@cursor/july 0.1.30 → 0.1.31

package/docs/quickstart.md

@@ -19,12 +19,12 @@ inspectable in the playground.
 You need:
 
 - Node 22.13 or newer. Bun isn't supported.
-- The `agentkit` CLI. See [Run the CLI](./README.md#run-the-cli)
+- The `agent-sdk` CLI. See [Run the CLI](./README.md#run-the-cli)
   for the current package and command names.
 - A Cursor credential for model turns. Sign in once:
 
 ```bash
-agentkit login
+agent-sdk login
 ```
 
 You can also set `CURSOR_API_KEY` instead of signing in.
@@ -53,12 +53,12 @@ full guided workflow.
 Start with the built-in scaffold:
 
 ```bash
-agentkit init ./pr-approver
+agent-sdk init ./pr-approver
 cd pr-approver
-agentkit dev
+agent-sdk dev
 ```
 
-The scaffold creates the files agentkit discovers, plus empty capability
+The scaffold creates the files the Agent SDK discovers, plus empty capability
 folders (each with a `.gitkeep`) so you can drop tools, channels, and
 evals in place:
 
@@ -91,8 +91,8 @@ framework runs your TypeScript directly, so nothing compiles.
 Check the project before you run it:
 
 ```bash
-agentkit validate --dir .
-agentkit info --dir .
+agent-sdk validate --dir .
+agent-sdk info --dir .
 ```
 
 These commands inspect the project without starting a model turn.
@@ -102,14 +102,14 @@ These commands inspect the project without starting a model turn.
 The scaffold already works. Run one turn from the terminal:
 
 ```bash
-agentkit run --dir . \
+agent-sdk run --dir . \
   --message "Introduce yourself in one sentence."
 ```
 
 `run` starts the agent, sends the message, and waits for the final
 reply. It prints a JSON trajectory with the response, tool calls, and
 token usage. It also writes an NDJSON trace under
-`.agentkit/traces/`.
+`.agent-sdk/traces/`.
 
 ## Teach it to review
 
@@ -266,7 +266,7 @@ a GitHub App) without parsing any of it.
 Call the tool directly first, on a real merged pull request:
 
 ```bash
-agentkit call inspect_pr --dir . \
+agent-sdk call inspect_pr --dir . \
   --input '{"prUrl":"https://github.com/react/react/pull/35623"}'
 ```
 
@@ -289,7 +289,7 @@ Now call it on the PR that added `experimental_useEvent` to React:
 1,027 additions across 26 files.
 
 ```bash
-agentkit call inspect_pr --dir . \
+agent-sdk call inspect_pr --dir . \
   --input '{"prUrl":"https://github.com/react/react/pull/25229"}'
 ```
 
@@ -363,7 +363,7 @@ teammate's open PR is the right pick: write access to the repo, and
 not authored by you.
 
 ```bash
-agentkit run --dir . \
+agent-sdk run --dir . \
   --message "Review https://github.com/acme/checkout/pull/42"
 ```
 
@@ -425,17 +425,17 @@ webhook delivery, and POSTs it to the channel. No repo admin, no
 tunnel:
 
 ```bash
-agentkit dev
+agent-sdk dev
 # second terminal:
-agentkit github replay https://github.com/acme/checkout/pull/42 \
+agent-sdk github replay https://github.com/acme/checkout/pull/42 \
   --dir . --action opened
 ```
 
 The replay prints the delivery, and the serve terminal shows the wake:
 
 ```text
-[agentkit] replaying acme/checkout#42 (pull_request) → 1 channel
-[agentkit]   pull_request.opened → pr-approver/github 200
+[agent-sdk] replaying acme/checkout#42 (pull_request) → 1 channel
+[agent-sdk]   pull_request.opened → pr-approver/github 200
 ```
 
 The agent runs the same inspect-then-submit loop, unprompted this time.
@@ -445,7 +445,7 @@ conversation.
 
