One read of Claude Code CLIclaude-code-20261110T180701Z
14 pages moved out of 228 read.
Pages moved
14
significant first
Pages read
228
in this capture
Captured
18:07 UTC
Corpus hash
09d9ec4623b1
corpus-hash
What this read moved
1-14 of 14agent-sdk/typescript Changed · +4 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 2003
20032003
20042004#### `startup_failure_reason`
20052005
2006Why Claude Code refused to start, so your application can offer the fix instead of a retry. Claude Code sets it on the `error_during_execution` result it writes before exiting on a known startup failure. That result carries zeroed totals, and its `errors` array carries the same text as stderr. The field is absent on every other result. Requires Agent SDK v0.3.274 or later.
2006Why Claude Code refused to start, so your application can offer the fix instead of a retry. Claude Code sets it on the `error_during_execution` result it writes before exiting on a known startup failure. That result carries zeroed totals, and its `errors` array carries the failure message. The field is absent on every other result. Requires Agent SDK v0.3.274 or later.
20072007
20082008Set `CLAUDE_CODE_STARTUP_FAILURE_RESULTS` to `1` in [`env`](#options) to receive this result for every `SDKStartupFailureReason` value. Without that variable, Claude Code writes the result only for these failures, and the rest end with stderr output, a non-zero exit, and no result message:
20092009
from line 4775
47754775
47764776Returns the scheduled cron jobs: durable jobs from `.claude/scheduled_tasks.json` and session-only jobs from the current session. A session-only job carries `durable: false`; jobs read from disk omit the field.
47774777
4778`nextFireAt` is the job's next run time in epoch milliseconds, [jitter](https://code.claude.com/docs/en/scheduled-tasks.md#jitter) included. No value is earlier than the `CronList` call
4778`nextFireAt` is the job's next run time in epoch milliseconds, [jitter](https://code.claude.com/docs/en/scheduled-tasks.md#jitter) included. No value is earlier than the `CronList` call: a
artifacts Changed · +16 / -0 lines
### Turn off one-step artifact updates
from line 85
8585Update https://claude.ai/code/artifact/5fbea6f3-... with today's numbers.
8686```
8787
88### Turn off one-step artifact updates
89
90A one-step update is a small change Claude makes to an artifact's file as part of a publish, instead of through an `Edit` or `Write` call.
91
92To turn one-step updates off, set [`CLAUDE_CODE_ARTIFACT_PUBLISH_EDITS`](https://code.claude.com/docs/en/env-vars) to `0`. This example adds the variable to the `env` block in `~/.claude/settings.json`:
93
94```json theme={null}
95{
96 "env": {
97 "CLAUDE_CODE_ARTIFACT_PUBLISH_EDITS": "0"
98 }
99}
100```
101
102Then quit and relaunch Claude Code, because a running session doesn't reread the variable.
103
88104## Find an artifact again
89105
90106Run `/artifacts` in Claude Code to list the artifacts you own and the ones shared with you. The current session's artifacts come first, under **This session**.
auto-mode-config Changed · +4 / -4 lines
from line 176
176176
177177Claude Code scans in the background, then shows you the draft. You accept or discard it as a whole, so edit `~/.claude/settings.json` afterwards to adjust single entries. When you accept, Claude Code writes the draft and reconciles it with the settings you already have:
178178
179* Claude Code writes the `environment` list without `"$defaults"`, because the draft spells out the built-in entries it left unchanged
179* If you chose to add to the `environment` list in `~/.claude/settings.json`, you keep any `"$defaults"` entry in it. If you chose to replace that list, you lose that entry, so add `"$defaults"` back if you want the default entries
180180* Claude Code includes `"$defaults"` in each of the `allow`, `soft_deny`, and `hard_deny` lists the draft adds entries to, unless you already wrote an `allow` list without it, so the [built-in rules](#override-the-block-and-allow-rules) you haven't replaced stay in effect
181181* After saving, Claude Code offers to remove `permissions.allow` rules in `~/.claude/settings.json` that auto mode ignores, such as `Bash(*)`, or that auto-approve destructive commands
182182
from line 212
212212
213213Three additional fields let you replace the classifier's built-in rule lists:
214214
215* `autoMode.hard_deny`: unconditional security boundaries
215* `autoMode.hard_deny`: actions to block even when the user asks for them
216216* `autoMode.soft_deny`: destructive actions that user intent can clear
217217* `autoMode.allow`: exceptions to soft block rules
218218
from line 227
227227
228228General requests don't count as explicit intent. Asking Claude to "clean up the repo" doesn't authorize force-pushing, but asking Claude to "force-push this branch" does.
