What this read moved
26–50 of 79This capture is too large to show at once. Changes 26-50 of 79 are below, significant first; the rest are on the following screens.
web-quickstart Changed · +6 / -1 lines
from line 224
224224
225225If you typed it inside Claude Code and the command menu shows `No commands match "/web-setup"`, or submitting it returns `Unknown command: /web-setup`, the command is hidden because a requirement isn't met. The cause is usually that you're authenticated with an API key or third-party provider instead of a claude.ai subscription. Run `/login` to sign in with your claude.ai account.
226226
227On Team and Enterprise plans, the command is hidden by default: the [Quick web setup toggle](/docs/en/claude-code-on-the-web#github-authentication-options) is off until an Owner turns it on. While it's off, [connect GitHub from the browser](#connect-github) instead. The command is also hidden when an administrator has disabled Claude Code on the web for your organization, or when your Enterprise organization has [Zero Data Retention](/docs/en/zero-data-retention) enabled, which makes Claude Code on the web unavailable.
227On Team and Enterprise plans, the command is hidden by default: the [Quick web setup toggle](/docs/en/claude-code-on-the-web#github-authentication-options) is off until an Owner turns it on. While it's off, [connect GitHub from the browser](#connect-github) instead.
228
229The command is also hidden in two other cases:
230
231* An administrator has disabled Claude Code on the web for your organization. In this case, submitting `/web-setup` returns [`Cloud sessions are disabled by your organization's policy`](/docs/en/errors#cloud-sessions-are-disabled-by-your-organizations-policy). Before v2.1.268, this case also returned `Unknown command: /web-setup`.
232* Your Enterprise organization has [Zero Data Retention](/docs/en/zero-data-retention) enabled, which makes Claude Code on the web unavailable.
228233
229234### "Could not create a cloud environment" or "No cloud environment available" when using `--cloud`
230235
workflows Changed · +3 / -3 lines
from line 23
2323| Scale | A few delegated tasks per turn | Same as subagents | A handful of long-running peers | Dozens to hundreds of agents per run |
2424| Interruption | Restarts the turn | Restarts the turn | Teammates keep running | Resumable in the same session |
2525
26A workflow moves the plan into code. With subagents, skills, and agent teams, Claude is the orchestrator: it decides turn by turn what to spawn or assign next, and every result lands in a context window. A workflow script holds the loop, the branching, and the intermediate results itself, so Claude's context holds only the final answer.
26A workflow moves the plan into code. With subagents, skills, and agent teams, Claude is the orchestrator: it decides turn by turn what to spawn or assign next, and every result goes into a context window. A workflow script holds the loop, the branching, and the intermediate results itself, so Claude's context holds only the final answer.
2727
2828Moving the plan into code also lets a workflow apply a repeatable quality pattern, not just run more agents: it can have independent agents adversarially review each other's findings before they're reported, or draft a plan from several angles and weigh them against each other, so you get a more trustworthy result than a single pass.
2929
from line 57
5757 </Step>
5858
5959 <Step title="Read the report">
60 When the run finishes, the report lands in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
60 When the run finishes, the report appears in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
6161
6262 When the verifier agents can't check a claim, such as after a rate limit or API error, the report lists that claim as unverified instead of counting it as refuted.
6363 </Step>
from line 257
257257
258258### Review every changed file and write one summary
259259
260Run a reviewer per file, then hand all the findings to one agent that ranks and deduplicates them.
260Run a reviewer per file, then pass all the findings to one agent that ranks and deduplicates them.
261261
262262```text wrap theme={null}
263263use a workflow to review every file changed in this PR for correctness issues, then merge the per-file findings into one ranked summary
agent-sdk/agent-loop Changed · +1 / -1 lines
from line 320
320320
321321The `result` field holds the final text output and is only present on the `success` variant, so always check the subtype before reading it.
322322
323All result subtypes carry `total_cost_usd`, `usage`, `num_turns`, and `session_id` so you can track cost and resume even after errors. Two things to guard for:
323All result subtypes carry `total_cost_usd`, `usage`, `num_turns`, and `session_id` so you can track cost and resume even after errors. Guard for these cases:
324324
325325* After a session crash, the final result is an `error_during_execution` whose cost fields may be zeroed and whose `stop_reason` is `null`, and the process exits after emitting it. See [Recover totals after a session crash](/docs/en/agent-sdk/cost-tracking#recover-totals-after-a-session-crash).
