@cursor/july 0.1.30 → 0.1.32

package/docs/reference/sessions.md

@@ -111,13 +111,13 @@ state resumes from the Cursor SDK store.
 
 ## What goes into a local session workspace?
 
-agentkit creates a workspace before the first local turn:
+The Agent SDK creates a workspace before the first local turn:
 
 | Source path                        | Lands as                                                                |
 | ---------------------------------- | ----------------------------------------------------------------------- |
 | `instructions.*`                   | `AGENTS.md`                                                             |
 | `skills/*`                         | `.cursor/skills/<name>/SKILL.md`                                        |
-| agent tools (`execution: "agent"`) | scripts under `.agentkit/tools/`, with a catalog in `AGENTS.md` |
+| agent tools (`execution: "agent"`) | scripts under `.agent-sdk/tools/`, with a catalog in `AGENTS.md` |
 | `sandbox/workspace/**`             | copied in as seed files                                                 |
 | per-send `workspaceFiles`          | written before the turn                                                 |
 
@@ -130,12 +130,12 @@ worktree.
 See [Agent config: local cwd](./agent-config.md#local-cwd) for the
 inheritance rules.
 
-## Where does agentkit store session data?
+## Where does the Agent SDK store session data?
 
 Local state uses one directory tree:
 
 ```text
-<project>/.agentkit/            # or <stateRoot>/<slug>/ under serve
+<project>/.agent-sdk/            # or <stateRoot>/<slug>/ under serve
   sessions/<id>/session.json       # metadata: channel, mode, principal, tokens
   sessions/<id>/events.ndjson      # the durable stream
   sessions/<id>/workspace/         # the harness cwd
@@ -158,8 +158,8 @@ repositories whose parent rules shouldn't reach the agent. See
 Use `trajectory` with a trace or session event file:
 
 ```bash
-agentkit trajectory --events .agentkit/traces/<sessionId>.ndjson
-agentkit trajectory --events <stateRoot>/<slug>/sessions/<id>/events.ndjson
+agent-sdk trajectory --events .agent-sdk/traces/<sessionId>.ndjson
+agent-sdk trajectory --events <stateRoot>/<slug>/sessions/<id>/events.ndjson
 ```
 
 The command prints tool calls, the reply, and token usage in the same
@@ -171,4 +171,4 @@ view.
 - [HTTP API](./http-api.md)
 - [Hooks](./hooks.md)
 - [Live A/B metrics](../ab.md)
-- [How agentkit works](../concepts.md)
+- [How the Agent SDK works](../concepts.md)

package/docs/reference/tools.md

@@ -108,7 +108,7 @@ printf '%s\\n' "$message"
 });
 ```
 
-On the local runtime, scripts land under `.agentkit/tools/` in the
+On the local runtime, scripts land under `.agent-sdk/tools/` in the
 session workspace with a catalog in `AGENTS.md`. On cloud, the catalog
 and script bodies travel on the first prompt.
 
@@ -159,9 +159,9 @@ From the CLI, which starts an ephemeral server unless `--url` targets
 a running one:
 
 ```bash
-agentkit call inspect_pr --dir . \
+agent-sdk call inspect_pr --dir . \
   --input '{"prUrl":"https://github.com/acme/checkout/pull/42"}'
-agentkit call inspect_pr \
+agent-sdk call inspect_pr \
   --url http://127.0.0.1:3000/<slug> \
   --input '{"prUrl":"https://github.com/acme/checkout/pull/42"}'
 ```

package/docs/scaffolding-agents.md

@@ -84,7 +84,7 @@ folder.
 
 Cursor checks the project in this order:
 
-1. Run `agentkit validate` and fix every error
+1. Run `agent-sdk validate` and fix every error
 2. Inspect the discovered surface with `info --json`
 3. Call each server tool directly with validated sample input
 4. Run one end-to-end model turn
@@ -93,7 +93,7 @@ Cursor checks the project in this order:
 
 Validation, discovery, direct server-tool calls, and server startup work
 without a Cursor credential. Model turns and evals need
-`CURSOR_API_KEY` or a saved `agentkit login`.
+`CURSOR_API_KEY` or a saved `agent-sdk login`.
 
 ## What happens after the first agent works?
 

package/docs/storage.md

@@ -1,11 +1,11 @@
 ---
 title: "Storage"
-description: "Point agentkit's durable storage at a backend you own with defineStorage."
+description: "Point the Agent SDK's durable storage at a backend you own with defineStorage."
 ---
 
 # Storage
 
-agentkit owns durable storage for sessions, continuation tokens,
+The Agent SDK owns durable storage for sessions, continuation tokens,
 reminders, playground eval history, and live A/B samples. It chooses the
 keys (under `agentkit/v1/`), when to read and write, and how to restore
 after restart.
@@ -22,7 +22,7 @@ for one machine; it does not survive replacing the host.
 