229229
230To loosen, add to `allow` when the classifier repeatedly flags a routine pattern the default exceptions don't cover. To tighten, add to `soft_deny` for destructive risks specific to your environment that the defaults miss, or to `hard_deny` for security boundaries that must never be crossed.
230To loosen, add to `allow` when the classifier repeatedly flags a routine pattern the default exceptions don't cover. To tighten, add to `soft_deny` for destructive risks specific to your environment that the defaults miss, or to `hard_deny` for actions to block even when the user asks for them.
231231
232232To keep the built-in rules while adding your own, include the literal string `"$defaults"` in the array. The default rules are spliced in at that position, so your custom rules can go before or after them, and you continue to inherit updates as the built-in list changes across releases.
233233
from line 248
248248 "soft_deny": [
249249 "$defaults",
250250 "Never run database migrations outside the migrations CLI, even against dev databases",
251 "Never modify files under infra/terraform/prod/: production infrastructure changes go through the review workflow"
251 "Running terraform apply in infra/terraform/prod/ needs an explicit request: production infrastructure changes go through the review workflow"
252252 ],
253253 "hard_deny": [
254254 "$defaults",
claude-security Changed · +4 / -4 lines
from line 67
6767
6868**2. Choose what to scan**
6969
70The plugin reads your repository first, then offers the whole repository or a focused area, with each option's file count and relative cost stated. Pick the whole repository, or answer "I don't know" and the plugin picks a sensible default for your repository's size.
70The plugin reads your repository first, then offers the whole repository or a focused area. Pick the whole repository, or answer "I don't know" and the plugin picks a sensible default for your repository's size.
7171
7272**3. Confirm the run**
7373
from line 91
9191
9292When your branch has commits its base doesn't, the `/claude-security` menu offers to scan only that diff, so you can check a branch before merging. You can also scan one of your open pull requests, or a single commit by asking for it, such as "scan commit abc1234". Only committed changes are scanned: commit or stash in-progress edits first, or run a full scan, which reads the working tree.
9393
94Change scans need a git repository; full scans of an unversioned directory still work. Finding your open pull requests is the one step that reaches the network, and it's offered only when your session already has permission to run the GitHub CLI and `gh` is signed in.
94Change scans need a git repository; full scans of an unversioned directory still work. Finding your open pull requests is offered only when your session already has permission to run the GitHub CLI and `gh` is signed in.
9595
9696### Scope large repositories
9797
from line 116
116116* **`CLAUDE-SECURITY-RESULTS.md`**: the report, with each finding's ID, such as `F1`, plus its impact, exploit scenario, severity, confidence, and recommendation
117117* **`CLAUDE-SECURITY-RESULTS.jsonl`**: the same findings in machine-readable form, one JSON object per line
118118* **`CLAUDE-SECURITY-RESULTS.sarif`**: the same findings as a [SARIF 2.1.0](https://docs.oasis-open.org/sarif/sarif/v2.1.0/sarif-v2.1.0.html) log for GitHub code scanning and any other tool that reads the standard. The scan classifies findings under their [CWE](https://cwe.mitre.org/) weakness categories
119* **`CLAUDE-SECURITY-REVISION-<commit>.json`**: the revision stamp, recording which commit was scanned, at what [scan effort](#choose-a-scan-effort), whether uncommitted changes were part of the scanned tree, and how thoroughly the run was verified, so a report is always tied to the code it describes. A scan outside version control stamps `UNVERSIONED` in place of the commit
119* **`CLAUDE-SECURITY-REVISION-<commit>.json`**: the revision stamp, recording which commit was scanned, at what [scan effort](#choose-a-scan-effort), whether uncommitted changes were part of the scanned tree, and how thoroughly the run was verified. A scan outside version control stamps `UNVERSIONED` in place of the commit
120120
121121That directory is the only change a scan makes to your checkout, and it carries its own `.gitignore`, so a stray `git add` never sweeps a report into a commit. To keep a report in history for an audit trail, delete that one `.gitignore` file and commit the directory like any other.
