Use the mods API changedplugins/mods/api
Nearest release: v2.1.306, published under an hour after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 21 Oct 2026 02:10 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 22 Oct 2026 18:07 UTC.
Upstream edited
Recorded here
Lines+27added
Lines−27removed
From line
2
where the diff opens
First seen
1 Oct 2026
this site's first read of the page
Recorded edits13to this page, all time
The whole hunk
from line 2, old and new numbered
/
from line 2
22
33> Call the mods API from a Claude Code mod to add commands and tools, call a model, run work on a timer, message other sessions, and reach files and the network.
44
5The mods API is the set of methods a mod calls to act: add commands and tools, call a model, run work between events, and reach the file system, processes, and the network. Every hook receives it as its first argument, `$`, with the methods grouped in namespaces such as `$.ui` and `$.fs`. [Events](/docs/en/plugins/mods/events) decide when a hook runs, and the mods API is what the hook calls once it does.
5The mods API is the set of methods a mod calls to act: add commands and tools, call a model, run work between events, and reach the file system, processes, and the network. Every hook receives it as its first argument, `$`, with the methods grouped in namespaces such as `$.ui` and `$.fs`. [Events](/docs/en/plugins/mods/events.md) decide when a hook runs, and the mods API is what the hook calls once it does.
66
7Build your [first mod](/docs/en/plugins/mods/create) before you start here. For every method, see [mods API methods](/docs/en/plugins/mods/reference#mods-api-methods) or read [the types for your build](/docs/en/plugins/mods/create#get-the-types-for-your-build).
7Build your [first mod](/docs/en/plugins/mods/create.md) before you start here. For every method, see [mods API methods](/docs/en/plugins/mods/reference.md#mods-api-methods) or read [the types for your build](/docs/en/plugins/mods/create.md#get-the-types-for-your-build).
88
99## Add a command or a tool
1010
from line 30
3030
3131After the session starts, `/standup` appears with its description in the list you see when you type `/`. The `argumentHint` shows in the prompt after you type the command and a space, as in `/standup [days]`. When you run `/standup 3`, the second hook returns `Summary for the last 3 day(s): ...`, and the transcript shows that text after the plugin's name. The hook never calls `next`, because the command has no behavior other than yours.
3232
33The `text` you return prints in the transcript and Claude reads it. To print nothing, as a command that only opens a [pane](/docs/en/plugins/mods/interface#pick-where-to-draw) does, return `{}`. To let the command run while Claude is working, add `immediate: true` to the registration.
33The `text` you return prints in the transcript and Claude reads it. To print nothing, as a command that only opens a [pane](/docs/en/plugins/mods/interface.md#pick-where-to-draw) does, return `{}`. To let the command run while Claude is working, add `immediate: true` to the registration.
3434
3535Pick a name that no built-in command uses. Type `/` in a session to see them. `$.command.register` throws for a taken name, with a message such as `"/focus" refused: it is the built-in /focus`. A hook that throws is skipped, so the rest of your `session.start` hook doesn't run either. Register commands last in that hook, or wrap the call in `try` and `catch`.
3636
from line 63
6363
6464> [!TIP]
6565>
66> When [MCP tool search](/docs/en/mcp#scale-with-mcp-tool-search) defers a registered tool, Claude sees its name but not its description until it searches for it. If Claude should consider the tool on every turn, add [`isDeferred: false`](/docs/en/plugins/mods/reference#tools) to the registration to [load the full tool upfront](/docs/en/mcp#exempt-a-server-from-deferral). The field requires Claude Code v2.1.293 or later, and earlier versions ignore it.
66> When [MCP tool search](/docs/en/mcp.md#scale-with-mcp-tool-search) defers a registered tool, Claude sees its name but not its description until it searches for it. If Claude should consider the tool on every turn, add [`isDeferred: false`](/docs/en/plugins/mods/reference#tools) to the registration to [load the full tool upfront](/docs/en/mcp.md#exempt-a-server-from-deferral). The field requires Claude Code v2.1.293 or later, and earlier versions ignore it.