326326* In Python, `total_cost_usd`, `usage`, and `model_usage` are typed as optional, so check that they aren't `None` before you read them.
agent-sdk/claude-code-features Changed · +1 / -1 lines
from line 97
9797
9898## Project instructions (CLAUDE.md and rules)
9999
100`CLAUDE.md` files and `.claude/rules/*.md` files give your agent persistent context about your project: coding conventions, build commands, architecture decisions, and instructions. When `settingSources` includes `"project"` (as in the example above), the SDK loads these files into context at session start. The agent then follows your project conventions without you repeating them in every prompt.
100`CLAUDE.md` files and `.claude/rules/*.md` files give your agent persistent context about your project: coding conventions, build commands, architecture decisions, and instructions. When `settingSources` includes `"project"`, as in the [`settingSources` example](#control-filesystem-settings-with-settingsources), the SDK loads these files into context at session start. The agent then follows your project conventions without you repeating them in every prompt.
101101
102102### CLAUDE.md load locations
103103
agent-sdk/custom-tools Changed · +1 / -1 lines
from line 126
126126
127127Pass the MCP server you created to `query` via the `mcpServers` option. The key in `mcpServers` becomes the `{server_name}` segment in each tool's fully qualified name: `mcp__{server_name}__{tool_name}`. List that name in `allowedTools` so the tool runs without a permission prompt.
128128
129These snippets reuse the `weatherServer` from the [example above](#weather-tool-example) to ask Claude what the weather is in a specific location.
129These snippets reuse the `weatherServer` from the [weather tool example](#weather-tool-example) to ask Claude what the weather is in a specific location.
130130
131131<CodeGroup>
132132 ```python Python theme={null}
agent-sdk/file-checkpointing Changed · +1 / -1 lines
from line 171
171171 </Step>
172172
173173 <Step title="Capture checkpoint UUID and session ID">
174 With the `replay-user-messages` option set (shown above), each user message in the response stream has a UUID that serves as a checkpoint.
174 With the `replay-user-messages` option set, each user message in the response stream has a UUID that serves as a checkpoint.
175175
176176 For most use cases, capture the first user message UUID (`message.uuid`); rewinding to it restores the tracked files to their original state. To store multiple checkpoints and rewind to intermediate states, see [Multiple restore points](#multiple-restore-points).
177177
agent-sdk/plugins Changed · +1 / -1 lines
from line 2
22
33> Load custom plugins to extend Claude Code with skills, agents, hooks, and MCP servers through the Agent SDK
44
5Plugins allow you to extend Claude Code with custom functionality that can be shared across projects. Through the Agent SDK, you can programmatically load plugins from local directories to add capabilities to your agent sessions. A plugin can include:
5Plugins let you extend Claude Code with custom functionality that can be shared across projects. Through the Agent SDK, you can programmatically load plugins from local directories to add capabilities to your agent sessions. A plugin can include:
66
77* **Skills**: capabilities Claude invokes autonomously when relevant. You can also invoke a plugin skill directly with `/plugin-name:skill-name`.
88* **Agents**: specialized subagents for specific tasks
agent-sdk/skills Changed · +1 / -1 lines
from line 114
114114* **Your skills**: prompt artifacts that you author, each a directory holding a `SKILL.md` file. A user-invocable skill's name joins the surface automatically, so dispatching your own `/security-check` and running a built-in work the same way
115115* **Custom command files**: an older artifact form with the same behavior, flat Markdown files in `.claude/commands/` whose filenames become command names. Skills are their recommended successor
116116
117By default, both you and Claude can invoke any skill. You can restrict either path through the skill's [frontmatter](/docs/en/skills#control-who-invokes-a-skill). For a definition of the two terms, see the glossary's [Command](/docs/en/glossary#command) and [Skill](/docs/en/glossary#skill) entries. See [Commands in Claude Code](/docs/en/commands) for every built-in and [Extend Claude with skills](/docs/en/skills) for the complete guide to both artifact forms.
117By default, both you and Claude can invoke any skill. You can restrict either path through the skill's [frontmatter](/docs/en/skills#control-who-invokes-a-skill). For definitions of command and skill, see the glossary's [Command](/docs/en/glossary#command) and [Skill](/docs/en/glossary#skill) entries. See [Commands in Claude Code](/docs/en/commands) for every built-in and [Extend Claude with skills](/docs/en/skills) for the complete guide to both artifact forms.