122122
123Findings only appear in the report after independent verifier agents analyze them, which keeps reports short and worth reading. Scans are nondeterministic: two scans of the same code can surface different findings. Run scans regularly, and use the revision stamps to attribute each report to the exact code and settings it covered.
123Findings only appear in the report after independent verifier agents analyze them, which keeps reports short and worth reading. Scans are nondeterministic: two scans of the same code can surface different findings. Run scans regularly.
124124
125125## Fix findings
126126
errors Changed · +36 / -1 lines
### Server file path not read ### Refusing to apply edits: a hook is configured for file edits in this session
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 318
318318| `The packages it lists are not installed` / `The packages it lists were not installed, because` | [Plugin troubleshooting](https://code.claude.com/docs/en/plugins/troubleshooting.md#the-packages-it-lists-are-not-installed) |
319319| `does not load (...), so Claude Code ignores the whole file` | [Plugin troubleshooting](https://code.claude.com/docs/en/plugins/troubleshooting.md#does-not-load-so-claude-code-ignores-the-whole-file) |
320320| `path escapes plugin directory` | [Plugin errors](#path-escapes-plugin-directory) |
321| `path not read: <path> is absolute or has a ".." part` | [Plugin errors](#server-file-path-not-read) |
321322| `Plugin not loaded: its manifest <path> was not read` | [Plugin errors](#plugin-not-loaded-its-manifest-was-not-read) |
322323| `path could not be checked` | [Plugin errors](#path-could-not-be-checked) |
323324| `its marketplace entry path does not stay inside the marketplace directory` | [Plugin errors](#marketplace-entry-path-does-not-stay-inside-the-marketplace-directory) |
from line 376
375376| `Command output was lost: the temp filesystem at <dir> is full` / `is out of inodes` | [Tool errors](#disk-quota-or-temp-filesystem-is-full) |
376377| `File is not valid UTF-8. It may use a legacy encoding such as Windows-1252, Shift-JIS or GBK, or be binary` | [Tool errors](#file-is-not-valid-utf-8) |
377378| `git is not installed on this Mac. To install it, run xcode-select --install, then try again.` | [Tool errors](#git-is-not-installed-on-this-mac) |
379| `Refusing to apply edits to <path>: a hook is configured for file edits in this session` | [Tool errors](#a-hook-is-configured-for-file-edits) |
378380| `the source file is not valid UTF-8 text` / `the source file is not valid UTF-16 text` | [Tool errors](#the-source-file-is-not-valid-utf-8-text) |
379381| `the source file has the replacement character U+FFFD` | [Tool errors](#the-source-file-is-not-valid-utf-8-text) |
380382| `Not published: that file is on a network share` | [Tool errors](#not-published-that-file-is-on-a-network-share) |
from line 387
385387| `The safety check for domain ... is rate-limited` | [Tool errors](#webfetch-domain-safety-check-failed) |
386388| `The safety check for domain ... is temporarily rate-limited` | [Tool errors](#webfetch-domain-safety-check-failed) |
387389| `Unable to verify if domain ... is safe to fetch` | [Tool errors](#webfetch-domain-safety-check-failed) |
388| `MCP tool "<tool>" on server "<server>" gave no answer that could be read` / `answered without its text` | [How an MCP tool hook's result is read](https://code.claude.com/docs/en/hooks.md#how-the-tool’s-result-is-read) |
390| `MCP tool "<tool>" on server "<server>" gave no answer that could be read` / `answered without its text` | [How an MCP tool hook's result is read](https://code.claude.com/docs/en/hooks.md#how-the-tools-result-is-read) |
389391| `Can't open MCP settings while no terminal is attached to this background session` | [Background session errors](#commands-refused-in-a-background-session) |
390392| `Can't open MCP settings in a background session` | [Background session errors](#commands-refused-in-a-background-session) |
391393| `blocked because the path is spelled in a form that cannot be safely resolved` | [Background session errors](#write-or-command-blocked-because-the-path-cannot-be-safely-resolved) |
from line 2501
24992501* Before v2.1.299, in VS Code, the Desktop app, and the Agent SDK, images you attached while Claude was working didn't get the resizing that other attached images get. They reached the API at their original size, which led to repeated image errors in long conversations.
