@cursor/july 0.1.29 → 0.1.31

package/docs/building-with-agents.md

@@ -10,7 +10,7 @@ scaffolding, channels, verification, evals, and measured improvement.
 
 ## What can a coding agent build for me?
 
-A coding agent can take a agentkit project from an idea to a
+A coding agent can take an Agent SDK project from an idea to a
 verified first version. It can:
 
 - Create the project and choose the smallest useful surface
@@ -65,7 +65,7 @@ the workflow, commands, and common mistakes for that task.
 
 > [!NOTE]
 > The skill bodies use the current `agent-serve` CLI names. This guide
-> uses the upcoming `agentkit` names. See
+> uses the upcoming `agent-sdk` names. See
 > [Run the CLI](./README.md#run-the-cli) for the full rename table.
 
 ## How does a coding agent verify its work?
@@ -74,19 +74,19 @@ The coding agent should discover the project, test each server tool,
 run a real turn, and finish with evals:
 
 ```bash
-agentkit validate --dir .
-agentkit info --dir . --json
+agent-sdk validate --dir .
+agent-sdk info --dir . --json
 
-agentkit call inspect_pr --dir . \
+agent-sdk call inspect_pr --dir . \
   --input '{"prUrl":"https://github.com/acme/checkout/pull/42"}'
 
-agentkit run --dir . \
+agent-sdk run --dir . \
   --message "Is https://github.com/acme/checkout/pull/42 ready to approve?"
 
-agentkit trajectory --events .agentkit/traces/<sessionId>.ndjson
+agent-sdk trajectory --events .agent-sdk/traces/<sessionId>.ndjson
 
-agentkit eval --dir . --list
-agentkit eval --dir . --json
+agent-sdk eval --dir . --list
+agent-sdk eval --dir . --json
 ```
 
 `serve` boots without an API key, which is enough to check channel

package/docs/concepts.md

@@ -1,11 +1,11 @@
 ---
-title: "How agentkit works"
+title: "How the Agent SDK works"
 description: "Understand projects, sessions, event streams, channels, and runtimes in plain language."
 ---
 
-# How agentkit works
+# How the Agent SDK works
 
-An agent is a folder of instructions and capabilities. agentkit
+An agent is a folder of instructions and capabilities. The Agent SDK
 discovers those files, runs conversations, and records what happened.
 
 ## What happens when someone sends a message?
@@ -17,7 +17,7 @@ Follow one message through the system:
 2. The channel starts a session or continues an existing one.
 3. The runtime gives the model its instructions, tools, and workspace.
 4. The model replies and can call tools along the way.
-5. agentkit appends every message and tool call to the session's
+5. The Agent SDK appends every message and tool call to the session's
    event stream.
 
 The channel is the front door. The runtime does the work. The event
@@ -26,7 +26,7 @@ stream is the record you inspect later.
 ## How do files become an agent?
 
 Each capability has a home in the project. The path tells
-agentkit what to load. The filename becomes the capability's
+the Agent SDK what to load. The filename becomes the capability's
 name. For example, `agent/tools/get_weather.ts` creates a tool named
 `get_weather`.
 
@@ -42,13 +42,13 @@ name. For example, `agent/tools/get_weather.ts` creates a tool named
 | `evals/**/*.eval.ts` | Repeatable checks at the project root |
 
 Other folders add subagents, hooks, schedules, and workspace files. You
-don't register them elsewhere. Run `agentkit validate` to catch
+don't register them elsewhere. Run `agent-sdk validate` to catch
 invalid files before serving the project.
 
 See [Project layout](./reference/project-layout.md) for every supported
 path.
 
-## How does agentkit identify a conversation?
+## How does the Agent SDK identify a conversation?
 
 A session is one durable conversation. It has two identifiers:
 
@@ -75,7 +75,7 @@ Each session writes an append-only NDJSON file:
 
 Sessions and their event streams survive server restarts. The
 playground renders the stream. Evals assert against it. The
-`agentkit trajectory` command turns a saved stream into a short
+`agent-sdk trajectory` command turns a saved stream into a short
 summary.
 
 When a run surprises you, inspect its event stream first. See
@@ -117,14 +117,14 @@ Choose a runtime in `agent/agent.ts`:
 
 Use the local runtime when the host has the tools and files the agent
 needs. Use the cloud runtime when each turn needs an isolated repository
-checkout. `agentkit validate` warns when a cloud agent uses a
+checkout. `agent-sdk validate` warns when a cloud agent uses a
 local-only capability.
 