 ## Open the playground
 
-Keep `agentkit dev` running and open the playground URL it printed. The
+Keep `agent-sdk dev` running and open the playground URL it printed. The
 webhook session is in the session list, titled
 `Review acme/checkout#42`, with the trigger message, both tool calls,
 and the verdict laid out. Start a new chat there and ask for another
@@ -456,7 +456,7 @@ review to watch a turn stream live.
 Replay is for development. For real deliveries, serve with
 `--cursor-events --repo owner/repo` to pull events for repositories
 connected to Cursor with no public URL, or run
-`agentkit github forward` to relay webhooks to your dev server. The
+`agent-sdk github forward` to relay webhooks to your dev server. The
 [GitHub guide](./guides/github.md) compares the options. In production,
 give the host GitHub App credentials so reviews post as your app's bot
 identity instead of a personal account.

package/docs/reference/agent-config.md

@@ -141,7 +141,7 @@ console.log(`listening on ${handle.url}`);
 `authToken` (the `--bearer-token` equivalent), `allowAnonymous`,
 `publicUrl`, `cursorEvents`, and `mode: "single" | "multi"`. The Cursor
 credential resolves in one order everywhere: explicit `apiKey`, then
-`CURSOR_API_KEY`, then the key stored by `agentkit login`.
+`CURSOR_API_KEY`, then the key stored by `agent-sdk login`.
 
 ## What's next
 

package/docs/reference/cli.md

@@ -6,16 +6,16 @@ description: "Commands and common flags for local development, running servers,
 # CLI reference
 
 `@cursor/july` installs `july` (so `npx @cursor/july docs` works),
-`agentkit`, and the legacy `agent-serve` alias. The examples on this
-page use `agentkit`. Run the CLI with Node 22.13 or newer. Don't run it
+`agent-sdk`, and the legacy `agent-serve` alias. The examples on this
+page use `agent-sdk`. Run the CLI with Node 22.13 or newer. Don't run it
 with Bun; Bun corrupts tool-result streams from the Cursor SDK.
 
 The current release still uses `.agent-serve` for on-disk state. See the
 [rename table](../README.md#run-the-cli) for identifiers still moving to
-agentkit names.
+agent-sdk names.
 
-`agentkit help` prints the built-in summary. The Slack and GitHub packs
-also provide `agentkit slack help` and `agentkit github help`.
+`agent-sdk help` prints the built-in summary. The Slack and GitHub packs
+also provide `agent-sdk slack help` and `agent-sdk github help`.
 
 | Command                                                 | Description                                                    |
 | ------------------------------------------------------- | -------------------------------------------------------------- |
@@ -45,7 +45,7 @@ also provide `agentkit slack help` and `agentkit github help`.
 | [`rotate-pod-credential`](#rotate-pod-credential)       | Replace a deployment's pod credential                          |
 | [`secrets`](#secrets)                                   | Manage deployment secrets                                      |
 | [`mcp oauth`](#mcp-oauth)                               | Authorize host MCP OAuth; optional `--store` to deployment secrets |
-| [`slack ...`](#slack)                                   | Set up and check Slack channels                                |
+| [`slack ...`](#slack)                                   | Provision, set up, and check Slack channels                    |
 | [`github ...`](#github)                                 | Forward, replay, and inspect GitHub webhook channels           |
 
 ## Choose a target
@@ -76,7 +76,7 @@ for `login`, `serve`, hosted targets, and managed-hosting commands.
 `eval` servers. Running and hosted targets ignore it.
 
 For ephemeral `run`, `call`, and `eval` commands, omitting `--slug`
-selects an unslugged root mount when one exists. Otherwise, agentkit
+selects an unslugged root mount when one exists. Otherwise, the Agent SDK
 selects the first discovered agent.
 