118118
119119### Discover available commands
120120
agent-sdk/typescript 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.
Nothing in the body moved in this read. What changed is above.
agent-sdk/typescript-v2-preview Changed · +1 / -1 lines
from line 8
88 To migrate, use the [`query()` API](/docs/en/agent-sdk/typescript) and the [session options](/docs/en/agent-sdk/sessions) it accepts. Pass an `AsyncIterable<SDKUserMessage>` for multi-turn conversations, or `options.resume` to continue a saved session. This page is kept for reference if you maintain code on Agent SDK 0.2.x or earlier.
99</Warning>
1010
11V2 was an experimental session API that removed the need for async generators and yield coordination. Instead of managing generator state across turns, each turn was a separate `send()`/`stream()` cycle. The API surface reduced to three concepts:
11V2 was an experimental session API that removed the need for async generators and yield coordination. Instead of managing generator state across turns, each turn was a separate `send()`/`stream()` cycle. The API surface reduced to creating a session, sending a message, and streaming the response:
1212
1313* `createSession()` / `resumeSession()`: Start or continue a conversation
1414* `session.send()`: Send a message
agent-view Changed · +1 / -0 lines
from line 930
930930| Version | Change |
931931| -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
932932| v2.1.268 | When a [delete is refused](#what-deleting-a-session-removes) because git or your `WorktreeRemove` hook couldn't remove the worktree, the message names the cause, including how a hook ended and the start of its stderr. For a linked worktree under the repository's `.claude/worktrees/` with no uncommitted changes to tracked files, no nested repository inside it, and no other session's record naming it, deleting the session again removes the directory anyway, from agent view or with `claude rm <id> --force-remove-worktree <worktree-id>`. Before this release, the row showed only `worktree could not be removed (WorktreeRemove hook failed)` or git's error, the hook's stderr went only to the debug log, and deleting again was refused the same way. |
933| v2.1.268 | After the first `←` shows `Press ← again to open agents`, or `Press ← again to go back to agents` in an attached session, [the first press that comes at least a second later switches](#switch-sessions-without-leaving-the-terminal), even when quicker presses in between were ignored. Before this release, each ignored press restarted the wait, so pressing `←` again at a steady pace didn't switch until you paused for over a second. |
933934| v2.1.260 | When you [background a session](#from-inside-a-session), your other sessions' [agent listing](/docs/en/cross-session-messaging#see-which-sessions-claude-can-reach) shows the conversation once, as its background session, and their messages to it no longer reach the terminal you moved it from. Before this release, that terminal could stay listed as a second interactive session under the conversation's name, and a session that had messaged the conversation before the move kept delivering to that terminal. |
934935| v2.1.260 | When a [delete is refused over unpushed commits](#what-deleting-a-session-removes), the message names the worktree's branch and how many commits are unpushed, and deleting the session again discards the worktree and its commits. Before this release, the refusal said only `worktree has commits that are not pushed anywhere`, deleting again was refused the same way, and deleting the session required pushing the commits or removing the worktree by hand. |
935936| v2.1.257 | `←` [detaches from an attached session while the `/btw` overlay is open](#attach-to-a-session), even mid-answer, and the overlay reopens when you next attach. Before this release, `←` didn't detach while the overlay was open. |
amazon-bedrock Changed · +2 / -2 lines
from line 114
114114Before you invoke an Anthropic model for the first time, submit use case details. You do this once per AWS account.
115115
1161161. Ensure you have the right IAM permissions described below
1172. Navigate to the [Amazon Bedrock console](https://console.aws.amazon.com/bedrock/)
1172. Go to the [Amazon Bedrock console](https://console.aws.amazon.com/bedrock/)
1181183. Select an Anthropic model from the **Model catalog**
1191194. Complete the use case form. Access is granted immediately after submission.
120120
from line 476
476476
477477## Use the Mantle endpoint
478478
479Mantle is an Amazon Bedrock endpoint that serves Claude models through the native Anthropic API shape rather than the Amazon Bedrock Invoke API. It uses the same AWS credentials, IAM permissions, and `awsAuthRefresh` configuration described earlier on this page.
479Mantle is an Amazon Bedrock endpoint that serves Claude models through the native Anthropic API shape rather than the Amazon Bedrock Invoke API. It uses the same [AWS credentials](#2-configure-aws-credentials), [IAM permissions](#iam-configuration), and [`awsAuthRefresh` configuration](#advanced-credential-configuration).
