cc-viewer 1.7.22 → 1.7.23

package/concepts/en/Tool-EndConversation.md

@@ -0,0 +1,35 @@
+# EndConversation
+
+Ends the current conversation and prevents any further messages from being sent.
+
+## When to Use
+
+- Only for sustained user abuse, or when the user explicitly requests a demonstration of this tool.
+
+This is a last-resort action: the tool's own rules require warning the user first and confirming before use, and it must never be used in self-harm or harm-related situations.
+
+## Activation
+
+- Requires Claude Code 2.1.213+ and a model from the Opus 4.8 / Sonnet 5 / Fable 5 or later family.
+- Interactive terminal sessions only — never in `--bare` mode, and never available to subagents.
+- Not available on Amazon Bedrock, Claude Platform on AWS, Vertex AI, Microsoft Foundry, or cloud gateways.
+- Requires a server-side feature flag — most sessions do not offer this tool.
+
+## Parameters
+
+This tool takes no parameters.
+
+## Examples
+
+### Example 1: End the conversation
+
+```
+EndConversation()
+```
+
+The flow is two-step: the first call returns a reflection message; a second call immediately after actually ends the conversation (`ended: true`).
+
+## Notes
+
+- Heavily gated: requires a supported model, the CLI entrypoint, and a server-side feature flag — most sessions do not offer this tool.
+- Once ended, no further messages can be sent in the conversation.

package/concepts/en/Tool-LSP.md

@@ -10,6 +10,11 @@ Queries Language Server Protocol (LSP) servers for code intelligence — definit
 - Find implementations of an interface or abstract method (`goToImplementation`)
 - Walk the call hierarchy of a function (`prepareCallHierarchy`, `incomingCalls`, `outgoingCalls`)
 
+## Activation
+
+- Inactive until a code-intelligence plugin for the language is installed (the server binary is installed separately).
+- The tool only appears when an LSP client is connected.
+
 ## Parameters
 
 - `operation` (string, required): one of the operations listed above.

package/concepts/en/Tool-ListAgents.md

@@ -0,0 +1,35 @@
+# ListAgents
+
+Lists the agents you can `SendMessage` to: in-process subagents you spawned, other local Claude sessions on this machine, your cloud sessions (when this session has cloud access), and — when Remote Control is connected — your account's other sessions. Each row is labeled by kind.
+
+## When to Use
+
+- You need the exact name of a peer session or subagent before sending it a message.
+- You want to see which sessions are currently reachable from this one.
+
+## Activation
+
+- Requires Claude Code 2.1.224+ and cross-session messaging (a server-side feature flag, off by default).
+- Cross-session messaging is unavailable on Amazon Bedrock, Claude Platform on AWS, Google Cloud Agent Platform, and Microsoft Foundry.
+- Off when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`, `DISABLE_TELEMETRY`, `DO_NOT_TRACK`, or `DISABLE_GROWTHBOOK` is set.
+- Force-enable with `CLAUDE_CODE_HARBOR_KITE=1`.
+
+## Parameters
+
+- `channel` (string, optional): Not available in this build; leave unset.
+- `q` (string, optional): Not available in this build; leave unset.
+
+## Examples
+
+### Example 1: List reachable agents
+
+```
+ListAgents()
+```
+
+Each row prints a name — that name is the address. Send with `SendMessage({to: "<name>", message: "..."})`, copying the name exactly as printed. Append a row's ` [ref]` only when the bare name is ambiguous (two rows share it, or an error asks you to disambiguate).
+
+## Notes
+
+- Read-only and concurrency-safe.
+- A cloud session receives your message but cannot message back yet — read its answer in its own transcript.

package/concepts/en/Tool-ListConnectors.md

@@ -0,0 +1,34 @@
+# ListConnectors
+
+Lists the MCP connectors installed for the user's claude.ai organization, optionally filtered by keyword.
+
+## When to Use
+
+- You need to know which connectors are already installed before suggesting new ones.
+- The user asks what integrations their organization has.
+
+## Activation
+
+- Only available in remote (claude.ai) sessions on the first-party API.
+
+## Parameters
+
+- `keywords` (array of strings, optional): Filter the list — up to 8 items, each 1–64 characters. Omit to list everything.
+
+## Examples
+
+### Example 1: List all installed connectors
+
+```
+ListConnectors()
+```
+
+### Example 2: Filter by keyword
+
+```
+ListConnectors(keywords=["github"])
+```
+
+## Notes
+
+- Pair with `SearchMcpRegistry` (discovery) and `SuggestConnectors` (details) for the full find-and-enable flow.