 ## serve
@@ -84,7 +84,7 @@ selects the first discovered agent.
 `serve` hosts every agent under `--dir` in multi-agent mode by default.
 
 ```bash
-agentkit serve [--dir <path>] [--port 3000] [--host 127.0.0.1] [--dev]
+agent-sdk serve [--dir <path>] [--port 3000] [--host 127.0.0.1] [--dev]
                   [--mode multi|single] [--api-key <key>]
                   [--state-root <path>] [--bearer-token <secret> | --allow-anonymous]
                   [--allow-anonymous-cursor-github]
@@ -129,9 +129,9 @@ and `docs`.
 agent folder as a positional path, or run it from inside the project:
 
 ```bash
-agentkit dev
-agentkit dev ./pr-approver
-agentkit dev ./pr-approver --port 3000
+agent-sdk dev
+agent-sdk dev ./pr-approver
+agent-sdk dev ./pr-approver --port 3000
 ```
 
 `dev` accepts the same flags as [`serve`](#serve). You can use `--dir`
@@ -148,10 +148,10 @@ path with a different `--dir`.
 server.
 
 ```bash
-agentkit chat --url http://127.0.0.1:3000/pr-approver
-agentkit chat --message "Is the PR ready to approve?"
-agentkit chat --message "Inspect PR 42" --json
-agentkit chat --prod --slug pr-approver --team 123
+agent-sdk chat --url http://127.0.0.1:3000/pr-approver
+agent-sdk chat --message "Is the PR ready to approve?"
+agent-sdk chat --message "Inspect PR 42" --json
+agent-sdk chat --prod --slug pr-approver --team 123
 ```
 
 `chat` streams text, tool calls, and a per-turn usage footer.
@@ -173,10 +173,10 @@ continuation token.
 `resume` is the direct way to reattach the chat REPL.
 
 ```bash
-agentkit resume ses_123 --url http://127.0.0.1:3000/pr-approver
-agentkit resume --url http://127.0.0.1:3000/pr-approver
-agentkit resume ses_123 --prod --team 123 --slug pr-approver
-agentkit resume ses_123 --message "Continue the review" --json
+agent-sdk resume ses_123 --url http://127.0.0.1:3000/pr-approver
+agent-sdk resume --url http://127.0.0.1:3000/pr-approver
+agent-sdk resume ses_123 --prod --team 123 --slug pr-approver
+agent-sdk resume ses_123 --message "Continue the review" --json
 ```
 
 Pass a session ID to select it. Omit the ID to select the most recently
@@ -190,8 +190,8 @@ available as `chat --session <id>` or `chat --resume`.
 `logs` follows the local or hosted log buffer.
 
 ```bash
-agentkit logs [--url http://127.0.0.1:3000] [--once] [--json]
-agentkit logs --prod [--slug <slug>] [--team <id>] [--once] [--json]
+agent-sdk logs [--url http://127.0.0.1:3000] [--once] [--json]
+agent-sdk logs --prod [--slug <slug>] [--team <id>] [--once] [--json]
 ```
 
 Local mode reads `/v1/logs` from the running server. Hosted mode reports
@@ -205,7 +205,7 @@ buffer and exits. `--json` emits newline-delimited JSON events.
 `sessions` lists sessions on a running or hosted agent.
 
 ```bash
-agentkit sessions [--url <baseUrl> | --prod] [--slug <slug>]
+agent-sdk sessions [--url <baseUrl> | --prod] [--slug <slug>]
                   [--team <id>] [--bearer-token <token>] [--json]
 ```
 
@@ -218,7 +218,7 @@ and update time. `--json` prints full session summaries in
 `session` inspects the event stream for one session.
 
 ```bash
-agentkit session <sessionId> [--url <baseUrl> | --prod]
+agent-sdk session <sessionId> [--url <baseUrl> | --prod]
                  [--slug <slug>] [--team <id>]
                  [--json | --text | --events]
 ```
@@ -234,7 +234,7 @@ same format. `--json` prints the trajectory object. `--events` prints
 `playground` opens an agent's web playground.
 
 ```bash
-agentkit playground [--url <baseUrl> | --prod] [--session <id>]
+agent-sdk playground [--url <baseUrl> | --prod] [--session <id>]
                     [--slug <slug>] [--team <id>]
                     [--bearer-token <token>] [--print]
 ```
@@ -254,7 +254,7 @@ it in a browser. You don't need an agent project.
 