25002502* Before v2.1.166, a pasted image could remain in the conversation, and the same error then repeated on every subsequent message
25012503
2502**What to do:**
2503
2504* Resize the image before pasting. The API accepts images up to 8000 pixels on the longest edge for a single image, or 3000 pixels when more than 20 images are in context.
2505* Take a tighter screenshot of the relevant region instead of the full s
2504**What to do
monitoring-usage Changed · +8 / -3 lines
from line 1454
14541454
14551455Like every OTel event on this page, it goes only to the telemetry backend you configure. Requires Claude Code v2.1.227 or later.
14561456
1457When Claude Code can't safely determine the retention period, it pauses the sweep and emits the event with `result` set to `"skipped"` and a `skip_reason`. When [managed settings](https://code.claude.com/docs/en/server-managed-settings.md) set `cleanupPeriodDays`, the managed value pins the retention period and the sweep runs even when a settings file in a lower-priority scope is broken or invalid. When `managed-settings.json` itself can't be read, Claude Code still pauses the sweep unless the [managed tier](https://code.claude.com/docs/en/managed-settings.md#how-claude-code-combines-managed-sources) supplies `cleanupPeriodDays` from elsewhere, such as server-managed settings or a `managed-settings.d/` drop-in beside the broken file. The deletion counter attributes are present only when `result` is `"complete"`.
1457Read `result` to see whether the sweep ran:
14581458
1459* `"complete"`: the sweep ran, and the event carries its counts
1460* `"skipped"`: Claude Code couldn't safely determine the retention period, so it paused the sweep and the event carries no counts. If `skip_reason` is `"settings_unknowable"` or `"settings_invalid_key_set"`, fix the settings error that `/status` reports on that machine so a later session can run the sweep
1461
1462When [managed settings](https://code.claude.com/docs/en/server-managed-settings.md) set `cleanupPeriodDays`, the managed value pins the retention period and the sweep runs even when a settings file in a lower-priority scope is broken or invalid.
1463
14591464**Event Name**: `claude_code.retention_sweep`
14601465
14611466**Attributes**:
from line 1470
14651470* `event.timestamp`: ISO 8601 timestamp
14661471* `event.sequence`: per-process counter for ordering events, described under [Event correlation attributes](#event-correlation-attributes)
14671472* `result`: `"complete"` when the sweep ran, `"skipped"` when Claude Code paused it
1468* `period_days`: The `cleanupPeriodDays` value from merged settings, in days, or `30` when no source sets it. On skipped events, the value the sweep would have used, computed from the settings sources Claude Code could read
1469* `used_default`: `"true"` when no readable settings source sets `cleanupPeriodDays`, `"false"` otherwise. On complete events, `"true"` means the 30-day default applied
1473* `period_days`: The retention period the sweep started with, in days: `cleanupPeriodDays` from merged settings, with any change from a [`settings.read` hook](https://code.claude.com/docs/en/plugins/mods/events#settings-read-hook) applied. `30` when that leaves the key unset. On skipped events, the value the sweep would have used, computed from the settings sources Claude Code could read
1474* `used_default`: `"true"` when `period_days` fell back to `30`, `"false"` otherwise. On complete events, `"true"` means the 30-day default applied
14701475* `skip_reason`: Why Claude Code paused the sweep. Present only when `result` is `"skipped"`:
14711476 * `"user_source_disabled"`: User settings are excluded, for example by the [`--setting-sources`](https://code.claude.com/docs/en/cli-reference#cli-flags) flag or the SDK's [`settingSources`](https://code.claude.com/docs/en/agent-sdk/typescript#options) option, and no enabled source provides `cleanupPeriodDays`
14721477 * `"settings_unknowable"`: A settings file couldn't be read or parsed, so `cleanupPeriodDays` or `desktopSessionCleanupPeriodDays` may be set to a value Claude Code can't see
plugins/loading Changed · +14 / -0 lines
### Enabled in an `--add-dir` directory but not loaded
from line 169
169169
170170To opt out of a project-enabled plugin on your machine, set the id to `false` in `.claude/settings.local.json`, which has higher precedence than the project file.