480480
481481### Enable Mantle
482482
artifacts Changed · +2 / -2 lines
from line 120
120120Read the comments on https://claude.ai/code/artifact/5fbea6f3-... and make the changes the commenters ask for.
121121```
122122
123If Claude tells you it can't read comments, check three things:
123If Claude tells you it can't read comments, confirm your version, your session, and your feature-flag setting:
124124
125125* You're running Claude Code v2.1.221 or later.
126126* You're not in your first session since you installed Claude Code or upgraded from a version before v2.1.221. In that [first session after an install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade), Claude might not be able to read comments yet; start a new session and ask again.
from line 229
229229
230230### Bring the result back to your session
231231
232An artifact can act as a lightweight editor for a decision you then hand back to Claude. Ask for an export control that produces text you can paste into the terminal, so the result of interacting with the page flows back into the session instead of staying on the page.
232An artifact can act as a lightweight editor for a decision you then send back to Claude. Ask for an export control that produces text you can paste into the terminal, so the result of interacting with the page flows back into the session instead of staying on the page.
233233
234234```text wrap theme={null}
235235Make a triage board artifact with each open issue as a draggable card across Now, Next, Later, and Cut columns. Add a "Copy as prompt" button that gives me the final ordering to paste back here.
best-practices Changed · +1 / -1 lines
from line 8
88
99But this autonomy still comes with a learning curve. Claude works within certain constraints you need to understand.
1010
11This guide covers patterns that have proven effective across Anthropic's internal teams and for engineers using Claude Code across various codebases, languages, and environments. For how the agentic loop works under the hood, see [How Claude Code works](/docs/en/how-claude-code-works).
11This guide covers patterns that have proven effective across Anthropic's internal teams and for engineers using Claude Code across various codebases, languages, and environments. For how the agentic loop works, see [How Claude Code works](/docs/en/how-claude-code-works).
1212
1313***
1414
checkpointing Changed · +1 / -1 lines
from line 65
6565
6666### Bash command changes not tracked
6767
68Checkpointing does not track files modified by bash commands. For example, if Claude Code runs:
68Checkpointing does not track files modified by Bash commands. For example, if Claude Code runs:
6969
7070```bash theme={null}
7171rm file.txt
claude-directory Changed · +1 / -1 lines
from line 1508
15081508
15091509## Application data
15101510
1511Beyond the config you author, `~/.claude` holds data Claude Code writes during sessions. These files are plaintext. Anything that passes through a tool lands in a transcript on disk: file contents, command output, pasted text.
1511Beyond the config you author, `~/.claude` holds data Claude Code writes during sessions. These files are plaintext. Anything that passes through a tool is written to a transcript on disk: file contents, command output, pasted text.
15121512
15131513### Cleaned up automatically
15141514
claude-platform-on-aws Changed · +1 / -1 lines
from line 247
247247Treat workspace API keys like any other production credential. The [user settings file](/docs/en/settings) `env` block is a convenient way to scope the key to your machine without exporting it globally.
248248
249249<Note>
250 The `/login` and `/logout` commands don't sign you into a Claude.ai subscription for Claude Platform on AWS. Authentication runs through your AWS credentials or workspace API key.
250 The `/login` and `/logout` commands don't sign you into a claude.ai subscription for Claude Platform on AWS. Authentication runs through your AWS credentials or workspace API key.
251251</Note>
252252
253253### 2. Configure Claude Code
cloud-environments Changed · +2 / -2 lines
from line 285
285285
286286¹ Bun is installed but has known [proxy compatibility issues](#install-dependencies-with-a-sessionstart-hook) for package fetching.
287287
288To get the versions of most of the tools in this table, ask Claude to run `check-tools` in a cloud session. It's a shell command installed on the session VM, not a slash command; you ask Claude because [Claude runs all VM commands for you](#run-tests-start-services-and-add-packages). For a tool it doesn't report, such as Ruby, PHP, bun, PostgreSQL, or Redis, ask Claude to run the tool's own version command, for example `psql --version`.
288To get the versions of most of the tools in this table, ask Claude to run `check-tools` in a cloud session. It's a shell command installed on the session VM, not a command you type with `/`; you ask Claude because [Claude runs all VM commands for you](#run-tests-start-services-and-add-packages). For a tool it doesn't report, such as Ruby, PHP, bun, PostgreSQL, or Redis, ask Claude to run the tool's own version command, for example `psql --version`.