 ```bash
 npx @cursor/july docs
-agentkit docs [--port <n>] [--host 127.0.0.1] [--print]
+agent-sdk docs [--port <n>] [--host 127.0.0.1] [--print]
 ```
 
 The site is the same VitePress build mounted at `/docs` on a running
@@ -267,11 +267,11 @@ the URL without opening a browser.
 `run` sends one or more turns and prints a JSON result.
 
 ```bash
-agentkit run --dir . --message "Is https://github.com/acme/checkout/pull/42 ready?"
-agentkit run --dir . --message "Inspect PR 42" --message "Summarize the risks"
-agentkit run --url http://127.0.0.1:3000/pr-approver --message "Inspect PR 42"
-agentkit run --prod --slug pr-approver --team 123 --message "Inspect PR 42"
-agentkit run --dir . --messages-file ./prompts.json
+agent-sdk run --dir . --message "Is https://github.com/acme/checkout/pull/42 ready?"
+agent-sdk run --dir . --message "Inspect PR 42" --message "Summarize the risks"
+agent-sdk run --url http://127.0.0.1:3000/pr-approver --message "Inspect PR 42"
+agent-sdk run --prod --slug pr-approver --team 123 --message "Inspect PR 42"
+agent-sdk run --dir . --messages-file ./prompts.json
 ```
 
 Without `--url` or `--prod`, the command starts an ephemeral server on
@@ -303,13 +303,13 @@ non-zero when the trajectory fails.
 `call` invokes a server tool directly, with no model turn.
 
 ```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 --url http://127.0.0.1:3000/pr-approver \
+agent-sdk call inspect_pr --url http://127.0.0.1:3000/pr-approver \
   --input '{"prUrl":"https://github.com/acme/checkout/pull/42"}'
-agentkit call refresh_cache --url http://127.0.0.1:3000/pr-approver \
+agent-sdk call refresh_cache --url http://127.0.0.1:3000/pr-approver \
   --session ses_123
-agentkit call inspect_pr --prod --slug pr-approver --team 123 --input '{}'
+agent-sdk call inspect_pr --prod --slug pr-approver --team 123 --input '{}'
 ```
 
 `call` sends `POST /v1/tools/:toolName` and runs the tool in the serving
@@ -330,17 +330,17 @@ response succeeds with `ok: true`. See
 `eval` runs the project's filesystem evals.
 
 ```bash
-agentkit eval --dir . --list          # discovered datapoints
-agentkit eval --dir .                 # run all
-agentkit eval --dir . builds/checkout # one datapoint
-agentkit eval --dir . builds          # every datapoint in the file
-agentkit eval --dir . --tag smoke     # by tag (repeatable)
-agentkit eval --dir . --json          # machine-readable results
-agentkit eval --dir . --verbose       # stream t.log lines + reply snippets
-agentkit eval --prod --slug pr-approver --team 123
+agent-sdk eval --dir . --list          # discovered datapoints
+agent-sdk eval --dir .                 # run all
+agent-sdk eval --dir . builds/checkout # one datapoint
+agent-sdk eval --dir . builds          # every datapoint in the file
+agent-sdk eval --dir . --tag smoke     # by tag (repeatable)
+agent-sdk eval --dir . --json          # machine-readable results
+agent-sdk eval --dir . --verbose       # stream t.log lines + reply snippets
+agent-sdk eval --prod --slug pr-approver --team 123
 # prints Eval ID immediately on --prod/--url; then:
-agentkit eval status <evalId> --prod --slug pr-approver
-agentkit eval cancel <evalId> --prod --slug pr-approver
+agent-sdk eval status <evalId> --prod --slug pr-approver
+agent-sdk eval cancel <evalId> --prod --slug pr-approver
 ```
 
 `eval` runs `evals/**/*.eval.{ts,js}` on an ephemeral server or against
@@ -362,7 +362,7 @@ matching cases exit `2`. See [Evals](../evals.md).
 `trajectory` summarizes a saved event stream.
 