package/concepts/en/Tool-ListMcpResources.md

@@ -0,0 +1,35 @@
+# ListMcpResources
+
+Lists the resources exposed by connected MCP servers, optionally filtered to one server.
+
+## When to Use
+
+- You need to discover what resources (files, records, documents) an MCP server offers before reading them.
+- You want an overview of all resources across every connected server.
+
+## Activation
+
+- Always enabled, but not exposed to the model's tool list — intended for thin-client / sidecar use.
+
+## Parameters
+
+- `server` (string, optional): Server name to filter resources by. Omit to list resources from all connected servers.
+
+## Examples
+
+### Example 1: List everything
+
+```
+ListMcpResources()
+```
+
+### Example 2: List one server's resources
+
+```
+ListMcpResources(server="github")
+```
+
+## Notes
+
+- This is the discovery step: feed interesting URIs into `ReadMcpResource` (single resource) or `ReadMcpResourceDir` (directory listings).
+- Servers connect and disconnect over the session lifetime; re-list if a server was just added.

package/concepts/en/Tool-ListPlugins.md

@@ -0,0 +1,35 @@
+# ListPlugins
+
+Lists the user's enabled claude.ai plugins, optionally filtered by keyword.
+
+## When to Use
+
+- You need to know which plugins are already enabled — for example, to confirm what was installed after a `SuggestPluginInstall` card.
+- The user asks what plugins they have.
+
+## Activation
+
+- Requires plugin registry access permission.
+- Availability depends on session type and feature rollout — disabled in HIPAA environments, always available in remote sessions.
+
+## Parameters
+
+- `keywords` (array of strings, optional): Filter the list — up to 8 items, each 1–64 characters. Omit to list everything.
+
+## Examples
+
+### Example 1: List enabled plugins
+
+```
+ListPlugins()
+```
+
+### Example 2: Filter by keyword
+
+```
+ListPlugins(keywords=["figma"])
+```
+
+## Notes
+
+- If the plugin catalog is unreachable (forbidden), the tool degrades to an empty list with a warning rather than failing.

package/concepts/en/Tool-ListSkills.md

@@ -0,0 +1,37 @@
+# ListSkills
+
+Lists the user's enabled claude.ai skills, optionally filtered by keyword.
+
+## When to Use
+
+- You need the authoritative list of skills currently enabled — before invoking one, or to confirm what a `SuggestSkills` card added.
+- The user asks which skills they have.
+
+## Activation
+
+- Requires plugin registry access permission.
+- Disabled in HIPAA environments.
+- Always available in remote sessions.
+
+## Parameters
+
+- `keywords` (array of strings, optional): Filter the list — up to 8 items, each 1–64 characters. Omit to list everything.
+
+## Examples
+
+### Example 1: List enabled skills
+
+```
+ListSkills()
+```
+
+### Example 2: Filter by keyword
+
+```
+ListSkills(keywords=["review"])
+```
+
+## Notes
+
+- If the catalog is unreachable (forbidden), the tool degrades to an empty list with a warning rather than failing.
+- This lists *enabled* skills; use `SuggestSkills` to surface skills the user could add.

package/concepts/en/Tool-Monitor.md

@@ -10,6 +10,13 @@ Start a background monitor that streams events from a long-running script. Each
 - Waiting for a specific condition across many iterations (e.g., a training step milestone or a queue draining)
 - **Not** for simple "wait until done" — use `Bash` with `run_in_background` for that; it emits one completion notification when the process exits
 
+## Activation
+
+- Off by default (server-side feature flag).
+- Unavailable on Amazon Bedrock, Google Cloud, and Microsoft Foundry.
+- Off when `DISABLE_TELEMETRY` or `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` is set.
+- The WebSocket source requires Claude Code 2.1.195+.
+
 ## Parameters
 
 - `command` (string, required): The shell command or script to run. Each line written to stdout becomes a separate notification event. The monitor ends when the process exits.