171171
172### Enabled in an `--add-dir` directory but not loaded
173
174Claude Code reads an `enabledPlugins` entry of `true` in one of the added directory's files only when that file's setting sources are on:
175
176* **`.claude/settings.json`**: `project`
177* **`.claude/settings.local.json`**: `project` and `local`
178
179Check which setting sources the session loads. You set them with [`--setting-sources`](https://code.claude.com/docs/en/cli-reference#cli-flags). In the CLI, `user`, `project`, and `local` are all on by default.
180
181For example, if you run `claude --setting-sources user --add-dir ./shared` in your shell, Claude Code reads neither file in `./shared`. Pass the flag for the file that holds the `true`:
182
183* **`settings.json`**: `--setting-sources user,project`
184* **`settings.local.json`**: `--setting-sources user,project,local`
185
172186### Enabled in project settings but not installed
173187
174188By default, a plugin enabled only in your project's `.claude/settings.json` doesn't load at session start until you install it on your machine. With the marketplace on your machine, the `/plugin` **Errors** tab shows [`Plugin "<name>" is enabled in project settings but isn't installed here`](https://code.claude.com/docs/en/plugins/troubleshooting#plugin-is-enabled-in-project-settings-but-isnt-installed-here) or [`Plugin "<name>" not cached at <path>`](https://code.claude.com/docs/en/plugins/troubleshooting#plugin-not-cached-at).
server-managed-settings Changed · +5 / -1 lines
from line 91
9191
9292To confirm that settings are being applied, ask a user to restart Claude Code. If the configuration includes settings that trigger the [security approval dialog](#security-approval-dialogs), the user sees a prompt describing the managed settings the next time Claude Code fetches them: at the next start, or within an hour in a running interactive session. You can also verify that managed permission rules are active by having a user run `/permissions` to view their effective permission rules.
9393
94In a session, have the user run `/status`. The [`Setting sources` line](https://code.claude.com/docs/en/managed-settings#read-the-source-in-/status) lists `Enterprise managed settings` with `remote` in parentheses when server-managed settings apply.
95
9496To check the fetch outcome on a specific machine, have the user run `claude doctor` and read the `Managed settings (remote)` line. Requires Claude Code v2.1.248 or later. The line reports one of four outcomes:
9597
9698* The delivered settings loaded
from line 245
243245* If the gateway answers an attended interactive launch with a `401` and this setting is off, the gateway has ended that sign-in. Claude Code prints [`Cloud gateway session expired — run /login to reconnect.`](https://code.claude.com/docs/en/errors#cloud-gateway-session-expired) and opens the session signed out of the gateway until the user runs `/login`.
244246* When the fetch fails in any other way, or in any other kind of launch except a `claude auth` subcommand, the client exits with an error.
245247
246When this setting is active in a session that fetches server-managed settings, the CLI blocks at startup until remote settings are freshly fetched. If the fetch fails, the CLI exits rather than proceeding without the policy. This setting self-perpetuates: once delivered from the server, it is also cached locally so that subsequent startups enforce the same behavior even before the first successful fetch of a new session. A session that [doesn't fetch server-managed settings](#platform-availability) starts without waiting.
248When this setting is active in a session that fetches server-managed settings, the CLI blocks at startup until remote settings are freshly fetched. If the fetch fails, the CLI exits rather than proceeding without the policy. A session that [doesn't fetch server-managed settings](#platform-availability) starts without waiting.
247249
248250To enable this, add the key to your managed settings configuration:
249251
from line 256
254256```
255257
256258You can also set this key in an [endpoint-managed](https://code.claude.com/docs/en/managed-settings.md#delivery-mechanisms) MDM profile or system `managed-settings.json` file to enforce fail-closed behavior on first launch, before any server payload has arrived. This flag is an exception to the [precedence rule](#settings-precedence) above: Claude Code honors it when any admin-controlled managed source sets it, even if a cached server-managed payload is also present, so it doesn't ignore an MDM-delivered value when server-managed settings exist.