 See [Cloud runtime](./guides/cloud-runtime.md) for setup and trade-offs.
 
 ## What files can a local session access?
 
-Each local session gets its own workspace. agentkit writes the
+Each local session gets its own workspace. The Agent SDK writes the
 instructions as `AGENTS.md`, installs authored skills, copies sandbox
 files, and adds agent tool scripts.
 
@@ -137,7 +137,7 @@ commands already use temporary state.
 Durable local state uses this shape:
 
 ```text
-<project>/.agentkit/
+<project>/.agent-sdk/
   sessions/<id>/events.ndjson
   sessions/<id>/workspace/
   traces/<sessionId>.ndjson

package/docs/deployment.md

@@ -1,9 +1,9 @@
 ---
 title: "Deployment"
-description: "Deploy agentkit with Cursor-managed hosting or on infrastructure you control."
+description: "Deploy the Agent SDK with Cursor-managed hosting or on infrastructure you control."
 ---
 
-# Deploy agentkit
+# Deploy the Agent SDK
 
 Both options run the same agent project and HTTP API. Channel delivery
 paths differ. Cursor-managed hosting is preferred for most agents.
@@ -56,10 +56,10 @@ creating the deployment. Names beginning with `CURSOR_` are reserved.
 
 For `defineConnection({ url, oauth: true })`, declare
 `MCP_OAUTH_<CONNECTION>_*` in `secretNames`, authorize with
-`agentkit mcp oauth <connection> --store`, then redeploy. See
+`agent-sdk mcp oauth <connection> --store`, then redeploy. See
 [Host MCP OAuth](./guides/mcp-oauth.md).
 
-Run `agentkit validate` before deploying. It reports invalid domains and
+Run `agent-sdk validate` before deploying. It reports invalid domains and
 secret names as warnings, so fix them even when validation exits zero.
 
 ### Deploy from Git
@@ -68,10 +68,10 @@ Sign in, validate the project, and deploy it:
 
 ```bash
 cd my-agent
-agentkit login
-agentkit whoami
-agentkit validate
-agentkit deploy
+agent-sdk login
+agent-sdk whoami
+agent-sdk validate
+agent-sdk deploy
 ```
 
 Inside a Git checkout, `deploy` infers the HTTPS `origin` URL, current
@@ -79,7 +79,7 @@ branch or detached commit, agent path, and deployment slug. Explicit
 flags override each value:
 
 ```bash
-agentkit deploy \
+agent-sdk deploy \
   --repo https://github.com/acme/agents \
   --ref main \
   --path agents/weather \
@@ -108,9 +108,9 @@ The command waits up to ten minutes for a running engine. Use
 it separately:
 
 ```bash
-agentkit deployments
-agentkit deployment weather-agent
-agentkit logs --prod --slug weather-agent
+agent-sdk deployments
+agent-sdk deployment weather-agent
+agent-sdk logs --prod --slug weather-agent
 ```
 
 ### Set deployment secrets
@@ -119,9 +119,9 @@ A deployment must exist before you can set its secrets. Omit values from
 the command line to enter them through the hidden prompt:
 
 ```bash
-agentkit secrets set weather-agent WEATHER_API_KEY
-agentkit secrets list weather-agent
-agentkit deploy --dir . --slug weather-agent
+agent-sdk secrets set weather-agent WEATHER_API_KEY
+agent-sdk secrets list weather-agent
+agent-sdk deploy --dir . --slug weather-agent
 ```
 
 The engine reads secret changes on its next deploy. `secrets list`
@@ -151,18 +151,18 @@ can't add this header.
 Use `--prod` with the normal client commands:
 
 ```bash
-agentkit playground --prod --slug weather-agent
-agentkit chat --prod --slug weather-agent
-agentkit run --prod --slug weather-agent --message "Forecast for Paris"
-agentkit sessions --prod --slug weather-agent
-agentkit logs --prod --slug weather-agent
+agent-sdk playground --prod --slug weather-agent
+agent-sdk chat --prod --slug weather-agent
+agent-sdk run --prod --slug weather-agent --message "Forecast for Paris"
+agent-sdk sessions --prod --slug weather-agent
+agent-sdk logs --prod --slug weather-agent
 ```
 
 Keep `playground --prod` running while the playground is open. Press
 Ctrl-C to stop it.
 