package/concepts/en/Tool-Projects.md

@@ -0,0 +1,46 @@
+# Projects
+
+Manages project documents in the user's Claude project knowledge base: read, search, write, and delete docs, or fetch project info.
+
+## When to Use
+
+- Persist a document (deliverable, notes, reference material) into the user's project so it survives the session.
+- Read or search existing project docs to ground the current task in prior context.
+- Upload a local file into the project without loading its contents into context.
+- Remove an outdated project doc.
+
+## Parameters
+
+- `method` (string, required): One of `project_info`, `project_read`, `project_search`, `project_write`, `project_delete`.
+- `path` (string, optional): For `project_read`/`project_write`/`project_delete`: the doc path. For `project_write`: an existing path is replaced in place; a new bare filename (no "/") is namespaced to `claude/<name>`.
+- `content` (string, optional): For `project_write`: inline doc text. Mutually exclusive with `local_path`.
+- `local_path` (string, optional): For `project_write`: a file inside the working directory to upload — contents never enter your context. Mutually exclusive with `content`.
+- `present_to_user` (boolean, optional): For `project_write`: mark this doc as the deliverable the user needs to see. Defaults to false; leave unset for routine saves and bulk writes.
+- `query` (string, optional): For `project_search`: knowledge-base query.
+- `n` (number, optional): For `project_search`: number of hits (default 5).
+
+## Examples
+
+### Example 1: Write the deliverable into the project
+
+```
+Projects(
+  method="project_write",
+  path="claude/migration-plan.md",
+  local_path="./migration-plan.md",
+  present_to_user=true
+)
+```
+
+Uploads the local file without pulling its content into context, and flags it as the user's deliverable.
+
+### Example 2: Search the knowledge base
+
+```
+Projects(method="project_search", query="authentication refresh tokens", n=5)
+```
+
+## Notes
+
+- `content` is for text you compose inline; `local_path` is for anything already on disk — never mix the two.
+- Use `present_to_user=true` sparingly: only for the one doc the user asked for or must act on.

package/concepts/en/Tool-ProposeGoal.md

@@ -0,0 +1,43 @@
+# ProposeGoal
+
+Proposes a verifiable completion goal for the session. The goal is shown to the user in an approval dialog (by default) and, once set, guides the rest of the conversation toward a checkable outcome.
+
+## When to Use
+
+- The session has a concrete end state that an evaluator could verify from the conversation (e.g. "all tests in test/auth pass").
+- You want the user's explicit sign-off on what "done" means before doing substantial work.
+- The user's own words already stated the outcome and you want it recorded as the session goal.
+
+## Activation
+
+- Off by default (server-side feature flag).
+- Excluded from interactive and background sessions.
+- Turned off by the `modelProposedGoals: "disabled"` settings key.
+
+## Parameters
+
+- `condition` (string, required): The completion condition, written so a separate evaluator can verify it from the conversation (e.g. "all tests in test/auth pass (bun test exits 0)"). At most 500 characters — the user must be able to read the whole condition in the approval dialog.
+- `ask_user` (boolean, optional): Whether to ask the user for approval before the goal is set. Defaults to true (an approval dialog is shown). Set false ONLY when the user's own words in this conversation stated this outcome as what they want; the goal is then set directly with a visible notice, and the user can clear it with `/goal clear`.
+
+## Examples
+
+### Example 1: Propose a test-backed goal
+
+```
+ProposeGoal(condition="npm run test exits 0 with the new catalog cases included")
+```
+
+The user sees the condition in an approval dialog and can accept, edit, or reject it.
+
+### Example 2: Adopt the user's stated outcome directly
+
+```
+ProposeGoal(condition="the login form validates email format and shows an inline error", ask_user=false)
+```
+
+Only valid because the user explicitly stated that outcome earlier in the conversation.
+
+## Notes
+
+- Keep `condition` short and objectively checkable — vague goals ("make it better") defeat the purpose.
+- `ask_user=false` is strictly limited to outcomes the user themselves stated; anything else must go through the approval dialog.

package/concepts/en/Tool-PushNotification.md

@@ -14,6 +14,12 @@ Sends a desktop notification from the current Claude Code session. If Remote Con
 
 Do not send a notification for routine progress updates mid-task, or to confirm you have answered a question the user clearly just asked and is still watching. Do not notify when a short task completes — if the user submitted it and is waiting, a notification adds no value and erodes trust for future ones. Err strongly toward not sending one.
 