259
260On later startups, Claude Code reads a server-delivered value from the cached settings, so the setting is active before the new session's first fetch. To keep the setting active without relying on the cached copy, also set the key in an endpoint-managed source.
257261
258262When a [`policyHelper`](https://code.claude.com/docs/en/settings-reference#policyhelper) supplies managed settings, its output replaces every other managed source for the keys Claude Code reads after startup. For the sources Claude Code reads this key from, see [its settings entry](https://code.claude.com/docs/en/settings-reference.md#forceremotesettingsrefresh). The `policyHelper` entry says which sources Claude Code reads the helper from and when it runs.
259263
claude-apps-gateway-spend-limits Changed · +1 / -1 lines
from line 72
72723. List price for the [`models[].id`](https://code.claude.com/docs/en/claude-apps-gateway-config#models) you mapped to that upstream ID, for upstream strings that carry no model name, such as an Amazon Bedrock application-inference-profile ARN or a Microsoft Foundry deployment name. Requires v2.1.218 or later.
73734. The unknown-model tier of \$5/\$25 per million input/output tokens, so an ID the meter can't place is never free. The gateway warns at boot and once per ID at runtime when it uses this tier.
7474
75Whichever rate applies, the meter then multiplies the amount by [`pricing.multiplier`](https://code.claude.com/docs/en/claude-apps-gateway-config#pricing), default `1`.
75Whichever rate applies, the meter then multiplies the amount by [`pricing.multiplier`](https://code.claude.com/docs/en/claude-apps-gateway-config#pricing), default `1`. Requires a gateway server running Claude Code v2.1.227 or later.
7676
7777Client aborts are billed too. When a stream ends without the upstream's final usage frame, the meter bills a floor estimate of about four characters per output token for the text already sent to the client, so aborting requests early doesn't evade a cap.
7878
desktop-ios-simulator Changed · +2 / -2 lines
from line 4
44
55> [!NOTE]
66>
7> The iOS Simulator pane is in public beta in Claude Code Desktop on macOS. It's available on Pro, Max, Ultra, Team, and Enterprise plans, except in Enterprise organizations that have a HIPAA configuration enabled.
7> The iOS Simulator pane is in public beta in Claude Code Desktop on macOS. It's available on Pro, Max, Ultra, Team, and Enterprise plans, except in Enterprise organizations that have a HIPAA configuration enabled. It isn't available if you use a [third-party provider](https://code.claude.com/docs/en/third-party-integrations.md).
88
99The iOS Simulator pane shows your app running in Apple's iOS Simulator next to your conversation in Claude Code Desktop. When Claude builds, installs, launches, or checks your app in a simulator, the pane opens automatically and streams the device screen live. Use it to watch Claude run and test your app, or to tap through the app yourself while Claude keeps working.
1010
from line 143
143143* State the goal explicitly, for example "run the app in the iOS Simulator and tap through the signup flow".
144144* Confirm Xcode and the iOS simulators are installed and that you're using a [recommended Xcode version](#requirements).
145145* If your organization manages Claude Code, the [simulator tools may be disabled by policy](#turn-off-simulator-access).
146* If you're in an Enterprise organization that has a HIPAA configuration enabled, the simulator pane isn't available to you.
146* If you're in an Enterprise organization that has a HIPAA configuration enabled, or you use a [third-party provider](https://code.claude.com/docs/en/third-party-integrations.md), the simulator pane isn't available to you.
147147* The simulator pane requires Claude Desktop v1.24012.0 or later. Open **Claude > Check for Updates…**, then restart the app.
148148
149149### The simulator pane says no simulators were found
interactive-mode Changed · +3 / -1 lines
from line 247
247247| `d`/`x` | Delete selection |
248248| `y` | Yank selection |
249249| `c`/`s` | Change selection |
250| `p` | Replace selection with register contents |
250| `p`/`P` | Replace selection with register contents |
251251| `r{char}` | Replace every selected character with `{char}` |
252252| `~`/`u`/`U` | Toggle, lowercase, or uppercase selection |
253253| `>`/`<` | Indent or dedent selected lines |
from line 299
299299 * Press `Backspace` on empty search to cancel
300300
301301Accepting a match or canceling the search takes effect immediately, even while Claude Code is still loading the history.