 The first deployment prints a reusable alias token once. Store it
-immediately. Run `agentkit deployment weather-agent` to retrieve the
+immediately. Run `agent-sdk deployment weather-agent` to retrieve the
 stable alias URL later. The token remains valid until rotation and can't
 be retrieved.
 
@@ -177,7 +177,7 @@ curl "$AGENT_ALIAS_URL/v1/health" \
 rotate it. The old token stops working immediately:
 
 ```bash
-agentkit rotate-token weather-agent
+agent-sdk rotate-token weather-agent
 ```
 
 ### Connect GitHub
@@ -187,7 +187,7 @@ Let the hosted engine pull Cursor SCM events. Repeat
 agent:
 
 ```bash
-agentkit deploy --dir . \
+agent-sdk deploy --dir . \
   --slug pr-approver \
   --cursor-events-repo acme/checkout \
   --cursor-events-repo acme/payments
@@ -231,13 +231,25 @@ import { slackChannel } from "@cursor/july/channels/slack";
 export default slackChannel({ envPrefix: "PR_APPROVER" });
 ```
 
-The prefix selects the deployment secret names:
+Provision the dedicated app from the dashboard. Open the deployment
+under **Deployed Agents** at
+[cursor.com/dashboard](https://cursor.com/dashboard), switch to
+**Details**, and expand **Slack** under **Integrations**. **Add to
+Slack** connects the workspace with a one-time authorization, and
+**Create Slack app** creates and installs the app, then stores its
+tokens as deployment secrets automatically. Redeploy when prompted so
+the running agent picks them up. See
+[Provision from the dashboard](./guides/slack.md#provision-from-the-dashboard-hosted-deployments)
+for the walkthrough, including workspace-admin approval.
+
+If you created the Slack app by hand instead, set its tokens as
+deployment secrets yourself. The prefix selects the secret names:
 
 ```bash
-agentkit secrets set pr-approver \
+agent-sdk secrets set pr-approver \
   PR_APPROVER_SLACK_BOT_TOKEN \
   PR_APPROVER_SLACK_APP_TOKEN
-agentkit deploy --dir . --slug pr-approver
+agent-sdk deploy --dir . --slug pr-approver
 ```
 
 Without `envPrefix`, a dedicated app reads `SLACK_BOT_TOKEN` and
@@ -251,17 +263,17 @@ continues to point at the active generation. Follow the same source rules
 from [Deploy from Git](#deploy-from-git).
 
 ```bash
-agentkit deploy --dir /path/to/my-agent --slug weather-agent
-agentkit stop weather-agent
+agent-sdk deploy --dir /path/to/my-agent --slug weather-agent
+agent-sdk stop weather-agent
 ```
 
 `stop` waits for the deployment to stop unless you pass `--no-wait`.
 See the [CLI reference](./reference/cli.md#deploy) for the full command
 reference.
 
-## Self-host agentkit
+## Self-host the Agent SDK
 
-agentkit runs as a Node HTTP server on Node 22.13 or newer. You can host
+The Agent SDK runs as a Node HTTP server on Node 22.13 or newer. You can host
 it on a VM, container platform, or ECS.
 
 ### The security model in one minute
@@ -284,13 +296,13 @@ A self-hosted server can read these credentials.
 
 | Credential | Used for | Provide it as |
 | --- | --- | --- |
-| Cursor API key | model turns, cloud runtime, Cursor account MCP connections | `agentkit login` (stores a revocable key), `CURSOR_API_KEY`, or `--api-key` / `serve({ apiKey })` |
+| Cursor API key | model turns, cloud runtime, Cursor account MCP connections | `agent-sdk login` (stores a revocable key), `CURSOR_API_KEY`, or `--api-key` / `serve({ apiKey })` |
 | Slack tokens | Slack channels | `<PREFIX>_SLACK_BOT_TOKEN` + `<PREFIX>_SLACK_APP_TOKEN` per agent |
 | GitHub webhook secret | delivery signature verification | `GITHUB_WEBHOOK_SECRET`, same value on server and signer |
 | GitHub API | outbound API calls | a GitHub App (`GITHUB_APP_ID` + `GITHUB_APP_PRIVATE_KEY` + installation id) or `GITHUB_TOKEN` / `gh auth login` |
-| MCP connection tokens | authored MCP connections | env vars your `mcp-connections/*.ts` read, or host OAuth secrets from `agentkit mcp oauth <name> --store` (`MCP_OAUTH_*`; see [Host MCP OAuth](./guides/mcp-oauth.md)) |
+| MCP connection tokens | authored MCP connections | env vars your `mcp-connections/*.ts` read, or host OAuth secrets from `agent-sdk mcp oauth <name> --store` (`MCP_OAUTH_*`; see [Host MCP OAuth](./guides/mcp-oauth.md)) |
 