+## Activation
+
+- Off by default (server-side feature flag).
+- Delivery runs through Anthropic-hosted infrastructure — not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud, or Microsoft Foundry.
+- Phone push additionally requires a connected Remote Control client.
+
 ## Parameters
 
 - `message` (string, required): the notification body. Keep under 200 characters; mobile operating systems truncate longer strings. Lead with what the user would act on: "build failed: 2 auth tests" is more useful than "task complete."

package/concepts/en/Tool-REPL.md

@@ -0,0 +1,47 @@
+# REPL
+
+Executes JavaScript in a persistent Node.js vm context inside the session. Top-level `await` is supported, and variables/functions defined in one call remain available in later calls.
+
+## When to Use
+
+- Quick computation, data transformation, or JSON wrangling that is easier in code than in shell one-liners.
+- Multi-step scripting where intermediate state should persist between calls (counters, accumulated results).
+- Probing an API or library behavior interactively before writing it into a file.
+
+## Activation
+
+- Off by default — set `CLAUDE_CODE_REPL=true` to enable it.
+- In terminal (`cli`) and claude.ai (`remote`) sessions, a server-side feature flag may also enable it.
+- When off, REPL is hidden from the model's tool list. When on, `Read`, `Glob`, `Grep`, `Bash`, `PowerShell`, and `NotebookEdit` are replaced by REPL shorthands.
+
+## Parameters
+
+- `code` (string, required): JavaScript code to execute. Supports top-level await. State persists across calls.
+- `description` (string, optional): Clear, concise description of what this script does in active voice (5–10 words), e.g. "Trace upgrade message to its GrowthBook flag".
+- `timeout` (number, optional): Timeout in milliseconds. Defaults to 30000; maximum 600000.
+
+## Examples
+
+### Example 1: Compute and reuse state
+
+```
+REPL(code="const counts = new Map(); ['a','b','a'].forEach(k => counts.set(k, (counts.get(k)||0)+1)); counts.get('a')")
+```
+
+Returns `2`; `counts` stays defined for subsequent REPL calls in the same session.
+
+### Example 2: Top-level await with a longer timeout
+
+```
+REPL(
+  code="const res = await fetch('https://example.com/api'); await res.json()",
+  description="Fetch example API and parse JSON",
+  timeout=60000
+)
+```
+
+## Notes
+
+- State is per-session: restarting the session clears all definitions.
+- This is a JavaScript (Node) environment — use Bash for shell commands, filesystem-heavy work, or non-JS runtimes.
+- Long-running code should set an explicit `timeout`; the default 30s kills anything slower.

package/concepts/en/Tool-ReadMcpResource.md

@@ -0,0 +1,32 @@
+# ReadMcpResource
+
+Reads a single resource exposed by a connected MCP (Model Context Protocol) server, addressed by its URI.
+
+## When to Use
+
+- An MCP server advertises a resource (file, record, document) whose content you need in context.
+- You have a concrete resource URI — from `ListMcpResources`, from the server's documentation, or from a previous tool result.
+
+## Activation
+
+- Always enabled, but not exposed to the model's tool list — intended for thin-client / sidecar use.
+
+## Parameters
+
+- `server` (string, required): The MCP server name.
+- `uri` (string, required): The resource URI to read.
+
+## Examples
+
+### Example 1: Read a server resource by URI
+
+```
+ReadMcpResource(server="github", uri="file:///repo/docs/architecture.md")
+```
+
+Returns the resource content as provided by the `github` MCP server.
+
+## Notes
+
+- Use `ListMcpResources` first if you don't know which resources a server exposes; use `ReadMcpResourceDir` for directory-style listings.
+- The URI scheme is server-specific (`file://`, `https://`, custom schemes) — check what the target server advertises.

package/concepts/en/Tool-ReadMcpResourceDir.md

@@ -0,0 +1,32 @@
+# ReadMcpResourceDir
+
+Lists the entries of a directory-style resource exposed by a connected MCP server, addressed by its URI.
+
+## When to Use
+
+- An MCP server organizes resources hierarchically and you need to enumerate one level of that hierarchy.
+- You want to browse before reading individual resources with `ReadMcpResource`.
+
+## Activation
+
+- Always enabled, but not exposed to the model's tool list — intended for thin-client / sidecar use.
+
+## Parameters
+
+- `server` (string, required): The MCP server name.
+- `uri` (string, required): The directory resource URI to list.
+
+## Examples
+
+### Example 1: List a resource directory
+
+```
+ReadMcpResourceDir(server="filesystem", uri="file:///project/src/")
+```
+
+Returns the child entries the server exposes under that directory URI.
+
+## Notes
+
+- Only servers that model their resources as directories support this; flat servers will return an error or an empty listing — fall back to `ListMcpResources`.
+- Combine with `ReadMcpResource` to drill into the entries that look relevant.

