@standardagents/skill 0.19.3 → 0.20.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@standardagents/skill",
-  "version": "0.19.3",
+  "version": "0.20.0",
   "private": false,
   "publishConfig": {
     "access": "public",

package/skills/agentbuilder/SKILL.md

@@ -508,7 +508,7 @@ This is the single biggest gap in most coding-agent-built tools. **Do not write
 Discoverability reference. For full signatures, read the spec types from `node_modules/@standardagents/spec/dist/` (or browse `packages/spec/src/` on GitHub). Worked examples live in `agents/tools/AGENTS.md`.
 
 ```
-Identity     threadId, agentId, userId, createdAt, children, terminated
+Identity     threadId, agentId, userId, createdAt, children, terminated, arguments
 Messages     getMessages, getMessage, injectMessage, queueMessage, updateMessage
 Logs         getLogs
 Resources    loadModel, loadPrompt, loadAgent,
@@ -519,7 +519,7 @@ Parent       notifyParent, setStatus, stopSession
 Tools        queueTool, invokeTool
 Effects      scheduleEffect, getScheduledEffects, removeScheduledEffect
 Events       emit
-Context      context (Record<string, unknown>, in-memory only)
+Context      context (Record<string, unknown>, current execution only)
 KV           getValue, setValue
 Files        writeFile, readFile, readFileStream, statFile, readdirFile,
              unlinkFile, mkdirFile, rmdirFile, getFileStats,
@@ -573,7 +573,8 @@ By default, `runCode()` executes the `default` export with no args. Use `execute
 
 ### Notes on a few that are easy to misuse
 
-- **`state.context`** is in-memory for the *current execution*. It is not durable across thread restarts. For durable structured state, use `state.getValue` / `state.setValue`.
+- **`state.arguments`** is read-only invocation/creation data. Resumable `subagent_create.arguments` persists with the child thread, is visible to both child sides, and is also available as prompt variables.
+- **`state.context`** is in-memory scratch data for the *current execution*. It is not durable across thread restarts and should not be used for invocation or subagent creation arguments. For durable structured state, use `state.getValue` / `state.setValue`.
 - **`state.getValue` / `state.setValue`** are durable per-thread JSON storage. Use them for small structured state; use files for larger content or artifacts.
 - **`state.env` / `state.envType` / `state.setEnv`** are for runtime configuration and secrets. `state.env(name)` resolves thread -> account -> instance -> agent -> prompt. `state.envType(name)` returns `'secret'` by default; `'text'` means the value may be shown in tool output. `state.setEnv(name, value, { type: 'text' | 'secret' })` writes thread-scoped env and propagates to active descendants. Omit `type` only when preserving the existing type is intentional; new keys default to secret.
 - **`state.runCode`** runs JavaScript or TypeScript in an isolated Dynamic Worker sandbox. The sandbox does not receive `ThreadState`, env, files, network, or host globals implicitly. Pass exact capabilities through `imports`, `globals`, `modules`, and `execute`. It executes exported values/functions; code such as `console.log(fibonacci(5))` can log, but it must still `export default ...` or export a named function/value for the host to receive a result.
@@ -756,6 +757,8 @@ SubagentToolConfig — entry on a parent prompt's `tools` array
   optional                   string (env name)           subagent disabled unless this env resolves truthy
 ```
 
+For resumable lifecycle creation, `subagent_create.arguments` is shaped by the prompt schema on the receiving child side (`resumable.receives_messages`). The runtime persists those values with the child thread and restores them as `ThreadState.arguments` for both child sides; top-level keys are also prompt variables during render, including included prompts.
+
 A second tool-config form exists for plain callables (`{ name, env, options }`), and a third for subprompts (`{ name, includeTextResponse, includeToolCalls, includeErrors, initUserMessageProperty, initAttachmentsProperty }`). Both are documented in full at `agents/prompts/AGENTS.md`.
 
 ### Inter-agent communication rules