-Use a dedicated Cursor key per host. `agentkit whoami` shows the active
+Use a dedicated Cursor key per host. `agent-sdk whoami` shows the active
 credential. `logout` removes the stored key from the host; revoke the key
 in the Cursor dashboard to invalidate it. See
 [CLI authentication](./reference/cli.md#login--logout--whoami) for
@@ -311,12 +323,12 @@ the supervisor environment:
 
 ```bash
 export CURSOR_API_KEY="<cursor-api-key>"
-export AGENTKIT_BEARER_TOKEN="$(openssl rand -hex 32)"
+export AGENT_SDK_BEARER_TOKEN="$(openssl rand -hex 32)"
 
 # the server: all agents under one port
-agentkit serve --dir /srv/agents --port 3000 --host 127.0.0.1 \
+agent-sdk serve --dir /srv/agents --port 3000 --host 127.0.0.1 \
   --state-root /var/lib/agent-serve \
-  --bearer-token "$AGENTKIT_BEARER_TOKEN"
+  --bearer-token "$AGENT_SDK_BEARER_TOKEN"
 ```
 
 Slack Socket Mode needs no inbound network. For GitHub, prefer
@@ -332,12 +344,12 @@ forwarding requires repo-admin access; organization forwarding with
 
 ```bash
 export GITHUB_WEBHOOK_SECRET="$(openssl rand -hex 32)"
-agentkit github doctor --install
+agent-sdk github doctor --install
 gh auth login
 
 # GitHub agents only: ONE forwarder relaying live deliveries to loopback
 GITHUB_TOKEN= GH_TOKEN= \
-  agentkit github forward --dir /srv/agents --repo owner/repo
+  agent-sdk github forward --dir /srv/agents --repo owner/repo
 ```
 
 Run long-lived processes under a supervisor. systemd survives reboots;
@@ -352,13 +364,13 @@ checks), and each agent also serves `/<slug>/v1/health`.
 ### Containers
 
 Build the image with Node 22.13 or newer, the agent source, and its
-package dependencies. Run `agentkit serve` as a non-root user:
+package dependencies. Run `agent-sdk serve` as a non-root user:
 
 ```bash
-agentkit serve --dir /srv/agents --mode multi \
+agent-sdk serve --dir /srv/agents --mode multi \
   --host 0.0.0.0 --port 3000 \
   --state-root /var/lib/agent-serve \
-  --bearer-token "$AGENTKIT_BEARER_TOKEN"
+  --bearer-token "$AGENT_SDK_BEARER_TOKEN"
 ```
 
 Mount the state root as a persistent volume and inject secrets at
@@ -372,7 +384,7 @@ its directory name on one port. One process, one state root, one
 credential:
 
 ```bash
-agentkit serve --dir /srv/agents
+agent-sdk serve --dir /srv/agents
 # index at /, each agent at /<slug>/v1/*, /<slug>/playground
 ```
 
@@ -410,7 +422,7 @@ survive a restart; re-run or recreate them afterward.
 
 ### Observability
 
-Use [`agentkit logs`](./reference/cli.md#logs) for runtime output,
+Use [`agent-sdk logs`](./reference/cli.md#logs) for runtime output,
 [hooks](./reference/hooks.md) for metrics export, and
 [session traces](./reference/sessions.md#how-do-i-inspect-a-saved-event-stream)
 for incident review.

package/docs/evals.md

@@ -1,6 +1,6 @@
 ---
 title: "Evals"
-description: "Define repeatable checks with defineEval, run them with agentkit eval, and use them as regression checks."
+description: "Define repeatable checks with defineEval, run them with agent-sdk eval, and use them as regression checks."
 ---
 