 To keep the same framework storage across hosts, plug in a key-value
 backend with `agent/storage.ts`. You provide `put` / `get` / `delete` /
-`list`. agentkit does the rest.
+`list`. The Agent SDK does the rest.
 
 ```ts
 // agent/storage.ts
@@ -86,7 +86,7 @@ follow-up arrives instead of at startup.
 
 With `get` and `list`, serve can rebuild local state from your store:
 
-- At startup, agentkit loads recent sessions up to the restore caps.
+- At startup, the Agent SDK loads recent sessions up to the restore caps.
   Local disk wins when both sides have the same session. Reminders
   hydrate the same way into `--state-root/reminders`.
 - On demand, a missing continuation token resolves through the store
@@ -107,7 +107,7 @@ await ctx.host.kv.put("alert-memory/abc", { updated: "…" });
 const prior = await ctx.host.kv.get("alert-memory/abc");
 ```
 
-agentkit prefixes author keys as `agentkit/v1/{agent}/kv/{key}` (same
+The Agent SDK prefixes author keys as `agentkit/v1/{agent}/kv/{key}` (same
 bounded encoding as continuation tokens). Writes **await** the sink and
 propagate errors — unlike session mirrors, which are at-most-once.
 

package/docs/troubleshooting.md

@@ -7,19 +7,19 @@ description: "Match what you see to a cause, then read a session trace when you
 
 Start with four checks, in order:
 
-1. Project discovery: `agentkit validate --dir .`
+1. Project discovery: `agent-sdk validate --dir .`
 2. Whether the serve process is running
 3. What the playground or HTTP API shows
 4. The session event stream (trace)
 
-Match your symptom below. Keep the commands as `agentkit`; see
+Match your symptom below. Keep the commands as `agent-sdk`; see
 [Run the CLI](./README.md#run-the-cli) if you still need an alias.
 
 ## What if serve or the playground looks wrong?
 
 | What you see | What to do |
 | --- | --- |
-| `serve` won't start | Run `agentkit validate --dir .` and fix the reported errors. |
+| `serve` won't start | Run `agent-sdk validate --dir .` and fix the reported errors. |
 | Playground is blank or says there are no agents | The UI needs a running `serve` process. Building the playground assets alone is not enough. |
 | Edits to the playground don't show up | Use `serve --dev` and open the printed playground HMR URL (often port `5273`), not only the static `:3000` URL. |
 | Sessions exist on disk but the playground list is empty | The list shows sessions for the authenticated caller. In `--dev` on loopback the list is wider. Otherwise open `/<slug>/playground?sessionId=ses_…` or inspect `sessions/` under your state root. |
@@ -30,7 +30,7 @@ Match your symptom below. Keep the commands as `agentkit`; see
 | What you see | What to do |
 | --- | --- |
 | Built-in file reads and greps fail; the turn retries for a long time | Run under Node 22.13+ (or `tsx`), never Bun. Look for `NGHTTP2_FRAME_SIZE_ERROR` in logs. |
-| The turn fails immediately with an API-key error | Sign in with `agentkit login`, or set `CURSOR_API_KEY`. Discovery, `info`, `call`, and serve bring-up work without a key; model turns need one. |
+| The turn fails immediately with an API-key error | Sign in with `agent-sdk login`, or set `CURSOR_API_KEY`. Discovery, `info`, `call`, and serve bring-up work without a key; model turns need one. |
 | Replies quote rules or `AGENTS.md` from outside your agent project | The session workspace inherited parent-folder config. Point `defineAgent({ local: { cwd } })` outside that tree, or set `--state-root` to a clean directory (for example under `/tmp`). |
 | Server tools, skills, or workspace seed files never appear | The agent runtime is `cloud`. Those features apply on the local runtime. `validate` warns when this combination is present. |
 | `validate` and `run` succeed, but typecheck fails in CI | The CLI runs TypeScript with type-stripping only. Keep tool `execute` return types as object literals or `type` aliases, not `interface` types. |
@@ -50,16 +50,17 @@ Match your symptom below. Keep the commands as `agentkit`; see
 
 | What you see | What to do |
 | --- | --- |
-| `github forward` returns 401 on every delivery, but the hook was created | Clear `GITHUB_TOKEN` and `GH_TOKEN` for that command. The forwarder uses your `gh` CLI login: `GITHUB_TOKEN= GH_TOKEN= agentkit github forward …` |
+| `github forward` returns 401 on every delivery, but the hook was created | Clear `GITHUB_TOKEN` and `GH_TOKEN` for that command. The forwarder uses your `gh` CLI login: `GITHUB_TOKEN= GH_TOKEN= agent-sdk github forward …` |
 | `Hook already exists` when starting a forwarder | GitHub allows one forwarder per repo. Run a single `github forward --dir <parent>` and stop stale forwarders. |
 | Deliveries rejected outside `--dev` | Set `GITHUB_WEBHOOK_SECRET` on the server and on the signer. Without a secret, the channel stays loopback-only. |
-| You lack repo admin and can't forward | Use `agentkit github replay <pr-url>`. It needs pull access only and posts signed test payloads. |
+| You lack repo admin and can't forward | Use `agent-sdk github replay <pr-url>`. It needs pull access only and posts signed test payloads. |
 