 ```bash
-agentkit trajectory --events /tmp/run.ndjson [--text]
+agent-sdk trajectory --events /tmp/run.ndjson [--text]
 ```
 
 `trajectory` converts a saved NDJSON stream into the trajectory JSON
@@ -374,9 +374,9 @@ non-zero when the reconstructed trajectory failed.
 `init` scaffolds a new project.
 
 ```bash
-agentkit init ./my-agent          # scaffold package.json, tsconfig.json, agent/ + a demo tool
-agentkit init ./my-agent --json   # machine-readable summary for tooling
-agentkit init                     # no directory: print the setup guide
+agent-sdk init ./my-agent          # scaffold package.json, tsconfig.json, agent/ + a demo tool
+agent-sdk init ./my-agent --json   # machine-readable summary for tooling
+agent-sdk init                     # no directory: print the setup guide
 ```
 
 `init` leaves existing files unchanged and labels each one `create` or
@@ -388,9 +388,9 @@ skills in `~/.cursor/skills/agentkit/`. If accepted, it overwrites them
 with the version bundled in the installed package. The prompt is skipped
 for `--json` and non-interactive hosts.
 
-If the host isn't signed in, `init` runs `agentkit login` and waits for
-the browser flow. It then prints the `cd`, `agentkit login`, and
-`agentkit dev` steps still needed.
+If the host isn't signed in, `init` runs `agent-sdk login` and waits for
+the browser flow. It then prints the `cd`, `agent-sdk login`, and
+`agent-sdk dev` steps still needed.
 
 With `--json`, `init` still installs dependencies but never blocks on
 login or skill installation. It prints
@@ -402,7 +402,7 @@ login or skill installation. It prints
 `info` prints the discovered agent surface.
 
 ```bash
-agentkit info --dir . [--json]
+agent-sdk info --dir . [--json]
 ```
 
 `info` reports the model, instruction size, tools, skills, MCP
@@ -417,7 +417,7 @@ exit status.
 `validate` checks the project and sets the exit code.
 
 ```bash
-agentkit validate --dir .
+agent-sdk validate --dir .
 ```
 
 `validate` prints diagnostics for each agent and exits non-zero when any
@@ -429,9 +429,9 @@ are present. Warnings don't change the exit status.
 Three commands manage the host's Cursor credential.
 
 ```bash
-agentkit login [--api-key <key>] [--key-name <name>]
-agentkit whoami [--json]
-agentkit logout
+agent-sdk login [--api-key <key>] [--key-name <name>]
+agent-sdk whoami [--json]
+agent-sdk logout
 ```
 
 `login` signs the host in to Cursor: browser sign-in mints a named,
@@ -456,10 +456,10 @@ the other.
 `update` upgrades an installed copy to the latest published version.
 
 ```bash
-agentkit update
+agent-sdk update
 ```
 
-The command checks npm's `latest` tag, detects how agentkit was installed,
+The command checks npm's `latest` tag, detects how the Agent SDK was installed,
 and runs the matching npm, pnpm, Yarn, or Bun upgrade command. It handles
 global installs and project dependencies. It doesn't prompt before
 running the package-manager command.
@@ -476,7 +476,7 @@ commands with an explicit `--json` flag skip this automatic check.
 `deploy` sends one or more agents to Cursor managed hosting.
 
 ```bash
-agentkit deploy [--dir <path>] [--slug <slug> | --all] [--team <id>]
+agent-sdk deploy [--dir <path>] [--slug <slug> | --all] [--team <id>]
                 [--repo <https-url>] [--ref <git-ref>] [--path <agent-path>]
                 [--cursor-events-repo owner/name]...
                 [--allow-domain <domain>]... [--no-wait] [--json]
@@ -525,7 +525,7 @@ state layout.
 `deployments` lists the selected team's deployments.
 
 ```bash
-agentkit deployments [--team <id>] [--json]
+agent-sdk deployments [--team <id>] [--json]
 ```
 