 # Evals
@@ -24,7 +24,7 @@ accepted a message, and did what you asserted.
 
 ## Define evals with `defineEval`
 
-agentkit discovers evals under the project-root `evals/` directory,
+The Agent SDK discovers evals under the project-root `evals/` directory,
 in `.eval.ts` or `.eval.js` files. That's a sibling of `agent/`, never
 inside it (`agent/evals/` is silently ignored). TypeScript is the normal
 authoring format.
@@ -213,13 +213,13 @@ Run the CLI under Node 22.13 or newer. Do not use Bun. Its HTTP/2 client
 breaks tool-result streams and causes eval turns to fail.
 
 ```bash
-agentkit eval --dir . --list                         # discover only
-agentkit eval --dir .                                # run all
-agentkit eval --dir . builds/checkout                # one datapoint
-agentkit eval --dir . builds search                  # several ids or prefixes
-agentkit eval --dir . --tag smoke --tag pull-request # any matching tag
-agentkit eval --dir . --json --no-stream             # machine-readable results
-agentkit eval --dir . --verbose                      # logs + reply snippets
+agent-sdk eval --dir . --list                         # discover only
+agent-sdk eval --dir .                                # run all
+agent-sdk eval --dir . builds/checkout                # one datapoint
+agent-sdk eval --dir . builds search                  # several ids or prefixes
+agent-sdk eval --dir . --tag smoke --tag pull-request # any matching tag
+agent-sdk eval --dir . --json --no-stream             # machine-readable results
+agent-sdk eval --dir . --verbose                      # logs + reply snippets
 ```
 
 Id filters use OR semantics. Each filter selects an exact id and its
@@ -230,11 +230,11 @@ match both groups.
 
 `eval` boots an ephemeral server on port 0 with a temp state root
 outside the project, so cases don't inherit ambient monorepo rules and
-don't pollute `.agentkit/`. Point `--url` at a running server to eval
+don't pollute `.agent-sdk/`. Point `--url` at a running server to eval
 a live agent instead:
 
 ```bash
-agentkit eval --dir . \
+agent-sdk eval --dir . \
   --url http://127.0.0.1:3000/weather-agent \
   --bearer-token "$AGENT_TOKEN"
 ```
@@ -248,7 +248,7 @@ keep live progress off stderr. A TTY streams turn progress by default.
 `--verbose` still writes `t.log` lines to stderr and adds reply snippets
 to text results.
 
-Model turns need a Cursor credential from `agentkit login` or
+Model turns need a Cursor credential from `agent-sdk login` or
 `CURSOR_API_KEY`.
 
 The exit code is `0` when every selected case passes, `1` when any case
@@ -293,7 +293,7 @@ Start the server with `--dev`, open the playground, and choose
 the resulting session trace.
 
 ```bash
-agentkit serve --dir . --dev
+agent-sdk serve --dir . --dev
 ```
 
 Playground runs target the live server instead of an ephemeral one.
@@ -318,13 +318,13 @@ On `--prod` / `--url`, the CLI prints the Eval ID as soon as the batch is
 accepted (and a Playground deep link with `?view=evals&evalRunId=…`):
 
 ```bash
-agentkit eval --prod --slug vulnerability-scanner --tag deepsec
+agent-sdk eval --prod --slug vulnerability-scanner --tag deepsec
 # Eval ID: evalrun_…
-# Cancel:  agentkit eval cancel evalrun_… --prod --slug vulnerability-scanner
+# Cancel:  agent-sdk eval cancel evalrun_… --prod --slug vulnerability-scanner
 # Playground: https://…/playground?view=evals&evalRunId=evalrun_…
 
-agentkit eval cancel evalrun_… --prod --slug vulnerability-scanner
-agentkit eval status evalrun_… --prod --slug vulnerability-scanner
+agent-sdk eval cancel evalrun_… --prod --slug vulnerability-scanner
+agent-sdk eval status evalrun_… --prod --slug vulnerability-scanner
 ```
 
