Update Claude Code docs - 2025-08-27 | Updated: common-workflows.md,mcp.md settings.md,slash-commands.md

Author: github-actions[bot]

docs/common-workflows.md

@@ -523,7 +523,7 @@ Suppose you're working on complex architectural decisions, challenging bugs, or
     ```
 
     ```
-    > think harder about edge cases we should handle 
+    > keep thinking about edge cases we should handle 
     ```
   </Step>
 </Steps>
@@ -542,7 +542,7 @@ Suppose you're working on complex architectural decisions, challenging bugs, or
   The way you prompt for thinking results in varying levels of thinking depth:
 
   * "think" triggers basic extended thinking
-  * intensifying phrases such as "think more", "think a lot", "think harder", or "think longer" triggers deeper thinking
+  * intensifying phrases such as "keep thinking", "think more", "think a lot", or "think longer" triggers deeper thinking
 
   For more extended thinking prompting tips, see [Extended thinking tips](/en/docs/build-with-claude/prompt-engineering/extended-thinking-tips).
 </Tip>

docs/docs_manifest.json

@@ -21,8 +21,8 @@
     "common-workflows.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/common-workflows",
       "original_md_url": "https://docs.anthropic.com/en/docs/claude-code/common-workflows.md",
-      "hash": "ac1c508033364228c68a452e5b4a794af8bc6982fdd9c495f48803c93b90f878",
-      "last_updated": "2025-08-26T21:03:54.125538"
+      "hash": "4004b1fe2440bbebb2d8c041f944d4a79a7bb8c61bd3bd355596340a1cf3f723",
+      "last_updated": "2025-08-27T18:05:39.042943"
     },
     "corporate-proxy.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/corporate-proxy",
@@ -105,8 +105,8 @@
     "mcp.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/mcp",
       "original_md_url": "https://docs.anthropic.com/en/docs/claude-code/mcp.md",
-      "hash": "3110c23f7a50c398bd6fe914b71b45f4ae5672d68a42e9fa4f5f089c47e3b752",
-      "last_updated": "2025-08-22T21:03:59.291460"
+      "hash": "aedc4db3406451dc397d4b92c5903d343cfe4582d2f8d0782477a482cbd84344",
+      "last_updated": "2025-08-27T18:05:46.641773"
     },
     "memory.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/memory",
@@ -171,8 +171,8 @@
     "settings.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/settings",
       "original_md_url": "https://docs.anthropic.com/en/docs/claude-code/settings.md",
-      "hash": "c4522c192d6ace37dd5c3fe1c11adc30e6aad754bad7b8ff6fc6d76681a47761",
-      "last_updated": "2025-08-26T18:06:01.457544"
+      "hash": "847612a6dbf2cff6913f17f2d33b8e7769a45a90c82a45872a7ab679d407220b",
+      "last_updated": "2025-08-27T18:05:52.647697"
     },
     "setup.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/setup",
@@ -183,8 +183,8 @@
     "slash-commands.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/slash-commands",
       "original_md_url": "https://docs.anthropic.com/en/docs/claude-code/slash-commands.md",
-      "hash": "d196c5cf49d7ae86357c2ab23ec90a4f15eafadea28dacf4ade9ff0a09f34234",
-      "last_updated": "2025-08-18T18:02:23.695887"
+      "hash": "a92657563011b0d9cf1b59de5c493e3d3cb5f4f1f5aa31ae3a3acf3bd97d7750",
+      "last_updated": "2025-08-27T18:05:53.748782"
     },
     "statusline.md": {
       "original_url": "https://docs.anthropic.com/en/docs/claude-code/statusline",
@@ -225,8 +225,8 @@
     }
   },
   "fetch_metadata": {
-    "last_fetch_completed": "2025-08-27T15:05:13.114474",
-    "fetch_duration_seconds": 19.743665,
+    "last_fetch_completed": "2025-08-27T18:05:56.559982",
+    "fetch_duration_seconds": 19.947657,
     "total_pages_discovered": 36,
     "pages_fetched_successfully": 37,
     "pages_failed": 0,
@@ -236,7 +236,7 @@
     "total_files": 37,
     "fetch_tool_version": "3.0"
   },
-  "last_updated": "2025-08-27T15:05:13.114506",
+  "last_updated": "2025-08-27T18:05:56.560012",
   "base_url": "https://raw.githubusercontent.com/mnestorov/cc-docs-mirror/main/docs/",
   "github_repository": "mnestorov/cc-docs-mirror",
   "github_ref": "main",

docs/mcp.md

@@ -714,6 +714,7 @@ claude mcp remove github
     * `user`: Available to you across all projects (was called `global` in older versions)
   * Set environment variables with `--env` flags (e.g., `--env KEY=value`)
   * Configure MCP server startup timeout using the MCP\_TIMEOUT environment variable (e.g., `MCP_TIMEOUT=10000 claude` sets a 10-second timeout)
+  * Claude Code will display a warning when MCP tool output exceeds 10,000 tokens. To increase this limit, set the `MAX_MCP_OUTPUT_TOKENS` environment variable (e.g., `MAX_MCP_OUTPUT_TOKENS=50000`)
   * Use `/mcp` to authenticate with remote servers that require OAuth 2.0 authentication
 </Tip>
 
@@ -1019,6 +1020,32 @@ You can use this in Claude Desktop by adding this configuration to claude\_deskt
   * Note that this MCP server is simply exposing Claude Code's tools to your MCP client, so your own client is responsible for implementing user confirmation for individual tool calls.
 </Tip>
 
