · 195 in use
  8. Context for working on the next AI SDK major release. Only use when explicitly invoked by the user (e.g. via '/major-version-mode'). Do NOT trigger autonomously based on task content.

    27k43 tok idle · 582 in use