 The Evals tab prefers the server’s in-flight batch (`activeRunId`) over a
@@ -357,8 +357,8 @@ The right fixture depends on the surface under test.
 | Agent surface | Fixture |
 | --- | --- |
 | Chat / domain assistant | A canonical prompt string, chosen once and frozen |
-| Tool-heavy | Run `agentkit call <tool>` first to pin what the tool returns, then freeze the prompt that triggers it |
-| GitHub webhook | `agentkit github replay <pr> --events '*' --dry-run --out fixtures/github` snapshots real payloads for offline replay ([GitHub guide](./guides/github.md)) |
+| Tool-heavy | Run `agent-sdk call <tool>` first to pin what the tool returns, then freeze the prompt that triggers it |
+| GitHub webhook | `agent-sdk github replay <pr> --events '*' --dry-run --out fixtures/github` snapshots real payloads for offline replay ([GitHub guide](./guides/github.md)) |
 | PR reviewer with host preparation | Diff, metadata, and gold labels pinned to commit SHAs; keep any live PR matrix small |
 | Workspace-dependent | `workspaceFiles` in `t.send` options, never developer-machine paths |
 
@@ -398,7 +398,7 @@ suite into a list of checks that no longer protect anything.
 ## Compare variants on live traffic
 
 Use `defineAB` to compare variant metrics on live sessions. It is not a
-test runner and has no `agentkit ab` command. Keep `defineEval` as the
+test runner and has no `agent-sdk ab` command. Keep `defineEval` as the
 regression ratchet. Eval sessions do not enroll or change live metrics.
 See [Live A/B metrics](./ab.md) for assignment, behavior, collection,
 and inspection.

package/docs/example-agents/approval-buddy.md

@@ -96,14 +96,14 @@ If you enable Giphy in a hosted copy, declare its secret and
 ## Validate without approving a PR
 
 ```bash
-agentkit validate --dir examples/approval-buddy
-agentkit info --dir examples/approval-buddy --json
+agent-sdk validate --dir examples/approval-buddy
+agent-sdk info --dir examples/approval-buddy --json
 ```
 
 List the deterministic roster:
 
 ```bash
-agentkit call list_buddies \
+agent-sdk call list_buddies \
   --dir examples/approval-buddy \
   --input '{}'
 ```
@@ -112,7 +112,7 @@ Set a known merged PR, then run the read-only precheck:
 
 ```bash
 MERGED_PR_URL=https://github.com/your-org/your-repo/pull/123
-agentkit call prepare_review \
+agent-sdk call prepare_review \
   --dir examples/approval-buddy \
   --input "{\"prUrl\":\"$MERGED_PR_URL\"}"
 ```
@@ -121,7 +121,7 @@ The result should decline because the PR is no longer open. `prepare_review`
 never posts an approval.
 
 > [!CAUTION]
-> Don't use `agentkit call approve_pr` as a smoke test. The tool has no
+> Don't use `agent-sdk call approve_pr` as a smoke test. The tool has no
 > `needsApproval` gate and posts a real GitHub review when the PR qualifies.
 
 ## See why preparation is separate
@@ -175,7 +175,7 @@ posts reviews, statuses, and comments. When adapting the example, start with
 
 Every terminal status is green by design. Declines and crashed turns are
 informational, not merge-blocking. This is a product decision in the example,
-not an agentkit default.
+not an Agent SDK default.
 
 A successful turn that never calls `approve_pr` leaves the pending status in
 place. The channel clears it on `approve_pr` results and `turn.failed`, but
@@ -190,7 +190,7 @@ test.
 Start the dev server:
 
 ```bash
-agentkit dev examples/approval-buddy
+agent-sdk dev examples/approval-buddy
 ```
 
 Then ask through the signed-in account-linked Slack connection:
@@ -221,7 +221,7 @@ shorter sessions.
 List the four eval cases:
 
 ```bash
-agentkit eval --dir examples/approval-buddy --list
+agent-sdk eval --dir examples/approval-buddy --list
 ```
 
