Skip to content

Commit e1fbae3

Browse files
claude-yolo[bot]claude
authored and
claude-yolo[bot]
committed
docs: Claude Code v1.0.110 with GitLab CI/CD integration
Major additions: - New GitLab CI/CD integration documentation with enterprise provider support - WezTerm support in /terminal-setup command - MCP OAuth token proactive refresh - Background Bash reliability improvements - New IDE security guidance for auto-edit mode - SDK partial message streaming support 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
1 parent 1a7f341 commit e1fbae3

11 files changed

Lines changed: 708 additions & 141 deletions

File tree

‎content/.metadata.json‎

Lines changed: 94 additions & 76 deletions
Large diffs are not rendered by default.

‎content/anthropic-blog/engineering/claude-code-best-practices.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@ Claude Code is intentionally low-level and unopinionated, providing close to raw
99

1010
This post outlines general patterns that have proven effective, both for Anthropic's internal teams and for external engineers using Claude Code across various codebases, languages, and environments. Nothing in this list is set in stone nor universally applicable; consider these suggestions as starting points. We encourage you to experiment and find what works best for you!
1111

12-
_Looking for more detailed information? Our comprehensive documentation at [claude.ai/code](https://claude.ai/redirect/website.v1.9c12b785-b9e6-48bf-b1ff-0b48423aca71/code)_ _covers all the features mentioned in this post and provides additional examples, implementation details, and advanced techniques._
12+
_Looking for more detailed information? Our comprehensive documentation at [claude.ai/code](https://claude.ai/redirect/website.v1.bc583822-b27b-4251-a0a5-98aca56fb4f1/code)_ _covers all the features mentioned in this post and provides additional examples, implementation details, and advanced techniques._
1313

1414
1. Customize your setup
1515
-----------------------

‎content/claude-code-docs/cli-reference.md‎

Lines changed: 18 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -20,23 +20,24 @@
2020

2121
Customize Claude Code's behavior with these command-line flags:
2222

23-
| Flag | Description | Example |
24-
| :------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------- |
25-
| `--add-dir` | Add additional working directories for Claude to access (validates each path exists as a directory) | `claude --add-dir ../apps ../lib` |
26-
| `--allowedTools` | A list of tools that should be allowed without prompting the user for permission, in addition to [settings.json files](/en/docs/claude-code/settings) | `"Bash(git log:*)" "Bash(git diff:*)" "Read"` |
27-
| `--disallowedTools` | A list of tools that should be disallowed without prompting the user for permission, in addition to [settings.json files](/en/docs/claude-code/settings) | `"Bash(git log:*)" "Bash(git diff:*)" "Edit"` |
28-
| `--print`, `-p` | Print response without interactive mode (see [SDK documentation](/en/docs/claude-code/sdk) for programmatic usage details) | `claude -p "query"` |
29-
| `--append-system-prompt` | Append to system prompt (only with `--print`) | `claude --append-system-prompt "Custom instruction"` |
30-
| `--output-format` | Specify output format for print mode (options: `text`, `json`, `stream-json`) | `claude -p "query" --output-format json` |
31-
| `--input-format` | Specify input format for print mode (options: `text`, `stream-json`) | `claude -p --output-format json --input-format stream-json` |
32-
| `--verbose` | Enable verbose logging, shows full turn-by-turn output (helpful for debugging in both print and interactive modes) | `claude --verbose` |
33-
| `--max-turns` | Limit the number of agentic turns in non-interactive mode | `claude -p --max-turns 3 "query"` |
34-
| `--model` | Sets the model for the current session with an alias for the latest model (`sonnet` or `opus`) or a model's full name | `claude --model claude-sonnet-4-20250514` |
35-
| `--permission-mode` | Begin in a specified [permission mode](iam#permission-modes) | `claude --permission-mode plan` |
36-
| `--permission-prompt-tool` | Specify an MCP tool to handle permission prompts in non-interactive mode | `claude -p --permission-prompt-tool mcp_auth_tool "query"` |
37-
| `--resume` | Resume a specific session by ID, or by choosing in interactive mode | `claude --resume abc123 "query"` |
38-
| `--continue` | Load the most recent conversation in the current directory | `claude --continue` |
39-
| `--dangerously-skip-permissions` | Skip permission prompts (use with caution) | `claude --dangerously-skip-permissions` |
23+
| Flag | Description | Example |
24+
| :------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------- |
25+
| `--add-dir` | Add additional working directories for Claude to access (validates each path exists as a directory) | `claude --add-dir ../apps ../lib` |
26+
| `--allowedTools` | A list of tools that should be allowed without prompting the user for permission, in addition to [settings.json files](/en/docs/claude-code/settings) | `"Bash(git log:*)" "Bash(git diff:*)" "Read"` |
27+
| `--disallowedTools` | A list of tools that should be disallowed without prompting the user for permission, in addition to [settings.json files](/en/docs/claude-code/settings) | `"Bash(git log:*)" "Bash(git diff:*)" "Edit"` |
28+
| `--print`, `-p` | Print response without interactive mode (see [SDK documentation](/en/docs/claude-code/sdk) for programmatic usage details) | `claude -p "query"` |
29+
| `--append-system-prompt` | Append to system prompt (only with `--print`) | `claude --append-system-prompt "Custom instruction"` |
30+
| `--output-format` | Specify output format for print mode (options: `text`, `json`, `stream-json`) | `claude -p "query" --output-format json` |
31+
| `--input-format` | Specify input format for print mode (options: `text`, `stream-json`) | `claude -p --output-format json --input-format stream-json` |
32+
| `--include-partial-messages` | Include partial streaming events in output (requires `--print` and `--output-format=stream-json`) | `claude -p --output-format stream-json --include-partial-messages "query"` |
33+
| `--verbose` | Enable verbose logging, shows full turn-by-turn output (helpful for debugging in both print and interactive modes) | `claude --verbose` |
34+
| `--max-turns` | Limit the number of agentic turns in non-interactive mode | `claude -p --max-turns 3 "query"` |
35+
| `--model` | Sets the model for the current session with an alias for the latest model (`sonnet` or `opus`) or a model's full name | `claude --model claude-sonnet-4-20250514` |
36+
| `--permission-mode` | Begin in a specified [permission mode](iam#permission-modes) | `claude --permission-mode plan` |
37+
| `--permission-prompt-tool` | Specify an MCP tool to handle permission prompts in non-interactive mode | `claude -p --permission-prompt-tool mcp_auth_tool "query"` |
38+
| `--resume` | Resume a specific session by ID, or by choosing in interactive mode | `claude --resume abc123 "query"` |
39+
| `--continue` | Load the most recent conversation in the current directory | `claude --continue` |
40+
| `--dangerously-skip-permissions` | Skip permission prompts (use with caution) | `claude --dangerously-skip-permissions` |
4041

4142
<Tip>
4243
The `--output-format json` flag is particularly useful for scripting and

0 commit comments

Comments
 (0)