 ## What if Slack stays quiet?
 
 | What you see | What to do |
 | --- | --- |
-| Logs show `channel idle … missing credentials` | Expected when tokens are missing. Set `<PREFIX>_SLACK_BOT_TOKEN` and `<PREFIX>_SLACK_APP_TOKEN` per agent, then run `agentkit slack doctor --prefix <PREFIX>`. |
+| Logs show `channel idle … missing credentials` | Expected when tokens are missing. Run `agent-sdk slack create --dir <agent>` to provision the app and write the tokens, or set `<PREFIX>_SLACK_BOT_TOKEN` and `<PREFIX>_SLACK_APP_TOKEN` per agent yourself, then run `agent-sdk slack doctor --prefix <PREFIX>`. |
+| `slack create` reports the app needs admin approval | The workspace requires admin approval for new apps. A Slack workspace admin approves it at the printed link (in the dashboard: **Approve in Slack**), then re-run `agent-sdk slack create` (or **Retry** in the dashboard). |
 | The bot ignores ordinary channel posts | Default engagement is mentions and DMs only. Enable `engagement.channelPosts` with an allowlist, and subscribe the app to `message.channels` / `message.groups`. |
 | Approve / Deny buttons do nothing | Re-import a Slack app manifest with interactivity enabled. Channels that post approval cards need `toolApprovals: true` (and `interactivity: true` when you compose events by hand). |
 
@@ -67,8 +68,8 @@ Match your symptom below. Keep the commands as `agentkit`; see
 
 | What you see | What to do |
 | --- | --- |
-| `must be defineConnection({ url, oauth: true })` | The connection file needs `oauth: true`, or you passed the wrong connection name to `agentkit mcp oauth`. |
-| Local auth works; hosted calls unauthorized | Run `agentkit mcp oauth <name> --store`, confirm names with `agentkit secrets list <slug>`, then redeploy. |
+| `must be defineConnection({ url, oauth: true })` | The connection file needs `oauth: true`, or you passed the wrong connection name to `agent-sdk mcp oauth`. |
+| Local auth works; hosted calls unauthorized | Run `agent-sdk mcp oauth <name> --store`, confirm names with `agent-sdk secrets list <slug>`, then redeploy. |
 | Model asks for `mcp_auth` or IDE MCP for a privileged server | That connection is likely `hostOnly`. Call it from a host tool via `ctx.host.mcp`, and update instructions. |
 
 See [Host MCP OAuth](./guides/mcp-oauth.md) and
@@ -96,7 +97,7 @@ If the model reads outside the session workspace, the prepared files
 don't match what the instructions expect. Fix the layout. See
 [Hillclimbing](./hillclimbing.md).
 
-`agentkit trajectory --events <file>` summarizes any saved NDJSON
+`agent-sdk trajectory --events <file>` summarizes any saved NDJSON
 stream. The playground **Open trace** control does the same visually.
 
 ## What's next

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cursor/july",
-  "version": "0.1.30",
+  "version": "0.1.32",
   "description": "(early alpha) Filesystem-first framework for defining Cursor agents as markdown and TypeScript and serving them over channels with the Cursor SDK.",
   "license": "SEE LICENSE IN LICENSE.md",
   "repository": {
@@ -14,6 +14,8 @@
   "types": "./dist/index.d.ts",
   "bin": {
     "july": "./dist/bin/agent-serve.js",
+    "agent-sdk": "./dist/bin/agent-serve.js",
+    "agentsdk": "./dist/bin/agent-serve.js",
     "agentkit": "./dist/bin/agent-serve.js",
     "agent-serve": "./dist/bin/agent-serve.js"
   },
@@ -191,7 +193,7 @@
     }
   },
   "scripts": {
-    "build": "tsgo -p tsconfig.build.json && pnpm run build:playground && pnpm run docs:build",
+    "build": "tsgo -p tsconfig.build.json && node scripts/bundle-publish-shims.mjs && pnpm run build:playground && pnpm run docs:build",
     "build:playground": "vite build --config playground/vite.config.ts",
     "build:playground:central": "vite build --mode central --config playground/vite.config.ts",
     "dev:playground": "vite --config playground/vite.config.ts",
@@ -227,6 +229,7 @@
     "zod-to-json-schema": "^3.24.5"
   },
   "devDependencies": {
+    "@anysphere/agent-store-sync": "workspace:*",
     "@anysphere/ui": "workspace:*",
     "@base-ui/react": "1.6.0",
     "@stylexjs/stylex": "0.18.3",

package/skills/ab/SKILL.md

@@ -7,11 +7,11 @@ description: >-
   comparison; use defineEval for regression gates.
 ---
 
-# agentkit A/B metrics (`defineAB`)
+# Agent SDK A/B metrics (`defineAB`)
 
 `defineAB` is a **live metrics plug-in**. At session creation the engine runs
 `split` and appends durable `ab.assigned` events; the collector folds the
-session event stream and calls `onSample`. There is **no** `agentkit ab`
+session event stream and calls `onSample`. There is **no** `agent-sdk ab`
 CLI and **no** assertion API.
 