302
303To find an earlier prompt when all you remember is something long you pasted into it, such as an error log, press `Ctrl+R` and type a word from the paste. Requires Claude Code v2.1.314 or later.
302304
303305## Background Bash commands
304306
permission-modes Changed · +2 / -0 lines
from line 682
682682* **If you accept**: Claude Code sets `skipDangerousModePermissionPrompt` to `true` in `~/.claude/settings.json`, so later sessions skip the dialog. To see the dialog again, remove the key from that file or set it to `false`. The [`skipDangerousModePermissionPrompt` reference](https://code.claude.com/docs/en/settings-reference#skipdangerousmodepermissionprompt) lists the other settings files where you or your organization can set it.
683683* **If you decline**: Claude Code exits.
684684
685If you pass [`--setting-sources`](https://code.claude.com/docs/en/cli-reference#cli-flags) without `user`, the dialog can appear again although you accepted it earlier. To skip it, add `user`, as in `--setting-sources user,project`.
686
685687In [non-interactive mode](https://code.claude.com/docs/en/headless.md) no dialog is shown.
686688
687689A [background session](https://code.claude.com/docs/en/agent-view.md) honors your acceptance when it's recorded in user or managed settings:
plugins/manifest-reference Changed · +1 / -1 lines
from line 399
399399
400400Every component path must resolve inside the plugin root and must exist. `claude plugin validate` checks the paths under every component key:
401401
402* **Containment**: a path that resolves outside the plugin root doesn't load, and the `/plugin` **Errors** tab shows `<component> path escapes plugin directory: <path>`. A path containing `..` is the usual case, and `claude plugin validate` reports the error `Path contains ".." which could be a path traversal attempt`
402* **Containment**: a path that resolves outside the plugin root doesn't load, and the `/plugin` **Errors** tab shows `<component> path escapes plugin directory: <path>`. A path containing `..` is the usual case, and `claude plugin validate` reports the error `Path contains ".." which could be a path traversal attempt`. For an `mcpServers` or `lspServers` file, a [`path not read`](https://code.claude.com/docs/en/errors#server-file-path-not-read) message means the path is absolute or contains `..`
403403* **Existence**: a path that doesn't exist doesn't load, and the `/plugin` **Errors** tab shows `<component> path not found: <path>`. `claude plugin validate` reports the error `Path not found`
404404
405405For `outputStyles`, `lspServers`, `monitors`, and `themes` paths, the `claude plugin validate` check requires Claude Code v2.1.283 or later.
settings-reference Changed · +1 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 1259
12591259
12601260Skip the confirmation dialog Claude Code shows before a session enters `bypassPermissions` mode, whether from `--dangerously-skip-permissions` or from `defaultMode: "bypassPermissions"`. Claude Code writes `true` here in your user settings when you accept that dialog once.
12611261
1262* **Scope**: [`User, local, or managed`](#scopes). An untrusted repository can't skip the dialog for you.
1262* **Scope**: [`User, local, or managed`](#scopes), and files passed with `--settings`. [Background sessions](https://code.claude.com/docs/en/permission-modes.md#bypass-permissions-ignored-in-a-background-session) count only user and managed settings. An untrusted repository can't skip the dialog for you.
12631263* **Type**: Boolean
12641264 * `true`: Claude Code skips the confirmation dialog before a session enters `bypassPermissions` mode
12651265 * `false`: the same as unset; the dialog appears unless another of these files sets `true`
from line 3342
33423342 * `true`: you see full tool output
33433343 * `false`: you see truncated summaries of tool output
33443344* **Default**: `false`
3345* **Per-session overrides**: [`--verbose`](https://code.claude.com/docs/en/cli-reference#cli-flags) takes precedence over this key for one session
3346
3347```json settings.json theme={null}
3348{
3349 "verbose": true
3350}
3351```
3352
3353A [`viewMode`](#viewmode) value or a sticky `/focus` selection overrides this ke
3345* **Per-session overrides**: [`--verbose`](https://code.claude.com/docs/en/cli-reference#c