+## MCP output limits and warnings
+
+When MCP tools produce large outputs, Claude Code helps manage the token usage to prevent overwhelming your conversation context:
+
+* **Output warning threshold**: Claude Code displays a warning when any MCP tool output exceeds 10,000 tokens
+* **Configurable limit**: You can adjust the maximum allowed MCP output tokens using the `MAX_MCP_OUTPUT_TOKENS` environment variable
+* **Default limit**: The default maximum is 25,000 tokens
+
+To increase the limit for tools that produce large outputs:
+
+```bash
+# Set a higher limit for MCP tool outputs
+export MAX_MCP_OUTPUT_TOKENS=50000
+claude
+```
+
+This is particularly useful when working with MCP servers that:
+
+* Query large datasets or databases
+* Generate detailed reports or documentation
+* Process extensive log files or debugging information
+
+<Warning>
+  If you frequently encounter output warnings with specific MCP servers, consider increasing the limit or configuring the server to paginate or filter its responses.
+</Warning>
+
 ## Use MCP resources
 
 MCP servers can expose resources that you can reference using @ mentions, similar to how you reference files.

docs/settings.md

@@ -183,7 +183,7 @@ Claude Code supports the following environment variables to control its behavior
 | `MAX_THINKING_TOKENS`                      | Force a thinking for the model budget                                                                                                                              |
 | `MCP_TIMEOUT`                              | Timeout in milliseconds for MCP server startup                                                                                                                     |
 | `MCP_TOOL_TIMEOUT`                         | Timeout in milliseconds for MCP tool execution                                                                                                                     |
-| `MAX_MCP_OUTPUT_TOKENS`                    | Maximum number of tokens allowed in MCP tool responses (default: 25000)                                                                                            |
+| `MAX_MCP_OUTPUT_TOKENS`                    | Maximum number of tokens allowed in MCP tool responses. Claude Code displays a warning when output exceeds 10,000 tokens (default: 25000)                          |
 | `USE_BUILTIN_RIPGREP`                      | Set to `0` to use system-installed `rg` intead of `rg` included with Claude Code                                                                                   |
 | `VERTEX_REGION_CLAUDE_3_5_HAIKU`           | Override region for Claude 3.5 Haiku when using Vertex AI                                                                                                          |
 | `VERTEX_REGION_CLAUDE_3_5_SONNET`          | Override region for Claude Sonnet 3.5 when using Vertex AI                                                                                                         |

docs/slash-commands.md

@@ -88,18 +88,40 @@ Meanwhile, a file at `~/.claude/commands/component.md` creates the command `/com
 
 #### Arguments
 
-Pass dynamic values to commands using the `$ARGUMENTS` placeholder.
+Pass dynamic values to commands using argument placeholders:
 
-For example:
+##### All arguments with `$ARGUMENTS`
+
+The `$ARGUMENTS` placeholder captures all arguments passed to the command:
 
 ```bash
 # Command definition
 echo 'Fix issue #$ARGUMENTS following our coding standards' > .claude/commands/fix-issue.md
 
 # Usage
-> /fix-issue 123
+> /fix-issue 123 high-priority
+# $ARGUMENTS becomes: "123 high-priority"
 ```
 
+##### Individual arguments with `$1`, `$2`, etc.
+
+Access specific arguments individually using positional parameters (similar to shell scripts):
+
+```bash
+# Command definition  
+echo 'Review PR #$1 with priority $2 and assign to $3' > .claude/commands/review-pr.md
+
+# Usage
+> /review-pr 456 high alice
+# $1 becomes "456", $2 becomes "high", $3 becomes "alice"
+```
+
+Use positional arguments when you need to:
+
+* Access arguments individually in different parts of your command
+* Provide defaults for missing arguments
+* Build more structured commands with specific parameter roles
+
 #### Bash command execution
 
 Execute bash commands before the slash command runs using the `!` prefix. The output is included in the command context. You *must* include `allowed-tools` with the `Bash` tool, but you can choose the specific bash commands to allow.
@@ -165,7 +187,19 @@ description: Create a git commit
 model: claude-3-5-haiku-20241022
 ---
 
-An example command
+Create a git commit with message: $ARGUMENTS
+```
+
+Example using positional arguments:
+
+```markdown
+---
+argument-hint: [pr-number] [priority] [assignee]
+description: Review pull request
+---
+
+Review PR #$1 with priority $2 and assign to $3.
+Focus on security, performance, and code style.
 ```
 
 ## MCP slash commands
@@ -219,8 +253,19 @@ Use the `/mcp` command to:
 * Clear authentication tokens
 * View available tools and prompts from each server
 
+### MCP permissions and wildcards
+
+When configuring [permissions for MCP tools](/en/docs/claude-code/iam#tool-specific-permission-rules), note that **wildcards are not supported**:
+
+* ✅ **Correct**: `mcp__github` (approves ALL tools from the github server)
+* ✅ **Correct**: `mcp__github__get_issue` (approves specific tool)
+* ❌ **Incorrect**: `mcp__github__*` (wildcards not supported)
+
+To approve all tools from an MCP server, use just the server name: `mcp__servername`. To approve specific tools only, list each tool individually.
+
 ## See also
 
+* [Identity and Access Management](/en/docs/claude-code/iam) - Complete guide to permissions, including MCP tool permissions
 * [Interactive mode](/en/docs/claude-code/interactive-mode) - Shortcuts, input modes, and interactive features
 * [CLI reference](/en/docs/claude-code/cli-reference) - Command-line flags and options
 * [Settings](/en/docs/claude-code/settings) - Configuration options