 Human-facing reference: [`docs/ab.md`](../../docs/ab.md).
@@ -20,7 +20,7 @@ Human-facing reference: [`docs/ab.md`](../../docs/ab.md).
 | --- | --- | --- |
 | Job | Regression gates on frozen fixtures | Collect metrics on live runs |
 | Location | `evals/**/*.eval.ts` | `agent/ab.ts` or `agent/ab/<name>.ts` |
-| How it runs | `agentkit eval` | Automatically under `serve` / `run` |
+| How it runs | `agent-sdk eval` | Automatically under `serve` / `run` |
 | Driver | `t.send` + gates | `split` → `ab.assigned` + `onSample` |
 
 ## Authoring
@@ -101,9 +101,9 @@ mirror, not a metrics store. After park/restart it replays `events.ndjson` to
 rebuild counters without re-firing `onSample`.
 
 **Evals are separate:** the eval harness creates sessions with
-`purpose: "eval"` (playground Evals / `agentkit eval`). Those skip
+`purpose: "eval"` (playground Evals / `agent-sdk eval`). Those skip
 enrollment entirely — no `ab.assigned`, no `onSample`, omitted from
-`GET /v1/abs`. Ordinary chat / `agentkit run` / Slack stay `"live"`.
+`GET /v1/abs`. Ordinary chat / `agent-sdk run` / Slack stay `"live"`.
 Do not use `splitIf` to filter evals; the framework already does.
 
 After enrollment, arms are on `session.abs` (experiment → variant | `null`)

package/skills/create-agent/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agentkit-create-agent
 description: >-
-  Scaffold a new agentkit agent through a guided AskQuestion interview —
+  Scaffold a new Agent SDK agent through a guided AskQuestion interview —
   purpose, name, runtime, model, channels, MCP connections, capabilities —
   then verify it serves and hand off to hillclimbing. Read this skill when
   creating a new agent.
@@ -9,7 +9,7 @@ paths:
   - packages/agent-serve/**/*
 ---
 
-# Create an agentkit agent
+# Create an Agent SDK agent
 
 Stand up one new agent project via a short interview, scaffold it, get
 channels working
@@ -22,9 +22,9 @@ for iteration once the agent runs.
 Read `framework-map/SKILL.md` first if you haven't; treat the package
 `AGENTS.md` and `README.md` as ground truth for
 framework behavior. Run the CLI with Node, never Bun (Bun corrupts harness
-tool-result streams): use the installed `agentkit` bin, or from a source
+tool-result streams): use the installed `agent-sdk` bin, or from a source
 checkout `pnpm exec tsx src/bin/agent-serve.ts <command> …` — written as
-`agentkit …` below.
+`agent-sdk …` below.
 
 ## Interview
 
@@ -97,7 +97,7 @@ Defaults that make first cuts good:
   `prompt\`…\`` / `prompt.lines\`…\`` from `@cursor/july` (dedents indented
   multi-line strings).
 - **Env prefix** for Slack tokens = upper-snake slug (`my-agent` →
-  `MY_AGENT_SLACK_*`); `agentkit slack init` derives it for you.
+  `MY_AGENT_SLACK_*`); `agent-sdk slack init` derives it for you.
   Dedicated-app path only — the Cursor-hosted connection has no tokens.
 - **Host prep beats model wandering — for evidence, not judgment.** When the
   purpose has a deterministic setup step (fetch a PR, seed files), do it in
@@ -135,7 +135,7 @@ Two smells to check before scaffolding and again before hand-off:
 ## Scaffold
 
 ```bash
-agentkit init ./<slug>
+agent-sdk init ./<slug>
 ```
 
 `init` writes `package.json` (with `typescript` dev deps and a
@@ -159,7 +159,7 @@ plan:
    short hand-written `agent/channels/slack.ts`
    (`slackChannel({ cursorAccount: true, agentName: "<Name>" })` — no
    tokens, no manifests); for a dedicated Socket Mode app do not hand-write
-   the channel — `agentkit slack init --dir ./<slug> --name "<Name>"`
+   the channel — `agent-sdk slack init --dir ./<slug> --name "<Name>"`
    generates `agent/channels/slack.ts` (with the env prefix) plus manifests
    and `env.example`; customize the generated file (e.g. `suggestedPrompts`)
    afterwards.
@@ -172,7 +172,7 @@ plan:
    (case id = file path, or `<fileId>/<case.id>`). Full assertion API and
    fixture strategy: `evals/SKILL.md` (sibling skill).
 
-Stick to deps agentkit already
+Stick to deps the Agent SDK already
 ships (`zod`, `@modelcontextprotocol/sdk`, `tsx`); a new npm dep needs its own
 install story and is a smell for a first cut.
 