6767
6868## Call a model
6969
from line 74
7474| In the request | `$.model.complete` | `$.model.fork` |
7575| :- | :- | :- |
7676| Model | The `model` you pass | The session's model |
77| System prompt | A short [attribution block](/docs/en/llm-gateway-protocol#system-prompt-attribution-block), then your `system` if you pass one | The session's system prompt |
77| System prompt | A short [attribution block](/docs/en/llm-gateway-protocol.md#system-prompt-attribution-block), then your `system` if you pass one | The session's system prompt |
7878| Messages | One user message, your `prompt` | The conversation so far, then your `prompt` as a user message |
7979| CLAUDE.md and other project context | Not included | Included, as in the conversation's last request |
8080| Tools | None | Claude's tools, which the model can't call |
8181
82A fork repeats the conversation's last request, so the Claude API serves most of it from the [prompt cache](/docs/en/prompt-caching) while the conversation is still cached.
82A fork repeats the conversation's last request, so the Claude API serves most of it from the [prompt cache](/docs/en/prompt-caching.md) while the conversation is still cached.
8383
84Both calls use the session's credentials, so they bill to the user's plan, API key, or cloud provider. [The types for your build](/docs/en/plugins/mods/create#get-the-types-for-your-build) document every `$.model` method.
84Both calls use the session's credentials, so they bill to the user's plan, API key, or cloud provider. [The types for your build](/docs/en/plugins/mods/create.md#get-the-types-for-your-build) document every `$.model` method.
8585
8686### Send one prompt
8787
from line 110
110110
111111A Claude API failure doesn't reject the call, so check `r.isAnswered`, and read `r.reason` when it's `false`. The call rejects for a request Claude Code won't send, such as a model your organization blocks.
112112
113[The types for your build](/docs/en/plugins/mods/create#get-the-types-for-your-build) list the other options, such as `effort`, and the [limits](/docs/en/plugins/mods/reference#limits) give the `maxTokens` default.
113[The types for your build](/docs/en/plugins/mods/create.md#get-the-types-for-your-build) list the other options, such as `effort`, and the [limits](/docs/en/plugins/mods/reference.md#limits) give the `maxTokens` default.
114114
115115### Use prompt caching
116116
from line 149
149149Put the static content that your calls share at the start of `prompt` unless you know that your requests go directly to the Claude API:
150150
151151* **Directly to the Claude API, with an API key or a Claude subscription**: either field works
152* **Through [Amazon Bedrock](/docs/en/amazon-bedrock), [Claude Platform on AWS](/docs/en/claude-platform-on-aws), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), [Microsoft Foundry](/docs/en/microsoft-foundry), or an [LLM gateway](/docs/en/llm-gateway)**: use `prompt`. Claude Code begins the system prompt with an [attribution block](/docs/en/llm-gateway-protocol#system-prompt-attribution-block) whose fingerprint comes from the start of the user message. The `api.anthropic.com` endpoint strips that block before caching. Other endpoints receive it as part of the prompt, so a breakpoint in `system` can miss when `prompt` starts differently.
152* **Through [Amazon Bedrock](/docs/en/amazon-bedrock.md), [Claude Platform on AWS](/docs/en/claude-platform-on-aws.md), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai.md), [Microsoft Foundry](/docs/en/microsoft-foundry.md), or an [LLM gateway](/docs/en/llm-gateway)**: use `prompt`. Claude Code begins the system prompt with an [attribution block](/docs/en/llm-gateway-protocol.md#system-prompt-attribution-block) whose fingerprint comes from the start of the user message. The `api.anthropic.com` endpoint strips that block before caching. Other endpoints receive it as part of the prompt, so a breakpoint in `system` can miss when `prompt` starts differently.
