docs: add Deep Agents Code diagnostic commands

src/oss/deepagents/code/cli-reference.mdx

@@ -233,14 +233,106 @@ Valid names are `ls`, `read_file`, `write_file`, `edit_file`, `delete`, `glob`,
     ```
 </Note>
 
-Run `/tools` in a session to inspect the active tool set. From the shell, place tool-shaping flags before the subcommand:
+Run [`/tools`](#diagnose-and-audit-a-session) in a session to inspect the active tool set. From the shell, place tool-shaping flags before the subcommand:
 
 ```bash
 dcode tools list
 dcode --allow-fs-tools ls,read_file tools list
 dcode --allow-fs-tools ls,read_file tools list --json
 ```
 
+## Diagnose and audit a session
+
+Deep Agents Code exposes read-only slash commands for inspecting what a session loads and spends: `/tools` lists the active tool set, `/context-doctor` audits the context injected before the conversation starts, and `/cost` reports the thread's estimated spend. Use them to confirm that a tool-shaping flag took effect or to find the source of unexpected context growth.
+
+### List available tools
+
+Run `/tools` in a session to list the tools the current agent can call, grouped into built-in tools and tools from each MCP server:
+
+```text
+/tools
+```
+
+```text
+**7 tools available**
+
+### Built-in
+
+| Tool | Description |
+|---|---|
+| read_file | Read a file from the filesystem |
+| write_file | Write content to a file |
+| execute | Run a shell command |
+| web_search | Search the web |
+| task | Launch a subagent |
+
+### github
+
+- create_issue
+- search_repositories
+
+MCP tool descriptions are available in /mcp.
+
+### Unavailable MCP servers
+
+| Server | Status |
+|---|---|
+| slack | needs login |
+```
+
+Unavailable MCP servers appear in a separate table. Run `/reload` after changing MCP configuration, then use `/tools` to verify the active tool set. For the non-interactive equivalent, see [`dcode tools list`](#cli-commands).
+
+### Audit injected context
+
+Run `/context-doctor` in a session to audit what the session injects into every model request and its estimated token cost. The report breaks the injected context into the base system prompt, `AGENTS.md` memory files, the skills index, built-in tool schemas, and each MCP server's tool schemas, then totals what the agent carries before the conversation starts:
+
+```text
+/context-doctor
+```
+
+```text
+Fresh-session context audit (estimated tokens)
+
+System prompt (base)                      ~6
+AGENTS.md memory (1 files)            ~1,286
+Skills index (1 loaded)                 ~477  largest: code-review ~15
+Built-in tool schemas (1 tools)          ~13  sent with every request
+MCP: docs (1 tool)                       ~31
+MCP: broken                               ~0  connection failed
+TOTAL injected before conversation  ~     1,813
+Conversation history             ~     4,200
+Provider-reported context              9,000
+Unattributed / estimation delta       +2,987
+
+Approximate: section counts use about four characters per token.
+Trim skills or disable an MCP server, then run /context-doctor again.
+```
+
+A large unattributed delta or injected total points to context you may want to trim. After changing skills or MCP configuration, run `/context-doctor` again to confirm.
+
+### Track thread cost
+
+Run `/cost` in a session to show the thread's estimated cost in USD:
+
+```text
+/cost
+```
+
+```text
+Estimated thread cost: $1.03
+
+By type since this thread was loaded:
+- Assistant: $0.87
+- Subagents: $0.16
+
+By model since this thread was loaded:
+- anthropic:claude-sonnet-4-5: $1.03
+```
+
+The total includes model calls from the assistant, subagents, offloading, Auto classification, and rubric grading. It persists when you resume or switch threads. Estimates use the [genai-prices](https://github.com/pydantic/genai-prices) catalog; requests without pricing are excluded.
+
+Use `/tokens` for the token counts behind the estimate. For uncovered models, [add a custom pricing override](/oss/deepagents/code/configuration#custom-pricing-overrides).
+
 ## Startup commands and initial prompts
 
 Use `-m`/`--message` to auto-submit an initial prompt when an interactive session starts. Combine with `--startup-cmd` to run a shell command first:
@@ -389,7 +481,7 @@ Pair `dcode doctor` with `dcode config show` when you need both a high-level hea
 | `dcode agents reset --agent NAME` | Clear agent memory and reset to default. Supports `--dry-run` |
 | `dcode agents reset --agent NAME --target SOURCE` | Copy memory from another agent |
 | `dcode update`                  | Check for and install Deep Agents Code updates |
-| `dcode doctor`                  | Run diagnostics without launching a session |
+| `dcode doctor`                  | Run diagnostics without launching a session. See [Run diagnostics](#run-diagnostics-dcode-doctor) |
 | `dcode skills list [--project]`           | List all skills (alias: `ls`) |
 | `dcode skills create NAME [--project]`    | Create a new skill with template `SKILL.md`. Idempotent—re-creating an existing skill prints an informational message instead of an error |
 | `dcode skills info NAME [--project]`      | Show detailed information about a skill |
@@ -418,3 +510,4 @@ Destructive commands (`agents reset`, `skills delete`, `threads delete`) support
 - [Configuration](/oss/deepagents/code/configuration)
 - [Config file](/oss/deepagents/code/config-file)
 - [Provider credentials](/oss/deepagents/code/credentials)
+- [MCP tools](/oss/deepagents/code/mcp-tools)

src/oss/deepagents/code/configuration.mdx

@@ -290,6 +290,29 @@ Deep Agents Code refreshes its model pricing catalog from upstream hourly in the
     </Tab>
 </Tabs>
 