 Text output shows each slug, status, generation, deployment kind, and
@@ -536,7 +536,7 @@ update time. `--json` prints `{ deployments }`.
 `deployment` prints the full status of one deployment.
 
 ```bash
-agentkit deployment <slug> [--team <id>] [--json]
+agent-sdk deployment <slug> [--team <id>] [--json]
 ```
 
 Text output includes status, generation, kind, alias, source, egress
@@ -549,7 +549,7 @@ domains, secret names, engine state, and the last error when present.
 `stop` shuts down a deployment.
 
 ```bash
-agentkit stop <slug> [--team <id>] [--no-wait] [--json]
+agent-sdk stop <slug> [--team <id>] [--no-wait] [--json]
 ```
 
 The command polls for up to ten minutes until the status reaches
@@ -561,7 +561,7 @@ The command polls for up to ten minutes until the status reaches
 playground.
 
 ```bash
-agentkit rotate-token <slug> [--team <id>] [--json]
+agent-sdk rotate-token <slug> [--team <id>] [--json]
 ```
 
 The old token stops working immediately. The replacement is shown once.
@@ -573,7 +573,7 @@ The old token stops working immediately. The replacement is shown once.
 engine pod.
 
 ```bash
-agentkit rotate-pod-credential <slug> [--team <id>] [--json]
+agent-sdk rotate-pod-credential <slug> [--team <id>] [--json]
 ```
 
 The command returns only the masked key and revokes the old credential
@@ -589,12 +589,12 @@ connection with a browser PKCE flow. Tokens are written to
 `MCP_OAUTH_<CONNECTION>_*` secrets on the hosted deployment.
 
 ```bash
-agentkit mcp oauth <connection> [--dir .] [--store] [--slug <slug>] [--team <id>]
+agent-sdk mcp oauth <connection> [--dir .] [--store] [--slug <slug>] [--team <id>]
 ```
 
 `<connection>` is the `agent/mcp-connections/<connection>.ts` basename.
 `--slug` defaults to the `--dir` basename. `--team` defaults to the
-signed-in account's team. You need `agentkit login` (or `--api-key`)
+signed-in account's team. You need `agent-sdk login` (or `--api-key`)
 before `--store`.
 
 Secret names are `MCP_OAUTH_<NAME>_ACCESS_TOKEN`,
@@ -612,9 +612,9 @@ See the [Host MCP OAuth guide](../guides/mcp-oauth.md).
 `secrets` manages environment secrets for a deployment.
 
 ```bash
-agentkit secrets set <slug> NAME[=VALUE]... [--team <id>] [--json]
-agentkit secrets list <slug> [--team <id>] [--json]
-agentkit secrets unset <slug> NAME [--team <id>] [--json]
+agent-sdk secrets set <slug> NAME[=VALUE]... [--team <id>] [--json]
+agent-sdk secrets list <slug> [--team <id>] [--json]
+agent-sdk secrets unset <slug> NAME [--team <id>] [--json]
 ```
 
 Omit `=VALUE` from `secrets set` to enter the value at a hidden TTY
@@ -634,25 +634,56 @@ and `{ removed }` for `unset`.
 
 ## slack
 
-The `slack` pack generates and checks Socket Mode channel setup.
+The `slack` pack provisions, generates, and checks Socket Mode channel
+setup.
 
 ```bash
-agentkit slack setup
-agentkit slack init [--dir <path>] [--name <name>]
+agent-sdk slack setup
+agent-sdk slack create [--dir <path>] [--name <name>] [--prod]
+                      [--slack-team <T…>] [--team <id>]
+                      [--icon <https-url-or-file>] [--force]
+                      [--prefix <prefix> | --no-prefix] [--json]
+agent-sdk slack destroy [--dir <path>] [--prod] [--slack-team <T…>]
+                       [--team <id>] [--json]
+agent-sdk slack icon <https-url-or-file> [--dir <path>] [--prod]
+                    [--slack-team <T…>] [--team <id>] [--json]
+agent-sdk slack init [--dir <path>] [--name <name>]
                     [--prefix <prefix> | --no-prefix] [--channel-posts]
-agentkit slack manifest [--dir <path>] [--name <name>]
+agent-sdk slack manifest [--dir <path>] [--name <name>]
                         [--env dev|prod|both] [--channel-posts] [--print]
-agentkit slack doctor [--prefix <prefix>] [--json]
+agent-sdk slack doctor [--prefix <prefix>] [--json]
 ```
 
 `slack setup` prints a guided checklist and doesn't change files.
 