289289
290290Node.js versions are installed at `/opt/node20`, `/opt/node21`, and `/opt/node22`, with 22 on `PATH` by default. To work with a different version, ask Claude to prepend that version's `bin` directory, such as `/opt/node20/bin`, to `PATH`.
291291
from line 454
454454
455455SessionStart hooks behave the same in the cloud as locally, with these caveats:
456456
457* **No cloud-only scoping**: hooks run in both local and cloud sessions. To skip local execution, check the `CLAUDE_CODE_REMOTE` environment variable as shown above.
457* **No cloud-only scoping**: hooks run in both local and cloud sessions. To skip local execution, exit early unless the `CLAUDE_CODE_REMOTE` environment variable is `true`, the way the [dependency install script](#install-dependencies-with-a-sessionstart-hook) does.
458458* **Requires network access**: install commands need to reach package registries. If your environment uses **None** network access, these hooks fail. The [default allowlist](#default-allowed-domains) under **Trusted** covers npm, PyPI, RubyGems, and crates.io.
459459* **Proxy compatibility**: in Anthropic-hosted environments, all outbound traffic passes through a [security proxy](#security-proxy), and some package managers don't work correctly with it; Bun is a known example. In a [self-hosted environment](/docs/en/self-hosted-environments-deploy#default-deny-egress), outbound traffic goes through your own network boundary instead.
460460* **Adds startup latency**: hooks run each time a session starts or resumes, unlike setup scripts which benefit from [environment caching](#environment-caching). Keep install scripts fast by checking whether dependencies are already present before reinstalling.
code-review Changed · +3 / -1 lines
from line 48
4848
4949Replying to an inline comment does not prompt Claude to respond or update the PR. To act on a finding, fix the code and push. If the PR is subscribed to push-triggered reviews, the next run resolves the thread when the issue is fixed. To request a fresh review without pushing, comment `@claude review` as a [top-level PR comment](#manually-trigger-reviews).
5050
51To dismiss a finding without a code change, resolve its thread; replying doesn't dismiss it.
52
5153### Check run output
5254
5355Beyond the inline review comments, each review populates the **Claude Code Review** check run that appears alongside your CI checks. Expand its **Details** link to see a summary of every finding in one place, sorted by severity:
from line 317
315317 </Step>
316318</Steps>
317319
318Claude reports the findings as text in the reply in both of these runs, even when a host application requests the findings list described below:
320Claude reports the findings as text in the reply in both of these runs, even when a host application requests a findings list:
319321
320322* In a terminal session, where `/code-review` runs the review as a [forked subagent](/docs/en/skills#run-skills-in-a-subagent)
321323* In a `-p` run with text or JSON output
deep-links Changed · +1 / -1 lines
from line 19
1919
2020The `claude-cli://` prefix is a custom URL scheme that Claude Code registers with your operating system, similar to how `mailto:` links open your email client. When you click a deep link:
2121
221. The browser or app hands the URL to your operating system.
221. The browser or app passes the URL to your operating system.
23232. The operating system recognizes the `claude-cli://` prefix and starts Claude Code on your machine.
24243. A new terminal window opens with Claude Code running in the directory the link specified, and the link's prompt text already in the input box.
25254. You read the prompt, edit it if you want, and press Enter to send it.
desktop-ios-simulator Changed · +1 / -1 lines
from line 68
6868
6969The row under the device name tunes the video stream from the simulator. Lower **Frame rate** or **Resolution** if the pane strains your Mac, switch **Encoding** between H.264 and JPEG, or check **FPS** to display the frame rate the pane is receiving. These settings change how the pane displays the device, not how the app runs.
7070
71You and Claude drive the same device, so your taps change the app state Claude sees. To have Claude check a specific screen, navigate to it by tapping, then ask. While Claude is driving the device, the pane shows a **Claude is using this device** badge above the screen; hold off tapping until the badge clears, so the result reflects the app rather than your input.
71You and Claude drive the same device, so your taps change the app state Claude sees. To have Claude check a specific screen, tap through to it, then ask. While Claude is driving the device, the pane shows a **Claude is using this device** badge above the screen; hold off tapping until the badge clears, so the result reflects the app rather than your input.
7272
7373## How sessions manage devices
7474
devcontainer Changed · +2 / -2 lines
from line 128
128128
129129`CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` also disables the feature-flag evaluation that [Remote Control](/docs/en/remote-control#requirements) and the other [features that need feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) depend on, so sessions in the container can't use them.
