git:20261028.30d344c to git:20261108.3ac8c0b

39 added, 31 removed. Audit A to A.

What this update changes in the checks

No check changed: every fixed check gives the same answer before and after this update.

A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.

---
name: embedded-agents-agent-sdk
description: "Only when the Agent SDK is asked for, an agent needs Claude Code's own tools, or the app already runs it: embed Claude agents in a Next.js app with the Agent SDK."
---
# Embedded agents — Claude Agent SDK
- **Which skill.** Two skills run the same agent directories. This one runs them through the Claude Agent SDK, which starts the Claude Code engine as a subprocess: built-in file and shell tools, Claude Code's own system prompt, its skill and MCP loading, and a long-lived Node host to run on. The `embedded-agents-messages-api` skill runs them on the Claude API with the Anthropic SDK's tool runner, in the app's own process: only the tools the wrapper gives the agent, no subprocess, any Node host. It is the default for a new product. Use this one when the agent needs what only the engine has, or when the product already runs it.
+ **Use the Agent SDK when the agent needs the Claude Code engine.** Also use it when the product already runs it. The SDK starts that engine as a subprocess with built-in file and shell tools and Claude Code's own system prompt. It loads skills and MCP and needs a long-lived Node host. Both embedded-agent skills run the same agent directories. The `embedded-agents-messages-api` skill is the default for a new product. It uses the Anthropic SDK's tool runner in the app's own process on any Node host, with only the wrapper's tools and no subprocess.
- Read the product's own agent instructions first (its root `AGENTS.md` or `CLAUDE.md`), and tell any subagent you spawn for this work to read them too: their rules on secrets, environment variables, validation, callers, tests and release apply to everything here. This skill adds how to run Claude agents inside the app. `reference/playbook.md` is the full playbook, with the measurement behind every option — read it before changing the wrapper's contract or explaining it in depth.
+ **Read the product's own agent instructions before changing its embedded agents.** Start with its root `AGENTS.md` or `CLAUDE.md`, and tell any subagent spawned for this work to read it too. Its rules on secrets, environment variables, validation, callers, tests and release apply here. This skill adds how to run Claude agents inside the app. Read `reference/playbook.md` before changing the wrapper's contract or explaining it in depth. It holds the full playbook and the measurement behind every option.
- The model: the app owns the request, the caller, storage and the UI; the agent owns reasoning and tools. An agent is a directory, `.claude/agents/<name>/`, holding `AGENTS.md` (its instructions — its only instruction file), and optionally `knowledge/`, agent-local skills in `.claude/skills/`, and `.mcp.json`. One wrapper function, `askAgent`, runs any of them. No agent name appears in code.
+ **Keep request, caller, storage and UI ownership in the app.** The agent owns reasoning and tools. An agent is a directory, `.claude/agents/<name>/`, with `AGENTS.md` as its only instruction file. It may also hold `knowledge/`, agent-local skills in `.claude/skills/`, and `.mcp.json`. One wrapper function, `askAgent`, runs any agent. No agent name appears in code.
## 1. First use: install the wrapper
- Search the code for `askAgent`. If it exists, skip to § 2. Otherwise:
+ **Search for `askAgent` before installing another wrapper.** If it exists, skip to § 2. Otherwise:
- 1. **No app yet?** Create the smallest Next.js App Router app in TypeScript (what this skill's files are written for) and nothing the user did not ask for — no database, sign-in or billing for a local prototype.
- 2. **Install** what is missing: `npm i @anthropic-ai/claude-agent-sdk zod server-only` and `npm i -D vitest`.
- 3. **Copy**, changing only import paths:
+ 1. **Create only the smallest requested app when none exists.** Use Next.js App Router in TypeScript, which these files target. Add nothing unasked for: no database, sign-in or billing for a local prototype.
+ 2. **Install the missing dependencies.** Run `npm i @anthropic-ai/claude-agent-sdk zod server-only` and `npm i -D vitest`.