package/concepts/en/Tool-ReadNotifications.md

@@ -0,0 +1,27 @@
+# ReadNotifications
+
+Reads notifications queued for the assistant in the current session — GitHub activity on subscribed PRs (`github_webhook`), scheduled-trigger fires (`trigger_fire`), and messages arriving from other Claude sessions (`mcp_send_message`).
+
+## When to Use
+
+- You were notified that something happened — a subscribed PR updated, a scheduled trigger fired, another session messaged you — and need the actual payload.
+- Draining a backlog: large batches are returned in parts, so keep calling until the result reports 0 `remaining`.
+
+## Parameters
+
+This tool takes no parameters.
+
+## Examples
+
+### Example 1: Drain pending notifications
+
+```
+ReadNotifications()
+```
+
+Returns queued notifications oldest first. The result includes a `remaining` count of notifications still queued after this drain — call the tool again to read them.
+
+## Notes
+
+- Drains are size-budgeted: a follow-up call returns the rest of the SAME queue (plus anything newly arrived), not only new arrivals. Loop until `remaining` is 0.
+- Notifications originate from GitHub webhooks on subscribed PRs, scheduled triggers, and messages from other Claude sessions; there is no filtering parameter in the current version.

package/concepts/en/Tool-RemoteTrigger.md

@@ -10,6 +10,13 @@ Call the claude.ai remote-trigger API to manage scheduled and on-demand trigger
 - Listing or auditing all current triggers to review their configuration and status
 - Updating trigger settings such as schedule, payload, or description without recreating the trigger
 
+## Activation
+
+- Requires a claude.ai Pro, Max, Team, or Enterprise plan.
+- Not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud, or Microsoft Foundry.
+- Requires server-side feature flags and the `allow_remote_sessions` / `allow_routines` policy settings.
+- Not for remote sessions themselves.
+
 ## Parameters
 
 - `action` (string, required): the operation to perform — one of `list`, `get`, `create`, `update`, or `run`

package/concepts/en/Tool-ScheduleWakeup.md

@@ -10,6 +10,11 @@ Schedule when to resume work in `/loop` dynamic mode. The tool lets Claude self-
 - Running an autonomous loop with no user prompt — pass the literal sentinel `<<autonomous-loop-dynamic>>` as `prompt`
 - Polling a process that is about to change state soon (stay cache-warm with a short delay)
 
+## Activation
+
+- Not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud Agent Platform, or Microsoft Foundry.
+- Also off when feature-flag fetching is disabled (telemetry/traffic env vars).
+
 ## Parameters
 
 - `delaySeconds` (number, required): Seconds from now to resume. The runtime clamps the value to `[60, 3600]`, so you do not need to clamp it yourself.

package/concepts/en/Tool-SearchMcpRegistry.md

@@ -0,0 +1,31 @@
+# SearchMcpRegistry
+
+Searches the MCP connector registry by keyword to discover connectors that might help complete the task.
+
+## When to Use
+
+- The task would benefit from an external service (a database, an issue tracker, a SaaS API) and you want to check whether an MCP connector exists for it.
+- The user names a product and asks to connect it — search the registry for a matching connector.
+
+## Activation
+
+- Only available in remote (claude.ai) sessions on the first-party API.
+
+## Parameters
+
+- `keywords` (array of strings, required): Keyword phrases describing the user's intent or a named product. 1–8 items, each 1–64 characters.
+
+## Examples
+
+### Example 1: Find a connector for a named product
+
+```
+SearchMcpRegistry(keywords=["linear", "issue tracker"])
+```
+
+Returns registry entries whose connectors match the keywords. Resolve full connector details with `SuggestConnectors`.
+
+## Notes
+
+- Read-only and concurrency-safe; results are capped in size.
+- Searching installs nothing — it is purely discovery.

