Add Opus 4.8 migration guide and model updates to claude-api skill (#1216)

* Add Managed Agents self-hosted sandboxes + mid-session agent updates + MCP tool-output offload to claude-api skill

Self-hosted sandboxes: new shared/managed-agents-self-hosted-sandboxes.md for config:{type:"self_hosted"} — agent loop on Anthropic's orchestration, tool execution on customer infra via outbound-polling worker. Covers EnvironmentWorker.run()/.run_one() (Py/TS), ant beta:worker poll/run, mid-level work.poller()/WorkPoller (Py/TS/Go only; Go has no auto_stop opt-out), AgentToolContext/beta_agent_toolset/tool_runner(), monitoring (environments.work.stats/stop — x-api-key, call from outside worker host), runtime deps, cloud-vs-self_hosted delta table, credentials, security ownership split. Cross-refs in environments.md, overview.md (Reading Guide + rewrote cloud-only pitfall), api-reference.md (SDK row + naming-quirks + schema + work REST rows), tools.md (Who-runs-it carve-out), onboarding.md, live-sources.md.

Mid-session agent updates: sessions.update(session_id, agent={tools, mcp_servers}, vault_ids=[...]) — session-local override (doesn't bump agent version), full-replacement semantics, session must be idle. New core.md section + pointers in tools.md, api-reference.md (UpdateSession row), overview.md.

Large MCP tool outputs → files: >100K tokens → automatic offload to sandbox file; agent gets truncated preview + path. Plus: invalid vault credentials don't block sessions.create() — session.error event fires, auth retries on next idle→running. Both in tools.md.

* Point ant CLI install ref to live-sources.md (OSS has no anthropic-cli.md)

* Add Opus 4.8 model migration guide to claude-api skill

* Add prescriptive tool-description guidance for Opus 4.8 to claude-api skill

skills/claude-api/ruby/claude-api.md

@@ -26,7 +26,7 @@ client = Anthropic::Client.new(api_key: "your-api-key")
 
 ```ruby
 message = client.messages.create(
-  model: :"claude-opus-4-7",
+  model: :"claude-opus-4-8",
   max_tokens: 16000,
   messages: [
     { role: "user", content: "What is the capital of France?" }
@@ -46,7 +46,7 @@ end
 
 ```ruby
 stream = client.messages.stream(
-  model: :"claude-opus-4-7",
+  model: :"claude-opus-4-8",
   max_tokens: 64000,
   messages: [{ role: "user", content: "Write a haiku" }]
 )
@@ -78,7 +78,7 @@ class GetWeather < Anthropic::BaseTool
 end
 
 client.beta.messages.tool_runner(
-  model: :"claude-opus-4-7",
+  model: :"claude-opus-4-8",
   max_tokens: 16000,
   tools: [GetWeather.new],
   messages: [{ role: "user", content: "What's the weather in San Francisco?" }]
@@ -99,7 +99,7 @@ See the [shared tool use concepts](../shared/tool-use-concepts.md) for the tool
 
 ```ruby
 message = client.messages.create(
-  model: :"claude-opus-4-7",
+  model: :"claude-opus-4-8",
   max_tokens: 16000,
   system_: [
     { type: "text", text: long_system_prompt, cache_control: { type: "ephemeral" } }

skills/claude-api/ruby/managed-agents/README.md

@@ -51,7 +51,7 @@ puts "Environment ID: #{environment.id}" # env_...
 # 1. Create the agent (reusable, versioned)
 agent = client.beta.agents.create(
   name: "Coding Assistant",
-  model: :"claude-opus-4-7",
+  model: :"claude-opus-4-8",
   system_: "You are a helpful coding assistant.",
   tools: [{type: "agent_toolset_20260401"}]
 )
@@ -260,7 +260,7 @@ client.beta.sessions.delete(session.id)
 # Agent declares MCP server (no auth here — auth goes in a vault)
 agent = client.beta.agents.create(
   name: "GitHub Assistant",
-  model: :"claude-opus-4-7",
+  model: :"claude-opus-4-8",
   mcp_servers: [
     {
       type: "url",