@@ -182,10 +182,10 @@ No API key needed for the structural half — run these first and fix every
 error diagnostic:
 
 ```bash
-agentkit validate --dir ./<slug>            # zero errors (warnings explain runtime mismatches)
-agentkit info --dir ./<slug> --json         # surface matches the plan
-agentkit call <tool> --dir ./<slug> --input '{…}'   # server tools, deterministic, no model
-agentkit eval --dir ./<slug> --list
+agent-sdk validate --dir ./<slug>            # zero errors (warnings explain runtime mismatches)
+agent-sdk info --dir ./<slug> --json         # surface matches the plan
+agent-sdk call <tool> --dir ./<slug> --input '{…}'   # server tools, deterministic, no model
+agent-sdk eval --dir ./<slug> --list
 npx tsc --noEmit -p ./<slug>                   # or the project's own type-check task
 ```
 
@@ -202,10 +202,10 @@ is forthcoming, finish every key-free check, confirm `run` fails with only
 the clean API-key error, and hand these to the user as their next steps:
 
 ```bash
-agentkit run --dir ./<slug> --message "<fixture prompt>"   # JSON trajectory
-agentkit serve --dir ./<slug> --dev
+agent-sdk run --dir ./<slug> --message "<fixture prompt>"   # JSON trajectory
+agent-sdk serve --dir ./<slug> --dev
 # playground: http://127.0.0.1:3000/<slug>/playground
-agentkit eval --dir ./<slug>
+agent-sdk eval --dir ./<slug>
 ```
 
 Serve only the new agent's directory during bring-up — pointing `serve` at a
@@ -221,7 +221,7 @@ it, verify with doctor commands, and smoke-test before declaring victory.
 
 - **Slack** — follow `packages/agent-serve/skills/setup-slack/SKILL.md` end
   to end, starting from its Step 0 connection gate. Cursor-hosted: sign in
-  (`agentkit login` / `CURSOR_API_KEY`) → serve → `@Cursor <AgentName>`
+  (`agent-sdk login` / `CURSOR_API_KEY`) → serve → `@Cursor <AgentName>`
   smoke. Dedicated app: init → human creates apps → doctor → `@mention`
   smoke.
 - **GitHub** — follow `packages/agent-serve/skills/github/SKILL.md`
@@ -251,7 +251,7 @@ at the smoke run's session (`.agent-serve/<slug>/sessions/<id>/events.ndjson`
 or the trace under `.agent-serve/traces/`) as the baseline measurement — or,
 when no API key was available, name the user's first real turn as the
 baseline instead. For GitHub agents, snapshot replay fixtures now
-(`agentkit github replay ... --dry-run --out fixtures/github`) so the
+(`agent-sdk github replay ... --dry-run --out fixtures/github`) so the
 loop starts deterministic.
 
 ## Working agreements

package/skills/debug/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: agentkit-debug
 description: >-
-  Diagnose a misbehaving agentkit agent, server, or playground — blank
+  Diagnose a misbehaving Agent SDK agent, server, or playground — blank
   playground, sessions missing, HMR not reloading, failing reads/retry
   loops, webhook 401s, 403/409 responses, approvals or reminders lost,
-  orphaned processes. Use when an agentkit project runs but behaves
+  orphaned processes. Use when an Agent SDK project runs but behaves
   wrong locally.
 ---
 