+ 3. **Copy the wrapper, route and tests, changing only import paths.**
| From this skill | To the app |
|---|---|
| `templates/agent.ts` | `src/lib/agent.ts` — the wrapper |
| `templates/route.ts` | `src/app/api/agents/route.ts` — `GET` lists agents, `POST` streams one |
| `templates/agent.test.ts` | `tests/unit/agent.test.ts` — the contract, inside `npm test`, no model call |
| `templates/agents.live.test.ts` | `tests/live/agents.live.test.ts` — every agent against the real model |
The tests import `@/lib/agent`, so Vitest needs the same `@` alias as `tsconfig.json`. The live test gets its own Vitest config (include `tests/live/**/*.live.test.ts`, `testTimeout: 180_000`, `fileParallelism: false`) and a script, `agents:live`. It costs money, so it stays out of `npm test` and the gate.
- 4. **Environment:** `ANTHROPIC_API_KEY`, plus every secret an agent's `.mcp.json` references, each set per environment and never committed (the `environments` skill). On a developer's laptop the SDK falls back to their own Claude login when the key is absent; a deployed product always uses the key.
+ 4. **Set each required secret per environment and never commit it.** Set `ANTHROPIC_API_KEY` and every secret referenced by an agent's `.mcp.json`; apply `environments`. On a developer's laptop the SDK falls back to their own Claude login when the key is absent; a deployed product always uses the key.
5. **Keep the contract.** Every option in `agentOptions()` exists because an SDK default failed a measurement (playbook § 9). Change one only after re-measuring it.
## 2. Add an agent
- 1. `node <skill dir>/scripts/new-agent.mjs <name> [--knowledge] [--mcp]`, then fill in `AGENTS.md`: role, sources, output format, refusals. A fixed sign-off line is the cheapest proof, in a live test, that the instructions are in force.
- 2. **Knowledge:** files in `knowledge/*.md`, and `AGENTS.md` says to answer only from them. **Agent-local skills:** `.claude/agents/<name>/.claude/skills/<skill>/SKILL.md`; found automatically.
- 3. **MCP:** servers in `.mcp.json`, secrets as `${VAR}`, never literal. Run `node --env-file=.env <skill dir>/scripts/discover-mcp-tools.mjs <name>` to list what each server offers, then put in that server's `allowedTools` only what the agent's job needs. Anything unlisted is denied. The agent's `.mcp.json` holds no secrets and is committed: if `git check-ignore` reports it ignored, the repo's `.gitignore` has an unanchored `.mcp.json` rule meant for the root file — anchor it as `/.mcp.json`.
- 4. **Routing needs nothing:** `listAgents()` finds the directory, `GET /api/agents` returns it, and — when users choose between agents — the UI's picker shows it. A UI that hardcodes the list is the bug to fix.
+ 1. **Create the agent directory and fill in its instructions.** Run `node <skill dir>/scripts/new-agent.mjs <name> [--knowledge] [--mcp]`, then fill in `AGENTS.md`: role, sources, output format, refusals. A fixed sign-off line is the cheapest live-test proof that the instructions are in force.
+ 2. **Keep knowledge and automatically discovered skills inside the agent directory.** Put knowledge in `knowledge/*.md`, and tell the agent in `AGENTS.md` to answer only from them. Agent-local skills are found automatically in `.claude/agents/<name>/.claude/skills/<skill>/SKILL.md`.
+ 3. **Allow only MCP tools the agent's job needs.** Put servers in `.mcp.json`, with secrets as `${VAR}`, never literal. Run `node --env-file=.env <skill dir>/scripts/discover-mcp-tools.mjs <name>` to list each server's tools, then restrict its `allowedTools`. Anything unlisted is denied. Commit the agent's `.mcp.json`, which holds no secrets. If `git check-ignore` reports it ignored, the repository's `.gitignore` has an unanchored `.mcp.json` rule meant for the root file. Anchor it as `/.mcp.json`.
+ 4. **Discover agents from their directories rather than hardcoding the UI list.** `listAgents()` finds the directory, `GET /api/agents` returns it, and the UI's picker shows it when users choose between agents. Fix a UI that hardcodes that list.