130130
131The Dev Container Feature always installs the latest Claude Code release. To pin a specific Claude Code version for reproducible builds, install it from your Dockerfile with `npm install -g @anthropic-ai/[email protected]` instead of using the feature, and set `DISABLE_AUTOUPDATER` as shown above.
131The Dev Container Feature always installs the latest Claude Code release. To pin a specific Claude Code version for reproducible builds, install it from your Dockerfile with `npm install -g @anthropic-ai/[email protected]` instead of using the feature, and set `DISABLE_AUTOUPDATER` to `1` in `containerEnv`.
132132
133133For the full list of policy controls including permission rules, tool restrictions, and MCP server allowlists, see [Set up Claude Code for your organization](/docs/en/admin-setup).
134134
from line 185
185185Once Claude Code is running in your dev container, the pages below cover the rest of an organization rollout: choosing an authentication path, delivering managed policy outside the repository, monitoring usage, and understanding what Claude Code stores and sends.
186186
187187* [Set up Claude Code for your organization](/docs/en/admin-setup): choose an authentication provider, decide how policy reaches devices, and plan the rollout
188* [Server-managed settings](/docs/en/server-managed-settings): deliver managed policy from the Claude.ai admin console so engineers cannot bypass it by editing repository files
188* [Server-managed settings](/docs/en/server-managed-settings): deliver managed policy from the claude.ai admin console so engineers cannot bypass it by editing repository files
189189* [Monitor usage and audit activity](/docs/en/monitoring-usage): export OpenTelemetry metrics and review what your team is running
190190* [Network access requirements](/docs/en/network-config#network-access-requirements): the full domain allowlist for proxies and firewalls
191191* [Telemetry services and opt-out](/docs/en/data-usage#telemetry-services): what Claude Code sends by default and the environment variables that disable it
discover-plugins Changed · +1 / -1 lines
from line 68
6868You can also [create your own LSP plugin](/docs/en/plugins-reference#lsp-servers) for other languages.
6969
7070<Note>
71 If you see `Executable not found in $PATH` in the `/plugin` Errors tab after installing a plugin, install the required binary from the table above.
71 If you see `Executable not found in $PATH` in the `/plugin` Errors tab after installing a plugin, install the binary the [code intelligence](#code-intelligence) table lists for that plugin.
7272</Note>
7373
7474#### What Claude gains from code intelligence plugins
env-vars Changed · +2 / -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 210
210210| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) in tokens, from `100000` to `1000000`. Accepts a plain integer such as `500000` only: a value like `500k` reads as `500` and clamps to the 100K minimum. The effective window is also capped at the model's context window. Takes precedence over the `/autocompact` command, the `--autocompact` flag, and the `autoCompactWindow` setting. The status line's `used_percentage` always measures against the model's full context window, so once this variable is set, that percentage no longer indicates when compaction will run |
211211| `CLAUDE_CODE_AUTO_CONNECT_IDE` | Override automatic [IDE connection](/docs/en/vs-code). By default, Claude Code connects automatically when launched inside a supported IDE's integrated terminal. Set to `false` to prevent this. Set to `true` to force a connection attempt when auto-detection fails, such as when tmux obscures the parent terminal. Takes precedence over the [`autoConnectIde`](/docs/en/settings-reference#autoconnectide) global config setting |
212212| `CLAUDE_CODE_AWS_CHAIN_RESOLVE_TIMEOUT_MS` | Time in milliseconds Claude Code waits for the AWS default credential provider chain to produce credentials before the request fails with [`AWS default-chain credential resolve timed out`](/docs/en/errors#aws-default-chain-credential-resolve-timed-out) (default: `60000`). Raise it when a step in your chain legitimately needs longer, such as a browser-based SSO sign-in with MFA through a wrapper like `aws-vault`. Applies wherever Claude Code signs with the default chain: [Amazon Bedrock](/docs/en/amazon-bedrock#credential-caching-and-resolution-timeout), [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and the [Mantle endpoint](/docs/en/amazon-bedrock#use-the-mantle-endpoint). Requires Claude Code v2.1.207 or later |