-# Debugging agentkit locally
+# Debugging the Agent SDK locally
 
 Read `framework-map/SKILL.md` (sibling skill) first if you don't know the
 project structure or session model. Everything below assumes Node/tsx (`pnpm exec tsx
@@ -18,7 +18,7 @@ src/bin/agent-serve.ts ...` in the everysphere monorepo).
 
 ```bash
 # 1. Is discovery clean? serve refuses to start on error diagnostics.
-agentkit validate --dir <project>
+agent-sdk validate --dir <project>
 
 # 2. What is actually running, and where?
 lsof -iTCP:3000 -sTCP:LISTEN; lsof -iTCP:5273 -sTCP:LISTEN
@@ -37,11 +37,11 @@ curl -sN 'localhost:3000/<slug>/v1/session/<id>/stream?startIndex=0' | head -50
 
 | Symptom | Cause / fix |
 | --- | --- |
-| Playground blank or "no agents" even though Vite assets are built | The SPA is static; it needs the agentkit backend on `:3000`. Start `serve` — building `dist/playground/` alone serves nothing. |
+| Playground blank or "no agents" even though Vite assets are built | The SPA is static; it needs the Agent SDK backend on `:3000`. Start `serve` — building `dist/playground/` alone serves nothing. |
 | Edits under `playground/src` don't show up in the browser | You're on the **static** `dist/playground` bundle, not HMR. Only `serve --dev` / `dev` starts Vite HMR (`:5273`) and prints that as `playground` — open that URL, not `:3000`. In the monorepo, `mise //packages/agent-serve:start` = all examples + multi-agent HMR; pin one slug with `AGENT_SERVE_BASE=/<slug>`. |
 | Webhook / schedule sessions exist on disk but the playground session list is empty | The list shows the calling principal's sessions. `--dev` (loopback) or `--allow-anonymous` (trusted shared host) switches it to `includeAll`. Otherwise deep-link `/<slug>/playground?sessionId=ses_...` or read `sessions/` on disk. |
 | Every built-in read/grep the model makes fails; turns crawl through retry loops | You ran the CLI under **Bun**. Kill it, rerun under Node/tsx. (`NGHTTP2_FRAME_SIZE_ERROR` in SDK logs is the tell.) |
-| `gh webhook forward` / `agentkit github forward` deliveries all 401 — but hook creation succeeded | `GITHUB_TOKEN`/`GH_TOKEN` in the env. The relay authenticates with the gh CLI login and rejects env tokens. `GITHUB_TOKEN= GH_TOKEN= agentkit github forward ...` |
+| `gh webhook forward` / `agent-sdk github forward` deliveries all 401 — but hook creation succeeded | `GITHUB_TOKEN`/`GH_TOKEN` in the env. The relay authenticates with the gh CLI login and rejects env tokens. `GITHUB_TOKEN= GH_TOKEN= agent-sdk github forward ...` |
 | `Hook already exists` starting a forwarder | GitHub allows one forwarder per repo. Use one `github forward --dir <parent>` (it fans out to every matching channel) instead of N processes; kill stale forwarders. |
 | Agent's answers reference monorepo rules / AGENTS.md it shouldn't know | Session workspace sits inside the monorepo, so the harness loaded ancestor config. `defineAgent({ local: { cwd } })` outside the repo, or `--state-root` under `/tmp`. |
 | Port 3000/5273 in use; stray processes after crashes | `lsof -iTCP:3000 -sTCP:LISTEN`, kill the pids; also check companion processes (e.g. vite). |
@@ -49,12 +49,12 @@ curl -sN 'localhost:3000/<slug>/v1/session/<id>/stream?startIndex=0' | head -50
 | Schedule / reminder never fires under `--dev` | Dev never auto-fires. `POST /<slug>/v1/dev/schedules/<id>` or `POST /<slug>/v1/dev/reminders/<id>` (list at `GET /v1/dev/reminders`). |
 | Reminder disarmed after restart with `handler_lost_on_restart` | `run`-handler reminders are in-memory; re-arm them from the code path that created them (enroll hook / policy), or use prompt-based reminders. |
 | `409` on a follow-up | Stale `continuationToken` (each accepted follow-up rotates it), busy session, or a task/schedule session (not followable). |
-| `409 session_busy` on `agentkit call --session` | Session-bound deterministic calls serialize with model turns; wait or use an ephemeral call (drop `--session`). |
+| `409 session_busy` on `agent-sdk call --session` | Session-bound deterministic calls serialize with model turns; wait or use an ephemeral call (drop `--session`). |
 | `403` on stream/follow-up | Caller principal ≠ session owner. In dev, create and inspect with the same auth; beyond loopback pass `--bearer-token` and send it. |
 | Works on localhost, 401/blocked through a tunnel or LAN | Default `localDevStrict()` auth only admits direct loopback, **rejects proxy-forwarding headers** (`X-Forwarded-For`, ...), and requires a loopback `Host`. Use `--bearer-token <secret>` (or authored `bearerAuth`) — `--allow-anonymous` only for trusted-network demos (and never with Cursor account MCP connections). |
 | Channel route won't compile: body/query schema type error | `GET` requires a Zod `querySchema`, `POST`/`PUT`/`PATCH` a Zod `bodySchema` — plain JSON Schema objects don't type-check. Use `z.object({})` / `z.unknown()` for open surfaces. Empty POST bodies are coerced to `{}` before validation. |
-| Slack channel prints `channel idle ... missing credentials` | Expected: tokens absent (dedicated-app path). Multi-agent needs `<PREFIX>_SLACK_BOT_TOKEN` + `<PREFIX>_SLACK_APP_TOKEN` per agent. `agentkit slack doctor --prefix <PREFIX>`. |
-| `serve` fails: `Slack channels using the Cursor account connection ... not signed in to Cursor` | Cursor-hosted Slack (`cursorAccount: true`) needs a signed-in host: `agentkit login` or `CURSOR_API_KEY`. No Slack tokens exist on this path — `slack doctor` doesn't apply. |
+| Slack channel prints `channel idle ... missing credentials` | Expected: tokens absent (dedicated-app path). Multi-agent needs `<PREFIX>_SLACK_BOT_TOKEN` + `<PREFIX>_SLACK_APP_TOKEN` per agent. `agent-sdk slack doctor --prefix <PREFIX>`. |
+| `serve` fails: `Slack channels using the Cursor account connection ... not signed in to Cursor` | Cursor-hosted Slack (`cursorAccount: true`) needs a signed-in host: `agent-sdk login` or `CURSOR_API_KEY`. No Slack tokens exist on this path — `slack doctor` doesn't apply. |
 | `@Cursor <name>` in Slack gets Cursor's normal agent, not yours | Agent name mismatch or host not relaying. Names are single-token and matched case-insensitively; confirm the serve log `cursor-slack: relaying Slack for <AgentName>` and that the workspace's Cursor Slack integration is linked to the signed-in account. |
 | Turn fails immediately with an API-key error | Model turns need `CURSOR_API_KEY`; everything structural (validate/info/call/serve bring-up) doesn't. |
 | Server tools / skills / sandbox silently absent | Runtime is `cloud` — those are local-only. `validate` prints exactly this warning; read it. |
@@ -69,5 +69,5 @@ curl -sN 'localhost:3000/<slug>/v1/session/<id>/stream?startIndex=0' | head -50
   preempted it — that's the designed behavior, not a crash.
 - Escapes outside the session workspace in read/grep paths mean the
   harness is fighting your evidence layout, not that the model is broken.
-- `agentkit trajectory --events <file>` renders any saved NDJSON; the
+- `agent-sdk trajectory --events <file>` renders any saved NDJSON; the
   playground "Open trace" does the same visually.

package/skills/evals/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: agentkit-evals
 description: >-
-  Author and run agentkit defineEval cases (single- or multi-datapoint).
+  Author and run Agent SDK defineEval cases (single- or multi-datapoint).
   Use when writing, fixing, seeding, or hillclimbing evals; AskQuestion
   whether to generate samples or upload data. Materialize API-backed
   fixtures first. Live A/B metrics: defineAB (skills/ab), not defineEval.
 ---
 
-# agentkit evals
+# Agent SDK evals
 
 Evals are the ratchet that makes iteration trustworthy: a fixed input, a
 model turn, and gates over the recorded trajectory. They live at the
@@ -29,13 +29,13 @@ and does not replace `defineEval` gates.
   (`evals/weather.eval.ts` + `{ id: "nyc" }` → `weather/nyc`).
 