153153* **In a mod that other people run**: use `prompt`, because you don't choose their provider
154154
155155`system` comes before `prompt` in the prefix, so a breakpoint in `prompt` covers `system` too, and a call with a different `system` misses the cache.
from line 164
164164
165165* **The prefix is too short**: the API doesn't cache a prefix under the model's [minimum length](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations), and it returns no error
166166* **Prompt caching is disabled**: when a [`DISABLE_PROMPT_CACHING` variable](/docs/en/prompt-caching#disable-prompt-caching) applies to the model, Claude Code removes the breakpoints and sends the text uncached
167* **Your gateway strips `cache_control`**: a gateway can [remove the field and still return success](/docs/en/prompt-caching#where-the-cache-lives)
167* **Your gateway strips `cache_control`**: a gateway can [remove the field and still return success](/docs/en/prompt-caching.md#where-the-cache-lives)
168168* **Another mod rewrites the start of the text**: Claude Code then [sends it without breakpoints](#what-a-model-complete-hook-receives)
169169
170170### What a `model.complete` hook receives
from line 179
179179
180180## Run work in the background
181181
182Work that outlives one event, such as checking on something once a minute, runs on a timer you start from `session.start`. A hook itself runs for one event and has a [time limit](/docs/en/plugins/mods/reference#limits) on its own execution time. Time spent waiting on `next` or on a mods API call doesn't count, except a `$.clock.sleep`. `$.clock.every` and `$.clock.after` take the place of `setInterval` and `setTimeout`, with the delay in milliseconds first: `$.clock.after(5000, fn)` calls `fn` once, five seconds from now. Each returns a timer with a `cancel()` method, and `await $.clock.now()` gives the time in milliseconds.
182Work that outlives one event, such as checking on something once a minute, runs on a timer you start from `session.start`. A hook itself runs for one event and has a [time limit](/docs/en/plugins/mods/reference.md#limits) on its own execution time. Time spent waiting on `next` or on a mods API call doesn't count, except a `$.clock.sleep`. `$.clock.every` and `$.clock.after` take the place of `setInterval` and `setTimeout`, with the delay in milliseconds first: `$.clock.after(5000, fn)` calls `fn` once, five seconds from now. Each returns a timer with a `cancel()` method, and `await $.clock.now()` gives the time in milliseconds.
183183
184184This hook looks up a pull request's checks once a minute and shows the result under the prompt. `summarize` is a function of your own that turns the command's JSON output into a few words:
185185
from line 196
196196})
197197```
198198
199The session starts as usual. A minute later, a line appears under the prompt with a `⚠`, the mod's name, and then `checks:` and your summary. It's replaced once a minute after that. The timer's callback runs outside any event, so it keeps running between turns and doesn't start one. If the callback throws, the error goes to the [debug log](/docs/en/plugins/mods/troubleshoot#read-the-debug-log) and the timer runs again at the next interval.
199The session starts as usual. A minute later, a line appears under the prompt with a `⚠`, the mod's name, and then `checks:` and your summary. It's replaced once a minute after that. The timer's callback runs outside any event, so it keeps running between turns and doesn't start one. If the callback throws, the error goes to the [debug log](/docs/en/plugins/mods/troubleshoot.md#read-the-debug-log) and the timer runs again at the next interval.
200200
201201### Show something without starting a turn
202202
from line 205
205205| Call | What the user sees |
206206| :- | :- |
207207| `$.ui.status(text)` | One line under the prompt that stays until you change it. It starts with `⚠` and the mod's name, as in `⚠ my-mod: checks: 3 passing`. |
208| `$.ui.toast(text)` | A toast notification with the mod's name that disappears after a few seconds. It's a box at the top right in [fullscreen rendering](/docs/en/fullscreen), and one line at the right under the prompt in the classic renderer. |
208| `$.ui.toast(text)` | A toast notification with the mod's name that disappears after a few seconds. It's a box at the top right in [fullscreen rendering](/docs/en/fullscreen.md), and one line at the right under the prompt in the classic renderer. |
209209| `$.ui.log(text)` | A dim line in the transcript that Claude doesn't read. It starts with `●` and the mod's name, as in `● my-mod: build finished`. |
210210| `$.ui.notify(text)` | A notification from their terminal, outside Claude Code, sent the way their [`preferredNotifChannel`](/docs/en/settings-reference#preferrednotifchannel) setting says. The mod's name is its title unless you pass a non-empty `{ title }`, which is shown as you give it. |
211211
from line 244
244244})
245245```
246246
247In the [VS Code extension](/docs/en/plugins/mods/interface#draw-in-the-vs-code-extension), status lines and toasts show above the prompt box instead, and log lines in the conversation.