package/concepts/en/Tool-SendFeedback.md

@@ -0,0 +1,38 @@
+# SendFeedback
+
+Sends structured feedback about Claude Code to Anthropic — bug reports, feature ideas, or missing capabilities — without leaving the session.
+
+## When to Use
+
+- The user asks to report a bug or send feedback about Claude Code itself.
+- You hit a clear product defect (broken command, wrong behavior, crash) worth reporting.
+- The user describes a feature they wish existed (an idea or missing capability).
+
+## Parameters
+
+- `type` (string, required): One of `bug`, `idea`, `missing_capability`.
+- `title` (string, required): Short, specific one-line summary of the issue.
+- `details` (string, required): Labeled bullets, in order: **What happened:** (observed vs. expected, exact error text if short); **What the user said:** (quoted, or "User didn't comment; observed by the model."); **Repro:** (minimal steps); **Evidence:** (request IDs, timestamps, paths, versions — omit if none); optionally a final **Cause:** only if verified in-session. One to three lines per bullet; no narrative paragraphs, no speculation, no secrets.
+- `area` (string, optional): Short tag naming the part of Claude Code this is about (e.g. "hooks config", "/help", "file editing"). Leave blank if unclear.
+- `failure_mode` (string, optional): For model-behavior reports, the closest failure mode (e.g. `instruction_following`, `repetition_and_looping`, `context_and_memory`, `stopping_short`, or `other`). Omit only when the report is a pure product/tool bug.
+- `task_category` (string, optional): What the session was doing when the issue occurred: `code_edit`, `debug`, `explain`, `plan`, `shell`, `search`, `review`, or `other`.
+
+## Examples
+
+### Example 1: Report a product bug
+
+```
+SendFeedback(
+  type="bug",
+  title="/export truncates the last message",
+  details="**What happened:** exported transcript is missing the final assistant message.\n**What the user said:** \"the last reply never shows up in the file\".\n**Repro:** run /export after any multi-turn session.\n**Evidence:** v2.1.233, macOS.",
+  area="/export",
+  task_category="other"
+)
+```
+
+## Notes
+
+- Never include secrets, tokens, or private user data in `details`.
+- Quote the user's words when available; otherwise state that the model observed the issue.
+- Keep the report factual — speculation about root cause belongs in `**Cause:**` only when verified in-session.

package/concepts/en/Tool-SendFile.md

@@ -0,0 +1,36 @@
+# SendFile
+
+Sends one or more files to another Claude Code session — a peer listed by `ListAgents`, or an explicit session address.
+
+## When to Use
+
+- A peer session needs a file from your working directory (a report, a patch, a fixture) to continue its own task.
+- You are coordinating work across sessions and want to hand off artifacts, not just text (use `SendMessage` for text).
+
+## Activation
+
+- Cross-session file transfer must be available in the session; when it is not, validation fails with "Cross-session file transfer is not available in this session."
+- Gated by the same cross-session messaging conditions as `ListAgents` (server-side feature flags, off by default).
+
+## Parameters
+
+- `to` (string, required): Recipient — a peer session name from `ListAgents`, or an explicit `uds:<socket>` / `bridge:<session id>` address.
+- `files` (array of strings, required): File paths (absolute or relative to cwd) to send. Always pass an array, even for a single file. 1–16 files, at most 30 MiB each.
+- `message` (string, optional): Short message delivered alongside the files.
+
+## Examples
+
+### Example 1: Send a report to a peer session
+
+```
+SendFile(
+  to="teammate-a",
+  files=["./dist/report.html"],
+  message="The analysis you asked for"
+)
+```
+
+## Notes
+
+- Transfers to remote machines may require additional approval.
+- Reading the file contents is part of the send — denied if file reads are disabled by permission rules.

package/concepts/en/Tool-SendMessage.md

@@ -10,6 +10,11 @@ Delivers a message from one team member to another within an active team, or bro
 - Replying to a protocol prompt such as a shutdown request or a plan-approval request from the team leader.
 - Closing the loop at the end of a delegated task so the leader can mark the item complete.
 
+## Activation
+
+- Gated by the same cross-session messaging conditions as `ListAgents` (server-side feature flags, off by default).
+- Teammates additionally require experimental agent teams to be enabled.
+
 ## Parameters
 
 - `to` (string, required): The target teammate's `name` as registered in the team, or `*` to broadcast to all teammates at once.