213| `CLAUDE_CODE_BASH_EDIT_DIFF` | Set to `0` to turn off the [diff of the files a Bash command changed](/docs/en/hooks#bash), or `1` to record it in every permission mode. Takes precedence over the [`bashEditDiffEnabled`](/docs/en/settings-reference#basheditdiffenabled) setting. Requires Claude Code v2.1.269 or later |
213214| `CLAUDE_CODE_BRIDGE_SESSION_ID` | Set automatically in Bash tool and [hook command](/docs/en/hooks) subprocesses while the session has an active [Remote Control](/docs/en/remote-control) connection, and removed when the connection ends. The value is the session's ID in `session_` form, the same identifier that appears in the session's `claude.ai/code` URL, so a script can link back to the session that ran it. Requires Claude Code v2.1.199 or later. In [cloud sessions](/docs/en/claude-code-on-the-web), read `CLAUDE_CODE_REMOTE_SESSION_ID` instead |
214215| `CLAUDE_CODE_BS_AS_CTRL_BACKSPACE` | Set to `0` to make Claude Code read the `0x08` byte, also written `^H`, as plain Backspace, or `1` to read it as Ctrl+Backspace. Either value replaces the platform default. By default, Claude Code reads it as Ctrl+Backspace on Windows, except when `TERM_PROGRAM` is `mintty` or `TERM` is `cygwin`, and as plain Backspace on macOS and Linux. Set `0` in a Windows terminal where [Backspace deletes a whole word](/docs/en/terminal-config#fix-backspace-deleting-a-whole-word-on-windows) |
215216| `CLAUDE_CODE_CERT_STORE` | Comma-separated list of CA certificate sources for TLS connections. `bundled` is the Mozilla CA set shipped with Claude Code. `system` is the operating system trust store, read only on runtimes with `tls.getCACertificates`: the native binary, or Node 22.15 or later for npm installs. See [CA certificate store](/docs/en/network-config#ca-certificate-store). Default is `bundled,system` |
from line 318
317318| `CLAUDE_CODE_OTEL_FLUSH_TIMEOUT_MS` | Timeout in milliseconds for flushing pending OpenTelemetry spans (default: 5000). See [Monitoring](/docs/en/monitoring-usage) |
318319| `CLAUDE_CODE_OTEL_HEADERS_HELPER_DEBOUNCE_MS` | Interval for refreshing dynamic OpenTelemetry headers in milliseconds (default: 1740000 / 29 minutes). See [Dynamic headers](/docs/en/monitoring-usage#dynamic-headers) |
319320| `CLAUDE_CODE_OTEL_SHUTDOWN_TIMEOUT_MS` | Timeout in milliseconds for the OpenTelemetry exporter to finish on shutdown (default: 2000). Increase if metrics are dropped at exit. See [Monitoring](/docs/en/monitoring-usage) |
320| `CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE` | Set to `1` to let Claude Code run your package manager's upgrade command in the background when a new version is available. Applies to Homebrew and WinGet installations. Other package managers continue to show the upgrade command without running it. See [Auto updates](/docs/en/setup#auto-updates) |
321| `CLAUDE_CODE_PERFORCE_MODE` | Set to `1` to enable Perforce-aware write protection. When set, Edit, Write, and NotebookEdit fail with a `p4 edit <file>` hint if the target file lacks the owner-write bit, which Perforce clears on synced files until `p4 edit` opens them. This prevents Claude Code from bypassing Perforce change tracking
321| `CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE` | Set to `1` to let Claude Code run your package manager's upgrade command in the background when a new version is available. Applies to Homebrew and WinGet installations. Other package managers continue to show the upgrade command without running it. See [Auto updates](/docs/en/setup#auto-updates)
features-overview Changed · +1 / -1 lines
from line 230
230230 </Tab>
231231
232232 <Tab title="Skills">
233 Skills are extra capabilities in Claude's toolkit. They can be reference material (like an API style guide) or invocable workflows you trigger with `/<name>` (like `/deploy`). Claude Code includes [bundled skills](/docs/en/commands) like `/code-review`, `/batch`, and `/debug` that work out of the box. You can also create your own.
233 Skills are extra capabilities in Claude's toolkit. They can be reference material (like an API style guide) or invocable workflows you trigger with `/<name>` (like `/deploy`). Claude Code includes [bundled skills](/docs/en/commands) like `/code-review`, `/batch`, and `/debug` that work without setup. You can also create your own.
234234
235235 **When:** Depends on the skill's configuration. By default, descriptions load at session start and full content loads when used. For user-only skills (`disable-model-invocation: true`), nothing loads until you invoke them.
236236