 ```bash
-agentkit eval --dir . --list              # all datapoints
-agentkit eval --dir . --json              # run all
-agentkit eval --dir . weather/nyc         # one datapoint
-agentkit eval --dir . weather             # every datapoint in that file
-agentkit eval --dir . weather forecast    # several files
-agentkit eval --dir . --tag smoke
-agentkit eval --dir . --verbose
+agent-sdk eval --dir . --list              # all datapoints
+agent-sdk eval --dir . --json              # run all
+agent-sdk eval --dir . weather/nyc         # one datapoint
+agent-sdk eval --dir . weather             # every datapoint in that file
+agent-sdk eval --dir . weather forecast    # several files
+agent-sdk eval --dir . --tag smoke
+agent-sdk eval --dir . --verbose
 ```
 
 `eval` (like `run`) boots an ephemeral server on port 0 with a temp state
@@ -65,7 +65,7 @@ If `AskQuestion` is unavailable, ask the same fork in plain chat and wait.
 
 Tell the user the **shape** of the data (see “The API” below) and **how to
 upload it**. Do not invent cases until they provide files (or paste content
-to write). After they add data, run `agentkit eval --dir <project>
+to write). After they add data, run `agent-sdk eval --dir <project>
 --list` to confirm discovery, then wire any missing gates.
 
 If the uploaded data is **API-backed** (PR URLs, pinned SHAs, gold labels,
@@ -79,7 +79,7 @@ fixtures first** — see “When eval data needs API calls to render” below.
 3. Optional fixtures beside the case or under `fixtures/`.
 4. Tell the agent once the files are in place — or paste case bodies in chat
    and ask the agent to write the file.
-5. Verify: `agentkit eval --dir <project> --list` shows the new ids.
+5. Verify: `agent-sdk eval --dir <project> --list` shows the new ids.
 
 ### Step 2b — user chose agent-generated samples
 
@@ -95,7 +95,7 @@ fixtures first** — see “When eval data needs API calls to render” below.
 3. **Append** — prefer adding entries to an existing file’s `cases` array
    when the suite fits; otherwise create a new `evals/<suite>.eval.ts` with
    `cases`. Never overwrite or weaken an existing datapoint. Case ids must
-   not collide with `agentkit eval --dir <project> --list`.
+   not collide with `agent-sdk eval --dir <project> --list`.
 4. Create `evals/evals.config.ts` if missing (`maxConcurrency: 20` is fine
    for now; hard limit 200 for model provider request limits).
 5. Re-list to confirm, then optionally run `--tag smoke` if you tagged any.
@@ -206,7 +206,7 @@ input instead — see fixtures).
 | Agent surface | Fixture source |
 | --- | --- |
 | Chat / domain assistant | A canonical prompt string, chosen once and frozen |
-| Tool-heavy | `agentkit call <tool> --dir . --input '{...}'` first, then the prompt that should trigger it |
+| Tool-heavy | `agent-sdk call <tool> --dir . --input '{...}'` first, then the prompt that should trigger it |
 | GitHub webhook | `github replay … --dry-run --out fixtures/github` (see `packages/agent-serve/skills/github/SKILL.md`) |
 | PR reviewer with host prep | A small fixed PR the team controls; assert on findings shape, not counts |
 | Workspace-dependent | `workspaceFiles` in `t.send` — never machine-local paths |

package/skills/framework-map/SKILL.md

@@ -4,10 +4,10 @@ description: >-
   Orientation for @cursor/july — folder structure, local vs cloud
   runtimes, sessions, state layout, and invariants (Node not Bun, root
   evals/, typecheck after tsx). Use when creating, editing, or running
-  agentkit projects with agent/agent.ts and agent/instructions.md.
+  Agent SDK projects with agent/agent.ts and agent/instructions.md.
 ---
 
-# agentkit framework map
+# Agent SDK framework map
 
 `@cursor/july` serves agents defined as ordinary files: markdown
 for prose, TypeScript for typed behavior, under an `agent/` directory. The
@@ -16,7 +16,7 @@ over HTTP/Slack/GitHub channels, with the Cursor SDK + harness as the
 execution engine. Ground truth is the package `README.md` (full reference)
 and `AGENTS.md` (coding-agent loop) — this skill is the map, not the spec.
 
-Run the CLI as `agentkit <cmd>`. In the everysphere monorepo there is no
+Run the CLI as `agent-sdk <cmd>`. In the everysphere monorepo there is no
 installed bin — use:
 