+### Custom pricing overrides
+
+For models that the catalog does not cover, add rates to `~/.deepagents/prices.json`. The file uses the [genai-prices](https://github.com/pydantic/genai-prices) provider-array schema. For example:
+
+```json
+[
+  {
+    "id": "my-provider",
+    "name": "My provider",
+    "api_pattern": "gateway\\.example\\.com",
+    "models": [
+      {
+        "id": "my-model",
+        "match": { "equals": "my-model" },
+        "prices": { "input_mtok": 2.5, "output_mtok": 10.0 }
+      }
+    ]
+  }
+]
+```
+
+Rates are in USD per million tokens. Restart Deep Agents Code after editing the file. Custom rates apply only when the genai-prices catalog does not include the model.
+
 To suppress automatic update checks entirely:
 
 <Tabs>

src/oss/deepagents/code/quickstart.mdx

@@ -65,9 +65,12 @@ The agent uses its built-in tools, skills, and memory to help you with tasks.
         - `/skill-creator [task]`: Guide for creating effective agent skills.
         - `/offload` (alias `/compact`) - Free up context window space by offloading messages to storage with a summary placeholder. The agent can retrieve the full history from the offloaded file if needed.
         - `/context`: Open a color-coded context-window usage report with model capacity, usage categories, and remaining space.
+        - `/context-doctor`: Audit the context injected into the session and its estimated token cost. See [Audit injected context](/oss/deepagents/code/cli-reference#audit-injected-context).
+        - `/tools`: List the built-in and MCP tools available to the current agent. See [List available tools](/oss/deepagents/code/cli-reference#list-available-tools).
+        - `/cost`: Show the thread's estimated cost. See [Track thread cost](/oss/deepagents/code/cli-reference#track-thread-cost).
         - `/tokens`: Display current context window token usage breakdown.
-        - `/clear`: Clear conversation history and start a new thread.
-        - `/force-clear`: Stop active work, clear the chat, and start a new thread.
+        - `/clear`: Start a fresh thread.
+        - `/force-clear`: Recover a stuck session with a fresh thread.
         - `/copy`: Copy the latest assistant message to the clipboard.
         - `/prompts`: Search, preview, copy, and reuse previously submitted prompts.
         - `/threads`: Browse and resume previous conversation threads.
@@ -111,9 +114,10 @@ The agent uses its built-in tools, skills, and memory to help you with tasks.
         | `Enter` | Submit prompt |
         | `Shift+Enter`, `Ctrl+J`, `Alt+Enter`, or `Ctrl+Enter` | Insert newline |
         | `@filename` | Auto-complete files and inject content |
-        | `Shift+Tab` or `Ctrl+T` | Toggle between Manual and Auto [approval mode](/oss/deepagents/code/approval-modes) |
-        | `Ctrl+X` | Open prompt in external editor |
-        | `Ctrl+N` | Review pending notifications |
+        | `Shift+Tab` | Cycle [approval modes](/oss/deepagents/code/approval-modes) |
+        | `Ctrl+G` | Open prompt in external editor |
+        | `Ctrl+T` | Expand or collapse the subagent panel when one is present |
+        | `Ctrl+N` | Review pending notifications when the panel is open |
         | `Ctrl+O` | Expand/collapse the most recent tool output |
         | `Escape` | Interrupt current operation |
         | `Ctrl+C` | Interrupt or quit |
@@ -159,9 +163,11 @@ Run `/context` to open a color-coded report of the current model's context-windo
 
 Provider-reported totals remain distinct from local conversation estimates. When a provider total is unavailable, the report labels the conversation count as an estimate and marks the total usage as unavailable. Use `/tokens` when you want a text summary in the conversation transcript instead.
 
+When usage grows faster than expected, run `/context-doctor` to attribute tokens to each injected component: the base system prompt, memory files, the skills index, built-in tool schemas, and MCP tool schemas. To confirm which tools the agent can currently call, run `/tools`. For the thread's running cost estimate, run `/cost`; the same figure appears in the status bar. See [Diagnose and audit a session](/oss/deepagents/code/cli-reference#diagnose-and-audit-a-session).
+
 ### External editor
 
-Press `Ctrl+X` or type `/editor` to compose prompts in an external editor. Deep Agents Code checks `$VISUAL`, then `$EDITOR`, then falls back to `vi` (macOS/Linux) or `notepad` (Windows). GUI editors (VS Code, Cursor, Zed, etc.) automatically receive a `--wait` flag so Deep Agents Code blocks until you close the file.
+Press `Ctrl+G` or type `/editor` to compose prompts in an external editor. Deep Agents Code checks `$VISUAL`, then `$EDITOR`, then falls back to `vi` (macOS/Linux) or `notepad` (Windows). GUI editors (VS Code, Cursor, Zed, etc.) automatically receive a `--wait` flag so Deep Agents Code blocks until you close the file.
 
 ```bash
 # Set in your shell profile (~/.zshrc, ~/.bashrc, etc.)