5. **The instruction file is always `AGENTS.md`.** Asked for another name, create `AGENTS.md` and say why: the wrapper loads only `AGENTS.md`, and the SDK loads some other instruction files on its own, which would give the agent two sets of instructions.
- 6. When the agent makes a promise worth pinning — it cites, it refuses, it answers only from its files — add a live test for it beside the generic one.
+ 6. **Add a live test for each promise worth pinning.** Examples include citing, refusing and answering only from its files. Put it beside the generic test.
## 3. Examples — only when asked
- `examples/` holds two finished agents. Use them when the user asks for examples, or describes one of them: an agent that answers only from local product-management knowledge files (`knowledge-agent`), or one that researches the live web through Perplexity with citations (`research-agent`). Copy `examples/<name>/` to `.claude/agents/<name>/` and `examples/<name>.live.test.ts` to `tests/live/`. `research-agent` needs `PERPLEXITY_API_KEY`. Otherwise, never copy them.
+ **Copy finished examples only when asked for or described.** The `examples/` agents are: answering only from local product-management knowledge files (`knowledge-agent`), or live-web research through Perplexity with citations (`research-agent`). Copy `examples/<name>/` to `.claude/agents/<name>/` and `examples/<name>.live.test.ts` to `tests/live/`. `research-agent` needs `PERPLEXITY_API_KEY`. Otherwise, never copy them.
## 4. The chat UI
- Product-specific, so there is no template. What it must do:
+ **Build the chat UI for this product and its agent flow.** There is no template. It must do the following:
- - When users choose between agents, fill the picker from `GET /api/agents`. A product may run one front agent and show no picker; the route still checks the name against `listAgents()`.
- - `POST { agent, prompt, history }` to `/api/agents` and read server-sent events: `{ text }` chunks, then `{ done, agent, metadata }` or `{ error, agent }`. The parser is in playbook § 5.
- - Store the agent on every message and, when there is more than one, show it on each reply, so the reader always knows which agent answered. History is the conversation so far, kept in client state unless the product asks to persist it.
- - Render agent output as plain text or sanitized markdown, never raw HTML: it is untrusted text, like anything a user typed. Show an `error` event instead of spinning forever.
+ - **Fill the picker from `GET /api/agents` when users choose agents.** A product may run one front agent and show no picker; the route still checks the name against `listAgents()`.
+ - **Send the conversation to the route and read server-sent events.** `POST { agent, prompt, history }` to `/api/agents` and read: `{ text }` chunks, then `{ done, agent, metadata }` or `{ error, agent }`. The parser is in playbook § 5.
+ - **Store the agent on every message; identify replies with several agents.** When there is more than one agent, show it on each reply, so the reader always knows which agent answered. History is the conversation so far, kept in client state unless the product asks to persist it.
+ - **Render agent output as plain text or sanitized markdown.** Never render raw HTML: it is untrusted text, like anything a user typed. Show an `error` event instead of spinning forever.
## 5. Explaining routing and the tool boundary
- **Routing:** UI → `POST /api/agents { agent }` → the route validates the body and requires the name to be in `listAgents()` → `askAgent` → `agentOptions()` accepts only a plain directory name and resolves `.claude/agents/<agent>/` → `query()` starts the Claude Code engine with that directory as `cwd` and its `AGENTS.md` appended to the system prompt → events stream back.
+ **Validate the requested agent before routing it to the wrapper.**
- **Boundary** — each layer measured (playbook § 9):
- 1. `tools`: only the built-ins on the allowlist exist — `Read`, `Glob`, `Grep` by default. `Bash`, `Write`, `Edit` and `WebFetch` do not.
- 2. `permissionMode: 'dontAsk'` with `allowedTools`: an MCP tool runs only if its server's `allowedTools` in `.mcp.json` lists it.
- 3. `strictMcpConfig`: only the agent's own `.mcp.json` servers load — nothing from the developer's or the server's user configuration.
- 4. `skills`: only the agent's own skills are listed.
- 5. The PreToolUse guard blocks any path outside the agent's directory, and any `.env` file.
- 6. `maxTurns` (10 by default) and `maxBudgetUsd` cap a run.
