Early flag scan no longer mistakes tool lists and directories…

What

The scan Claude Code does over its own arguments before full parsing now knows that --allowedTools, --allowed-tools, --disallowedTools, --disallowed-tools, --add-dir, --agents and --append-system-prompt each consume a following value, so those values are no longer read as flags themselves.

Details

This scan runs ahead of the main parser to pick up things like --ax-screen-reader, --model and --effort.

Evidence

"--append-system-prompt",

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Read from

Names in the bundle--allowedTools--disallowedTools--add-dir--agents--append-system-prompt

Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Confirmed since 12 Sep 2026 Anthropic's documentation has since written up --agents, on Error reference. | `Error: Invalid --agents configuration:` | [Command-line errors](#invalid-agents-configuration) | errors see the edit

Confirmed since 11 Sep 2026 Anthropic's documentation has since written up --disallowedTools, on Tools reference. * A permissions [deny rule](/docs/en/permissions#match-all-uses-of-a-tool), the `--disallowedTools` flag, or [`--restricted`](/docs/en/cli-reference#cli-flags) removes `Bash` from the session. tools-reference see the edit

Confirmed since 11 Sep 2026 Anthropic's documentation has since written up --allowedTools, on Tools reference. * You name `Glob` or `Grep` in [`--tools` or `--allowedTools`](/docs/en/cli-reference#cli-flags) when you start the session, or in the equivalent [Agent SDK](/docs/en/agent-sdk/overview) options. With `--tools` you get the ones you list, a… tools-reference see the edit

Added since 11 Sep 2026 A small documentation edit on CLI reference touched a line naming --disallowedTools after this was published. | `--tools` | Restrict which built-in tools Claude can use. Use `""` to disable all, `"default"` for the default set, or tool names like `"Bash,Edit,Read"`. On macOS, Linux, and WSL, the default set leaves out `Glob` and `Grep`, as describ… cli-reference see the edit

Added since 11 Sep 2026 A small documentation edit on Run Claude Code programmatically touched a line naming --allowedTools after this was published. * **`dontAsk`**: Claude Code denies every call that would otherwise prompt, which is useful for locked-down CI runs. Actions that need no approval in Manual mode still run, such as file reads in your working directories and the [read-only … headless see the edit

Added since 11 Sep 2026 A small documentation edit on Fullscreen rendering touched a line naming --append-system-prompt after this was published. * Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-prompt-snapshot` flags fullscreen see the edit

How sure we are

Two sources agreeTwo things we can check say the same as this entry.

Anthropic's documentation agreesAnthropic's documentation has since written up --append-system-prompt, on How Claude Code uses prompt caching.

Anthropic's release notes agreeFixed /tui dropping launch --allowed-tools/--disallowed-tools rules when it restarts; it now declines to switch, with the reason, when the…

See this entry in the whole of v2.1.234 →

The build it came inv2.1.234

17 Aug 2026 · 332 entries, this one is #232.

Use it now28
You'll notice172
Nothing to try yet32
Under the hood100

Either side of it

v2.1.233Older
v2.1.235Newer

Open the release →

Names in this entry

cli--allowedTools
Tools that execute without prompting for permission. See permission rule syntax for pattern matching. To restrict which tools are available, use --tools instead. If you name one of the task-tracking tools here, Claude Code also opts the session in
cli--allowed-tools
Tools that execute without prompting for permission. See permission rule syntax for pattern matching. To restrict which tools are available, use --tools instead. If you name one of the task-tracking tools here, Claude Code also opts the session in
cli--disallowedTools
Deny rules. A bare tool name removes the matching tools from Claude's context: "Edit" removes Edit, "" removes every tool, and "mcp__" removes every MCP tool. A scoped rule such as Bash(rm *) leaves the tool available and denies only calls that match as written. A rule naming EndConversation can't remove it while any other tool remains
cli--disallowed-tools
Deny rules. A bare tool name removes the matching tools from Claude's context: "Edit" removes Edit, "" removes every tool, and "mcp__" removes every MCP tool. A scoped rule such as Bash(rm *) leaves the tool available and denies only calls that match as written. A rule naming EndConversation can't remove it while any other tool remains
cli--add-dir
Add additional working directories for Claude to read and edit files. Grants file access; Claude Code doesn't discover most .claude/ configuration from these directories. Validates that each path exists as a directory. You can't add most network paths, such as \\server\share. To persist these directories across sessions, set permissions.additionalDirectories in settings
cli--agents
Define custom subagents dynamically via JSON. Accepts the fields listed for CLI-defined subagents. With --print, the value can instead be the path to a JSON file holding the object; the file form requires Claude Code v2.1.281 or later. Claude Code validates the value at startup and exits on an invalid one; see Invalid --agents configuration for the message and for the flags and environment variable that skip the validation. Validation requires Claude Code v2.1.242 or later
cli--append-system-prompt
Append custom text to the end of the default system prompt
cli--model
Sets the model for the current session with a model alias such as sonnet, opus, haiku, or fable, or a model's full name. Overrides the model setting and ANTHROPIC_MODEL
cli--effort
Set the effort level for the current session. Options: low, medium, high, xhigh, max, or ultracode. Available levels depend on the model. ultracode requests xhigh effort with ultracode turned on, and requires Claude Code v2.1.203 or later. Overrides the modelSettings and effortLevel settings for this session and does not persist

Anthropic's note

Upstream's own release notes for v2.1.234 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Fixed /tui dropping launch --allowed-tools/--disallowed-tools rules when it restarts; it now declines to switch, with the reason, when the session has restrictions a restart can't carry over

Is this right?