 ```bash

package/skills/github/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: agentkit-github
 description: >-
-  Build and test GitHub-webhook-driven agentkit agents: githubChannel
+  Build and test GitHub-webhook-driven Agent SDK agents: githubChannel
   hooks (auth turn vs host task), signature modes, and testing tiers
   (fixtures, github replay, github forward, serve --cursor-events). Use
   when wiring GitHub events, replaying PR webhooks, or debugging delivery.
 ---
 
-# GitHub channels in agentkit
+# GitHub channels in the Agent SDK
 
 Author `agent/channels/github.ts` with `githubChannel()` from
 `@cursor/july/channels/github`. It mounts
@@ -47,7 +47,7 @@ the model should reason about the event.
 
 - **`cursorAccount`** → the signed-in Cursor principal supplies both the SCM
   event stream and a short-lived, repo-scoped GitHub credential. It works in
-  local dev (`agentkit login`) and hosted deployments (`CURSOR_API_KEY`).
+  local dev (`agent-sdk login`) and hosted deployments (`CURSOR_API_KEY`).
   `ctx.github`, `ctx.host.github`, and child `gh` commands share the lease.
   Use `{ repos: ["owner/repo"] }`, or `true` with `serve --cursor-events
   --repo owner/repo`. One host credential covers up to 20 repositories under
@@ -81,9 +81,9 @@ is fine here), synthesizes GitHub-shaped payloads, signs them when a secret
 is configured, and POSTs them at the channel. Fully deterministic.
 
 ```bash
-agentkit github replay https://github.com/owner/repo/pull/123 --dir <project>
-agentkit github replay owner/repo#123 --dir <project> --events '*' --conclusion failure
-agentkit github replay owner/repo#123 --dir <project> --events '*' --dry-run --out fixtures/github
+agent-sdk github replay https://github.com/owner/repo/pull/123 --dir <project>
+agent-sdk github replay owner/repo#123 --dir <project> --events '*' --conclusion failure
+agent-sdk github replay owner/repo#123 --dir <project> --events '*' --dry-run --out fixtures/github
 ```
 
 `--events` defaults to `pull_request` (`'*'` = the channel's declared
@@ -96,9 +96,9 @@ Wraps `gh webhook forward`: registers a real webhook and relays deliveries
 to loopback. URL + events auto-derived; repo inferred from the git remote.
 
 ```bash
-agentkit github doctor --install     # one-time: gh + cli/gh-webhook
-agentkit github events --dir <parent> --json   # what would be forwarded
-GITHUB_TOKEN= GH_TOKEN= agentkit github forward --dir <project>
+agent-sdk github doctor --install     # one-time: gh + cli/gh-webhook
+agent-sdk github events --dir <parent> --json   # what would be forwarded
+GITHUB_TOKEN= GH_TOKEN= agent-sdk github forward --dir <project>
 ```
 
 Traps, in order of hours lost:
@@ -121,11 +121,11 @@ Traps, in order of hours lost:
 ### 4. `serve --cursor-events` — pull from Cursor (`/v0/scm-events`)
 
 ```bash
-agentkit serve --dir <project> --cursor-events --repo owner/repo
+agent-sdk serve --dir <project> --cursor-events --repo owner/repo
 ```
 
 Reads the stream as the host's Cursor user, so it **requires sign-in**
-(`agentkit login` / `CURSOR_API_KEY`) — `serve` refuses to start signed
+(`agent-sdk login` / `CURSOR_API_KEY`) — `serve` refuses to start signed
 out instead of running a relay that can never receive events. No public URL
 or repo admin. Registers before consuming; offset + consumer id under
 `<state-root>/cursor-events/`. `CURSOR_API_BASE_URL` for a non-default