@standardagents/skill 0.45.2 → 0.45.3

package/README.md

@@ -1,6 +1,6 @@
 # @standardagents/skill
 
-Markdown-authored coding skills for Standard Agents and AgentBuilder.
+Markdown-authored coding skills for Standard Agents Builder.
 
 ## Overview
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@standardagents/skill",
-  "version": "0.45.2",
+  "version": "0.45.3",
   "private": false,
   "publishConfig": {
     "access": "public",

package/skills/agentbuilder/SKILL.md

@@ -2,15 +2,15 @@
 name: agentbuilder
 description: >
   Use this skill when creating, editing, debugging, reviewing, or documenting
-  Standard Agents or AgentBuilder projects. Apply it for work on agents,
+  Standard Agents Builder projects. Apply it for work on agents,
   prompts, models, tools, hooks, threads, APIs, subagents, provider setup,
   model selection, environment variables, and spec-aligned architecture, even
   if the user only says things like "build an agent", "write a prompt",
-  "choose a model", or "fix my AgentBuilder app" without explicitly naming
+  "choose a model", or "fix my Standard Agents Builder app" without explicitly naming
   Standard Agents.
 ---
 
-# AgentBuilder Skill
+# Standard Agents Builder Skill
 
 This guide is a living record. It is not part of the Standard Agent Specification — it exists to help humans and coding agents *use* the spec to build effective agents. It is updated regularly and not bound to any spec version.
 
@@ -32,7 +32,7 @@ For deeper reference material that this skill links to, see:
 
 ## The specification comes first
 
-This skill covers how to build with AgentBuilder. The published Standard Agent Specification defines what a Standard Agent is. Read it before you answer what the specification requires, decide whether an agent is portable, or write or review a definition that must conform. Do not answer from memory, and do not rely on a remembered version number.
+This skill covers how to build with Standard Agents Builder. The published Standard Agent Specification defines what a Standard Agent is. Read it before you answer what the specification requires, decide whether an agent is portable, or write or review a definition that must conform. Do not answer from memory, and do not rely on a remembered version number.
 
 1. Read https://standardagentspec.org/llms.txt. Its `Latest version:` line names the latest version, and it lists a Markdown URL for every page of that version.
 2. Use the latest version unless the user or the project names another one. For a named older version, read `https://standardagentspec.org/api/navigation/<version>.json`. Each `href` in it becomes a Markdown URL when you put `https://standardagentspec.org` before it and `.md` after it.
@@ -40,7 +40,7 @@ This skill covers how to build with AgentBuilder. The published Standard Agent S
 4. Name the version and the pages you used in your answer. Separate what the specification requires from what it recommends and from your own inference. When the specification does not define something, say so.
 5. If you cannot reach the site, tell the user, and label anything you then say about the specification as unverified.
 
-If this skill and the published specification disagree, the specification is correct. Report the disagreement to the user. AgentBuilder's types, source, and documentation, and this skill, describe AgentBuilder only.
+If this skill and the published specification disagree, the specification is correct. Report the disagreement to the user. Standard Agents Builder's types, source, and documentation, and this skill, describe Standard Agents Builder only.
 
 ## Keeping this skill up to date
 
@@ -67,7 +67,7 @@ Most failed Standard Agent projects fail in the same seven ways. Read this secti
 List the domains the system touches. Determine the tree (coordinator → domain agents → sub-domain agents). *Then* decide what each node is. Do not start by writing one agent and bolting tools onto it. → [Architecture & decomposition](#architecture--decomposition)
 
 **2. Decide what backs each side. Prompt × prompt is the default worker shape; a human backing is the exception.**
-Every agent has exactly two explicit sides, and each side is backed by exactly one of a human, a prompt, or a handler. A human backing is correct only when the thread itself is the chat surface (chat UI, website widget, AgentBuilder admin, direct API chat). For Slack, email, SMS, Discord, webhooks, polled inboxes, schedulers, or any other mediated channel, the human is just a tool target — back both sides with prompts. The whole graph being prompt × prompt is fine and often cleaner. → [What backs each side?](#what-backs-each-side)
+Every agent has exactly two explicit sides, and each side is backed by exactly one of a human, a prompt, or a handler. A human backing is correct only when the thread itself is the chat surface (chat UI, website widget, Standard Agents Builder admin, direct API chat). For Slack, email, SMS, Discord, webhooks, polled inboxes, schedulers, or any other mediated channel, the human is just a tool target — back both sides with prompts. The whole graph being prompt × prompt is fine and often cleaner. → [What backs each side?](#what-backs-each-side)
 
 **3. Every prompt × prompt agent must have explicit session boundaries.**
 Name its `sessionStop` tool. Name its `sessionFail` tool. Set a finite `maxSessionTurns` (the spec makes the cap optional; this skill makes it required practice for prompt × prompt). Give side B a real, non-redundant job. If you cannot say in one sentence what tool call ends the session, the agent is not designed yet. → [Session boundary discipline](#session-boundary-discipline)
@@ -208,7 +208,7 @@ Every agent has **exactly two sides** — `sideA` and `sideB` — and each side
 
 There is no agent `type` field. Chat surface, composability, and termination are all **derived from the backings**. Both sides are always explicit — if a person takes side B's turns, write `sideB: { human: true }`; there is no implicit default side.
 
-> **Prompt × prompt is the default worker shape. A human backing is the exception**, used only when the thread itself is the chat surface — chat UI, website widget, AgentBuilder admin, or an API the user is talking to directly.
+> **Prompt × prompt is the default worker shape. A human backing is the exception**, used only when the thread itself is the chat surface — chat UI, website widget, Standard Agents Builder admin, or an API the user is talking to directly.
 
 For **Slack, email, SMS, Discord, webhooks, polled inboxes, schedulers, or any other mediated channel**, the human is just a tool target. Back both sides with prompts. The whole graph being prompt × prompt is fine — often cleaner.
 
@@ -571,7 +571,7 @@ probabilities, confidence, and score legends; boolean answers return a 0–1
 request/response/duration/status/cost automatically, persist before the first
 message, and never append messages;
 explicitly use `state.injectMessage()` when needed.
-Automatic logging and optional `name`/`trigger` attribution are AgentBuilder
+Automatic logging and optional `name`/`trigger` attribution are Standard Agents Builder
 extensions, not spec requirements. Standalone `typesafe({ apiKey }).decide(...)`
 creates no thread logs. Read the package README for limits and the complete
 conversion contract.
@@ -1206,7 +1206,7 @@ Validation order:
 2. Refresh Cloudflare types:
    - use `pnpm cf-typegen` if that script exists
    - otherwise run `npx wrangler types`
-3. Regenerate AgentBuilder types by running the project's build command:
+3. Regenerate Standard Agents Builder types by running the project's build command:
    - usually `pnpm build`, `npm run build`, `pnpm run dev`, or equivalent
 4. Run the project's type checker:
    - prefer `pnpm type-check` / `npm run type-check` if present