+`slack create` provisions a dedicated Socket Mode app through Cursor's
+Add to Slack API instead of the manual manifest import. It requires a
+signed-in host (`agent-sdk login` or `CURSOR_API_KEY`) and the
+provisioning feature to be enabled for the account. The command
+scaffolds the channel file when missing, opens the browser consent flow
+when the workspace isn't connected to Cursor yet, creates and installs
+the app, writes the bot and app-level tokens into `<dir>/.env.local`,
+and ends with a `doctor` pass. `--prod` provisions the production app;
+the default is the development app. When the install needs a Slack
+workspace admin's approval, the command prints the approval page and
+exits non-zero; re-run it after the approval to finish and mint the
+tokens. A re-run rebuilds the manifest from the command's flags and
+refuses to overwrite edits made by hand in Slack unless you pass
+`--force`.
+
+`slack destroy` deletes the provisioned app for the selected
+environment. Tokens already written to `.env.local` stay in place and
+stop working.
+
+`slack icon` sets the provisioned app's icon from an https image URL or
+a local png, jpg, or gif file of at most 512KB.
+
 `slack init` creates the channel file, development and production
 manifests, `env.example`, and setup status under the project. It refuses
 to overwrite a target file. If a collision occurs, it exits non-zero;
 files created earlier in the run remain. The token prefix defaults to
 the directory basename normalized to uppercase snake case. Explicit
-`--prefix` values use the same normalization when agentkit builds token
+`--prefix` values use the same normalization when the Agent SDK builds token
 variable names. For example, `pr-approver` becomes
 `PR_APPROVER_SLACK_BOT_TOKEN`. `--no-prefix` uses shared
 `SLACK_BOT_TOKEN` and `SLACK_APP_TOKEN`. `--channel-posts` subscribes
@@ -676,12 +707,12 @@ The `github` pack discovers `githubChannel()` definitions and sends live
 or synthesized deliveries to them.
 
 ```bash
-agentkit github doctor [--install] [--json]
-agentkit github events [--dir <path>] [--host <host>] [--port <n>] [--json]
-agentkit github forward [--dir <path>] [--slug <slug>] [--channel <id>]
+agent-sdk github doctor [--install] [--json]
+agent-sdk github events [--dir <path>] [--host <host>] [--port <n>] [--json]
+agent-sdk github forward [--dir <path>] [--slug <slug>] [--channel <id>]
     [--repo owner/repo | --org <org>] [--events a,b,c] [--url <url>]
     [--host <host>] [--port <n>] [--secret <secret>] [--install]
-agentkit github replay <pr-url|owner/repo#N> --dir .
+agent-sdk github replay <pr-url|owner/repo#N> --dir .
     [--events a,b,c|'*'] [--action <action>] [--conclusion <result>]
     [--comment <body>] [--context <name>] [--slug <slug>] [--channel <id>]
     [--host <host>] [--port <n>] [--url <url>] [--secret <secret>]

package/docs/reference/connections.md

@@ -42,8 +42,8 @@ export default defineConnection({
 ```
 
 ```bash
-agentkit mcp oauth inventory           # browser PKCE → local mcp-auth.json
-agentkit mcp oauth inventory --store   # also upsert deployment secrets
+agent-sdk mcp oauth inventory           # browser PKCE → local mcp-auth.json
+agent-sdk mcp oauth inventory --store   # also upsert deployment secrets
 ```
 