 The suite covers:
@@ -234,7 +234,7 @@ The suite covers:
 Run the safe qualification case:
 
 ```bash
-agentkit eval \
+agent-sdk eval \
   --dir examples/approval-buddy \
   qualify/merged-pr-question \
   --json

package/docs/example-agents/benny.md

@@ -33,7 +33,7 @@ The result is a thin agent project over a mature procedure library.
 2. The dedicated Socket Mode channel accepts the allowlisted channel.
 3. A 15-second debounce lets edits settle. Deleting the post during that
    window cancels the dispatch.
-4. Agentkit creates a thread-scoped session and sends the report to the
+4. The Agent SDK creates a thread-scoped session and sends the report to the
    playbook router.
 5. The instructions select the matching triage playbook.
 6. The harness finds the repository root, opens the inherited playbook, and
@@ -59,7 +59,7 @@ experiments, or sandbox seeds.
 
 ## See why `local.cwd` matters
 
-Agentkit normally keeps an ephemeral `run` or `eval` workspace outside a
+The Agent SDK normally keeps an ephemeral `run` or `eval` workspace outside a
 large monorepo. This prevents ancestor instruction and repository-rule files
 from leaking into an unrelated agent.
 
@@ -77,7 +77,7 @@ Each harness workspace lands under
 `examples/benny/.agent-serve/harness/<sessionId>`. Walking up the directory
 tree reaches the host repository and its inherited playbook directory.
 
-Those playbooks are inherited context. `agentkit info` reports zero authored
+Those playbooks are inherited context. `agent-sdk info` reports zero authored
 skills for the agent. Copying this project into another repository removes
 its main procedures unless you copy or replace the skill library too.
 
@@ -87,8 +87,8 @@ The account-linked path needs an agent-runtime login and a connected Slack
 account:
 
 ```bash
-agentkit login
-agentkit whoami
+agent-sdk login
+agent-sdk whoami
 ```
 
 It routes explicit mentions without a dedicated Slack token on the host.
@@ -99,9 +99,9 @@ For the watched-channel path, configure a dedicated Socket Mode app with:
 - have an App-Level Token with `connections:write`, and
 - be a member of the watched channel.
 
-Run `agentkit slack setup` for the guided app workflow. Generate the project
+Run `agent-sdk slack setup` for the guided app workflow. Generate the project
 manifest with `--channel-posts` when you create a new copy, then validate the
-configured channel prefix with `agentkit slack doctor`.
+configured channel prefix with `agent-sdk slack doctor`.
 
 Missing dedicated-app tokens leave that channel idle. They don't stop the
 account-linked channel.
@@ -109,9 +109,9 @@ account-linked channel.
 ## Validate and start the server
 
 ```bash
-agentkit validate --dir examples/benny
-agentkit info --dir examples/benny --json
-agentkit dev examples/benny
+agent-sdk validate --dir examples/benny
+agent-sdk info --dir examples/benny --json
+agent-sdk dev examples/benny
 ```
 
 The info output should show two Slack channels and no authored skill. That
@@ -139,7 +139,7 @@ turn and reaches the prompt.
 
 ## Inspect thread continuity
 
-Agentkit keys Slack sessions by channel and thread timestamp. A follow-up in
+The Agent SDK keys Slack sessions by channel and thread timestamp. A follow-up in
 the same thread resumes the conversation and workspace. A new top-level issue
 gets a new session.
 
@@ -150,8 +150,8 @@ sessions while the dev server runs.
 ## Run the smoke eval
 
 ```bash
-agentkit eval --dir examples/benny --list
-agentkit eval --dir examples/benny smoke --json
+agent-sdk eval --dir examples/benny --list
+agent-sdk eval --dir examples/benny smoke --json
 ```
 
 The case asks for the agent identity and the playbook used for issue triage.

package/docs/example-agents/bugbot.md

@@ -80,8 +80,8 @@ checks out the PR into the serve host's working tree.
 ## Validate the surface
 
 ```bash
-agentkit validate --dir examples/bugbot
-agentkit info --dir examples/bugbot --json
+agent-sdk validate --dir examples/bugbot
+agent-sdk info --dir examples/bugbot --json
 ```
 
 The manifest should show one server tool, one skill, and two authored
@@ -92,7 +92,7 @@ channels.
 Call the preparation tool directly:
 
 ```bash
-agentkit call prepare_pr \
+agent-sdk call prepare_pr \
   --dir examples/bugbot \
   --input '{"pr":"https://github.com/owner/repo/pull/123"}'
 ```
@@ -122,7 +122,7 @@ buffer; a larger diff fails preparation instead of being truncated.
 Start the server:
 
 ```bash
-agentkit dev examples/bugbot
+agent-sdk dev examples/bugbot
 ```
 
 From another terminal:
@@ -185,8 +185,8 @@ same skill with different intake channels.
 ## Run the fixture-backed eval
 
 ```bash
-agentkit eval --dir examples/bugbot --list
-agentkit eval --dir examples/bugbot review/smoke --json
+agent-sdk eval --dir examples/bugbot --list
+agent-sdk eval --dir examples/bugbot review/smoke --json
 ```
 
 The eval constructs a `PreparedPrReview`, seeds its file map through