247In the [VS Code extension](/docs/en/plugins/mods/interface.md#draw-in-the-vs-code-extension), status lines and toasts show above the prompt box instead, and log lines in the conversation.
248248
249249### Start a turn from a background job
250250
from line 269
269269* **`the session was stopped and nobody has sent input since`**: the call was refused
270270* **`was removed from the queue before it ran`**: the prompt or command left the queue without running and was dropped, for example when the user stopped the turn
271271
272In this example, call `submitPrompt` from your background job in place of [`$.prompt.submit`](#start-a-turn-from-a-background-job). Put the `pendingText` variable and the `submitPrompt` function above [`register`](/docs/en/plugins/mods/reference#files), and the `turn.complete` hook inside it, because [validation](/docs/en/plugins/mods/create#check-what-claude-code-reads-from-your-mod) refuses `$` passed to a function declared inside `register`. When the result or the error carries one of those strings, `submitPrompt` keeps the text in `pendingText` for the `turn.complete` hook to submit again:
272In this example, call `submitPrompt` from your background job in place of [`$.prompt.submit`](#start-a-turn-from-a-background-job). Put the `pendingText` variable and the `submitPrompt` function above [`register`](/docs/en/plugins/mods/reference#files), and the `turn.complete` hook inside it, because [validation](/docs/en/plugins/mods/create.md#check-what-claude-code-reads-from-your-mod) refuses `$` passed to a function declared inside `register`. When the result or the error carries one of those strings, `submitPrompt` keeps the text in `pendingText` for the `turn.complete` hook to submit again:
273273
274274```javascript theme={null}
275275// The text of the last refused or dropped prompt, or null
from line 317
317317| `$.command.run` | Rejects with an error whose message ends with `<reason>` |
318318| [`$.agent.spawn`](/docs/en/plugins/mods/reference#mods-api-methods) | Resolves with `{ deny: '<reason>' }` and starts no subagent |
319319| `$.session.send` to a subagent that finished | Resolves with `{ isDelivered: false, reason: 'Agent "<id>" was not resumed: <reason>.' }`, where `<id>` is the subagent's id. A subagent that's still running receives the message. |
320| `$.session.send` to an [agent team](/docs/en/agent-teams) teammate | Resolves with `{ isDelivered: false, reason: 'Teammate "<name>" was not messaged: <reason>.' }`, where `<name>` is the teammate's name |
320| `$.session.send` to an [agent team](/docs/en/agent-teams.md) teammate | Resolves with `{ isDelivered: false, reason: 'Teammate "<name>" was not messaged: <reason>.' }`, where `<name>` is the teammate's name |
321321| [`$.tool.call`](/docs/en/plugins/mods/reference#mods-api-methods) of Bash with `run_in_background: true`, Monitor, or CronCreate | Resolves with `{ deny: '<tool> was not run: it starts background work, a schedule or a goal, and <reason>' }`, where `<tool>` is the tool's name |
322322
323323Along with these `$.session.send` and `$.tool.call` results, the user can see the [`Stopped:` toast](/docs/en/plugins/mods/troubleshoot#stopped-type-a-message-to-continue).
from line 339
339339
340340## Send and receive messages between sessions
341341
342A mod can send a plain-text message to another of your sessions, to one of this session's subagents, or to a teammate in its [agent team](/docs/en/agent-teams). It can also observe the messages that arrive and leave.
342A mod can send a plain-text message to another of your sessions, to one of this session's subagents, or to a teammate in its [agent team](/docs/en/agent-teams.md). It can also observe the messages that arrive and leave.