+ 1. UI
+ 2. `POST /api/agents { agent }`
+ 3. the route validates the body and requires the name to be in `listAgents()`
+ 4. `askAgent`
+ 5. `agentOptions()` accepts only a plain directory name and resolves `.claude/agents/<agent>/`
+ 6. `query()` starts the Claude Code engine with that directory as `cwd` and its `AGENTS.md` appended to the system prompt
+ 7. events stream back.
+ **Keep every measured layer of the tool boundary in force.** See playbook § 9:
+ 1. **Expose only built-in tools on the allowlist.** In `tools`, only those built-ins exist — `Read`, `Glob`, `Grep` by default. `Bash`, `Write`, `Edit` and `WebFetch` do not.
+ 2. **Allow an MCP tool only when its server lists it.** With `permissionMode: 'dontAsk'` and `allowedTools`: an MCP tool runs only if its server's `allowedTools` in `.mcp.json` lists it.
+ 3. **Load only the agent's own MCP servers.** `strictMcpConfig`: only the agent's own `.mcp.json` servers load — nothing from the developer's or the server's user configuration.
+ 4. **List only the agent's own skills.** `skills` enforces this.
+ 5. **Block paths outside the agent directory and every `.env` file.** The PreToolUse guard enforces this.
+ 6. **Cap the run by turns and budget.** Use `maxTurns` (10 by default) and `maxBudgetUsd`.
+
## 6. Before it leaves localhost
- - **Hosting.** The SDK runs the Claude Code engine as a subprocess, so an agent cannot run in a serverless function such as a Netlify Function (playbook § 7). A product whose site deploys there needs a second, long-lived Node host (a container or VM, such as Railway), chosen before the agent goes beyond localhost; write its deploy procedure into the product's docs the first time it is used. `next dev` needs nothing.
+ - **Choose a long-lived Node host before the agent leaves localhost.** The SDK runs the Claude Code engine as a subprocess, so an agent cannot run in a serverless function such as a Netlify Function (playbook § 7). A product whose site deploys there needs a second, long-lived Node host (a container or VM, such as Railway), chosen before the agent goes beyond localhost; write its deploy procedure into the product's docs the first time it is used. `next dev` needs nothing.
- **History is a client claim.** `templates/route.ts` accepts `history` from the client, `assistant` turns included, and `composePrompt` turns it into a "Previous conversation" preamble — so a client can forge earlier turns, the agent's own included. That is acceptable for a read-only agent, which can only be talked into saying something to the person forging it. Before any tool acts on the caller's behalf, keep the transcript on the server and stop reading it from the request.
- - **Caller and cost:** before anyone but the developer can reach the route, resolve the caller there (who they are, which workspace, which permission: `saas-authorization`) and set a per-actor limit and a `maxBudgetUsd`.
- - **Release:** run `npm run agents:live` before any release that adds or changes an agent, its prompt or its model, record the run in the product's test-coverage map (which test proves what, and when it last passed), and describe each agent in its automation doc: what it may read, the exact tools it may call, and what the app enforces around it (`shipping-artifacts`).
+ - **Resolve the caller and cap cost before opening the route.** Before anyone but the developer can reach the route, resolve the caller there (who they are, which workspace, which permission: `saas-authorization`) and set a per-actor limit and a `maxBudgetUsd`.
+ - **Run live tests before releasing any agent, prompt or model change.** Run `npm run agents:live` before any release that adds or changes an agent, its prompt or its model, record the run in the product's test-coverage map (which test proves what, and when it last passed), and describe each agent in its automation doc: what it may read, the exact tools it may call, and what the app enforces around it (`shipping-artifacts`).
## How you can tell it worked
The agent runs on the deployed host, not only on localhost, uses only the tools it was given, and the live agent suite passes against the real model.
## Running the scripts
- Run them from the app's repository root: `<skill dir>` is wherever this skill is installed (a plugin, `~/.claude/skills/`, or the repo's own `.claude/skills/`), and the scripts write into the current directory.
+ **Run these scripts from the app's repository root.** `<skill dir>` is this skill's installation location: a plugin, `~/.claude/skills/`, or the repository's own `.claude/skills/`. The scripts write into the current directory.