 Full walkthrough: [Host MCP OAuth](../guides/mcp-oauth.md). Companion
@@ -94,7 +94,7 @@ export default defineConnection({
 });
 ```
 
-The host must be signed in (`agentkit login` or `CURSOR_API_KEY`).
+The host must be signed in (`agent-sdk login` or `CURSOR_API_KEY`).
 `serve` fails fast at startup otherwise, and logs each connector's live
 status (`connected`, `needsAuth`, `error`) as it starts.
 

package/docs/reference/http-api.md

@@ -5,7 +5,7 @@ description: "Every route the server mounts: sessions, approvals, deterministic
 
 # HTTP API reference
 
-Every agentkit host speaks the same stable HTTP API. In the default
+Every Agent SDK host speaks the same stable HTTP API. In the default
 multi-agent layout each agent is namespaced under its slug
 (`/<slug>/v1/session`, `/<slug>/playground`), with host-level routes at
 the root. With `--mode single`, one agent serves the same surface
@@ -132,7 +132,7 @@ Five read-only routes describe the running agent.
 
 | Route                  | What it does                                                                                                                                                                             |
 | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `GET /v1/info`         | The manifest snapshot: model, tools, skills, MCP connections, subagents, channels and routes (with schemas), schedules, hooks, A/B experiments, diagnostics; the same shape as `agentkit info --json` |
+| `GET /v1/info`         | The manifest snapshot: model, tools, skills, MCP connections, subagents, channels and routes (with schemas), schedules, hooks, A/B experiments, diagnostics; the same shape as `agent-sdk info --json` |
 | `GET /v1/health`       | Per-agent liveness, no auth                                                                                                                                                              |
 | `GET /v1/meta`         | SPA bootstrap: agent name, dev flag, base path (no auth)                                                                                                                                 |
 | `GET /v1/logs?after=N` | Recent server log lines from the ring buffer, with a polling cursor                                                                                                                      |

package/docs/reference/project-layout.md

@@ -5,9 +5,9 @@ description: "The folder structure under agent/ and the path-derived naming rule
 
 # Project layout
 
-agentkit builds an agent by walking the filesystem under `agent/`.
+The Agent SDK builds an agent by walking the filesystem under `agent/`.
 Each folder has a defined purpose. The path a file lands in determines
-how agentkit loads it.
+how the Agent SDK loads it.
 
 ## Folder structure
 
@@ -92,9 +92,9 @@ Each path maps to a capability and a reference page.
 `agent/` is discovery surface. A stray `.ts` file in one of these
 folders is treated as a definition.
 
-## Why didn't agentkit discover my file?
+## Why didn't the Agent SDK discover my file?
 
-Run `agentkit validate --dir .` and `agentkit info --dir .`.
+Run `agent-sdk validate --dir .` and `agent-sdk info --dir .`.
 `validate` prints diagnostics, and `serve` refuses to start on
 error-severity ones. Warnings, such as cloud runtime combined with
 local-only capabilities, print but don't block. `info` lists the discovered
@@ -103,9 +103,9 @@ there, check the folder reference: the file is usually in the wrong directory
 or has the wrong extension.
 
 ```bash
-agentkit validate --dir .    # diagnostics; non-zero exit on errors
-agentkit info --dir .        # human-readable surface
-agentkit info --dir . --json # machine-readable manifest (same shape as GET /v1/info)
+agent-sdk validate --dir .    # diagnostics; non-zero exit on errors
+agent-sdk info --dir .        # human-readable surface
+agent-sdk info --dir . --json # machine-readable manifest (same shape as GET /v1/info)
 ```
 
 ## What's next

package/docs/reference/schedules.md

@@ -66,7 +66,7 @@ and `host` (shared services: `host.mcp`, `host.github`, `host.slack`,
 
 ### Dispatch and dev mode
 
-In production (`agentkit serve`), schedules fire on their cron
+In production (`agent-sdk serve`), schedules fire on their cron
 cadence. Disable them with `--no-schedules`. There's no cross-host
 coordination, so run them in exactly one process per project.