343343
344344To send one, call `$.session.send({ to, text })`, which makes the same delivery the SendMessage tool makes. Set `to` by who receives the message:
345345
from line 371
371371| `session.receive` | A message arrives for this session, before Claude reads it | `e.text`, and `e.origin.kind`, such as `peer` or `peer-send-message` for another session or agent, `task-notification`, or `scheduled-trigger`. Return `{ consumed: reason }` to keep it from Claude. |
372372| `session.send` | A message is about to leave, from the SendMessage tool or a mod | `e.to`, `e.text`, and `e.origin.kind`, which is `model` or `plugin` |
373373
374A session set to [refuse inbound messages](/docs/en/cross-session-messaging#control-inbound-messages) refuses a message before `session.receive` fires, so a hook never sees it. A message that's held for your approval reaches the hook first, so a mod can read a message you haven't approved yet. The hook's `next(e)` rejects when the message isn't delivered.
374A session set to [refuse inbound messages](/docs/en/cross-session-messaging.md#control-inbound-messages) refuses a message before `session.receive` fires, so a hook never sees it. A message that's held for your approval reaches the hook first, so a mod can read a message you haven't approved yet. The hook's `next(e)` rejects when the message isn't delivered.
375375
376376The sender's name on a received message is whatever the sender wrote, so don't base a decision on it.
377377
from line 395
395395* **Paths**: a relative path resolves against the working directory of the session, or of the subagent whose event the hook is handling
396396* **`$.fs.list`**: returns one directory's entries as `{ name, kind, size, isLink }` and isn't recursive
397397* **`$.process.run`**: takes an argument list and uses no shell. It resolves to `{ exitCode, stdout, stderr }` whatever the exit code. It rejects if the program can't start or is still running at the timeout, which is 30 seconds by default, so wrap it in `try` and `catch`.
398* **`$.http.fetch`**: follows up to five redirects. On a redirect to a different origin, it keeps only the `accept`, `accept-language`, `content-type`, and `user-agent` request headers you set and drops the rest, so a request that depends on another header, such as `Authorization`, can fail after that redirect. The [limits](/docs/en/plugins/mods/reference#limits) give its timeout and body sizes.
398* **`$.http.fetch`**: follows up to five redirects. On a redirect to a different origin, it keeps only the `accept`, `accept-language`, `content-type`, and `user-agent` request headers you set and drops the rest, so a request that depends on another header, such as `Authorization`, can fail after that redirect. The [limits](/docs/en/plugins/mods/reference.md#limits) give its timeout and body sizes.
399399
400Every one of these calls is itself an event, named for its namespace and method without the `$.`, such as `fs.read` for `$.fs.read`. A mod [earlier in the chain](/docs/en/plugins/mods/events#the-order-mods-run-in) can observe, rewrite, or refuse your call, which is how an organization restricts what mods reach.
400Every one of these calls is itself an event, named for its namespace and method without the `$.`, such as `fs.read` for `$.fs.read`. A mod [earlier in the chain](/docs/en/plugins/mods/events.md#the-order-mods-run-in) can observe, rewrite, or refuse your call, which is how an organization restricts what mods reach.
401401
402402A mod can refuse your `$.process.spawn` call after the command has produced output or exited, and nothing the command did is undone. The call then rejects with a message that ends with one of these strings and the refusing mod's reason:
403403
from line 406
406406
407407## Next steps
408408
409* [React to events](/docs/en/plugins/mods/events): hook tool calls, prompts, and turns
410* [Draw in the interface](/docs/en/plugins/mods/interface): show what your mod collects in a pane or above the prompt
411* [Test a mod](/docs/en/plugins/mods/test): stub any of these calls in a test
412* [Mods reference](/docs/en/plugins/mods/reference): events, mods API methods, and limits
409* [React to events](/docs/en/plugins/mods/events.md): hook tool calls, prompts, and turns
410* [Draw in the interface](/docs/en/plugins/mods/interface.md): show what your mod collects in a pane or above the prompt
411* [Test a mod](/docs/en/plugins/mods/test.md): stub any of these calls in a test
412* [Mods reference](/docs/en/plugins/mods/reference.md): events, mods API methods, and limits
413413
No line in this hunk matches that.