surshar / claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Built by Anthropic · github.com/anthropics
Large file, diff not shown.
| @@ -6,8 +6,36 @@ | ||
| 6 | 6 | <author><name>Anthropic</name></author> |
| 7 | 7 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/> |
| 8 | 8 | <link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/> |
| 9 | - <updated>2026-06-12T21:53:21Z</updated> | |
| 9 | + <updated>2026-06-15T21:35:48Z</updated> | |
| 10 | 10 | <entry> |
| 11 | + <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.178</id> | |
| 12 | + <title>Claude Code v2.1.178</title> | |
| 13 | + <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.178"/> | |
| 14 | + <updated>2026-06-15T21:35:48Z</updated> | |
| 15 | + <content type="html"><p>• Added Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents</p> | |
| 16 | +<p>• Skills in nested .claude/skills directories now load when working on files there; on a name clash, the nested skill appears as &lt;dir&gt;:&lt;name&gt; so both stay available</p> | |
| 17 | +<p>• Nested .claude/ directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing .claude/workflows/</p> | |
| 18 | +<p>• Improved auto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review</p> | |
| 19 | +<p>• Improved /doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names</p> | |
| 20 | +<p>• Improved the skill listing truncation warning to show how many skill descriptions are affected</p> | |
| 21 | +<p>• Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word</p> | |
| 22 | +<p>• Improved Remote Control error messages: connection failures now show a persistent red "/rc failed" indicator in the footer, and the "not yet enabled" error now explains whether it's a gate, a check failure, stale entitlement, or org policy</p> | |
| 23 | +<p>• /bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title</p> | |
| 24 | +<p>• Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process</p> | |
| 25 | +<p>• Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login</p> | |
| 26 | +<p>• Fixed nested .claude/skills skills with directory-qualified names being blocked by permission prompts in non-interactive runs</p> | |
| 27 | +<p>• Fixed several subagent issues: viewing a subagent's transcript now shows tool results and live progress, messages sent while it finishes its turn are no longer dropped, and backgrounding a running subagent (ctrl+b) no longer restarts it from scratch</p> | |
| 28 | +<p>• Fixed claude agents workers failing with 401 Invalid bearer token when the daemon was started from a shell with a custom API gateway via ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN</p> | |
| 29 | +<p>• Fixed compaction not honoring --fallback-model: compaction now falls back to the configured fallback model chain on overload or model-availability errors</p> | |
| 30 | +<p>• Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration</p> | |
| 31 | +<p>• Fixed background sessions created with /bg or ←← after a turn finished showing "Working" forever in the agents list</p> | |
| 32 | +<p>• Fixed CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning</p> | |
| 33 | +<p>• Fixed MCP server-level specs (mcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignored</p> | |
| 34 | +<p>• Fixed vim mode undo: u now steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo step</p> | |
| 35 | +<p>• Fixed statusline links with custom URI schemes (e.g. vscode://) not opening when clicked in claude agents</p> | |
| 36 | +<p>• [VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task</p></content> | |
| 37 | + </entry> | |
| 38 | + <entry> | |
| 11 | 39 | <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.176</id> |
| 12 | 40 | <title>Claude Code v2.1.176</title> |
| 13 | 41 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.176"/> |
| @@ -381,54 +409,4 @@ | ||
| 381 | 409 | <updated>2026-05-29T01:42:17Z</updated> |
| 382 | 410 | <content type="html"><p>• Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.</p></content> |
| 383 | 411 | </entry> |
| 384 | - <entry> | |
| 385 | - <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.154</id> | |
| 386 | - <title>Claude Code v2.1.154</title> | |
| 387 | - <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.154"/> | |
| 388 | - <updated>2026-05-28T18:00:47Z</updated> | |
| 389 | - <content type="html"><p>• Opus 4.8 is here! Now defaults to high effort · /effort xhigh for your hardest tasks</p> | |
| 390 | -<p>• Introducing dynamic workflows: ask Claude to create a workflow and it orchestrates work across tens to hundreds of agents in the background, so you can take on larger, more complex tasks. Run /workflows to view your runs</p> | |
| 391 | -<p>• Fast mode on Opus 4.8 is now available at a fraction of its previous cost: 2x the standard rate for 2.5x the speed</p> | |
| 392 | -<p>• The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlier</p> | |
| 393 | -<p>• Claude now reserves the multiple-choice question prompt for decisions it genuinely cannot make itself, instead of asking when it already has enough context to proceed</p> | |
| 394 | -<p>• /simplify now runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixes, instead of running the full /code-review --fix bug-hunting review</p> | |
| 395 | -<p>• Renamed the /effort slider labels from "Speed"/"Intelligence" to "Faster"/"Smarter" for clarity</p> | |
| 396 | -<p>• claude agents: type ! &lt;command&gt; to run a shell command as a background session you can attach to and detach from. Also available as claude --bg --exec '&lt;command&gt;'</p> | |
| 397 | -<p>• claude agents: /logout now signs you out instead of being sent to a background session</p> | |
| 398 | -<p>• ←← to open the agents view now works on Bedrock, Vertex, Foundry, and with telemetry disabled</p> | |
| 399 | -<p>• Claude in Chrome: pick which connected browser to use via /chrome → "Select browser…", or in-chat when a browser action runs with multiple connected</p> | |
| 400 | -<p>• Plugins can now declare defaultEnabled: false in plugin.json or a marketplace entry; enable them with /plugin or claude plugin enable. Dependencies of enabled plugins are still enabled automatically</p> | |
| 401 | -<p>• The /plugin Discover tab now pins plugins whose relevance signals match the current directory with a "suggested for this directory" annotation</p> | |
| 402 | -<p>• Streaming tool execution is now always enabled, including when telemetry is disabled or on Bedrock/Vertex/Foundry (previously behind a feature flag)</p> | |
| 403 | -<p>• Stdio MCP server subprocesses now receive CLAUDE_CODE_SESSION_ID and CLAUDECODE=1 in their environment</p> | |
| 404 | -<p>• claude mcp list/get now show unapproved .mcp.json servers as ⏸ Pending approval instead of auto-approving and connecting when output is piped</p> | |
| 405 | -<p>• /remote-control autocomplete now shows "Disconnect Remote Control" when Remote Control is already active</p> | |
| 406 | -<p>• Added Claude Opus 4.8 support and 4.7 → 4.8 migration guidance to the /claude-api skill</p> | |
| 407 | -<p>• Deprecated CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE (will be removed on 06/01). To use fast mode on Opus 4.6, switch with /model claude-opus-4-6[1m] and then /fast on</p> | |
| 408 | -<p>• Improved the auto-mode classifier's detection of data exfiltration, particularly bulk transfers of repository contents</p> | |
| 409 | -<p>• Fixed rm -rf $HOME not being blocked as a dangerous path when HOME has a trailing slash</p> | |
| 410 | -<p>• Fixed $TMPDIR resolving to different directories in sandboxed vs unsandboxed Bash commands within the same session</p> | |
| 411 | -<p>• Fixed unreadable highlighted-row text in claude agents when the Claude Code theme doesn't match the terminal background</p> | |
| 412 | -<p>• Fixed background-agent completion notifications triggering premature "out of context" behavior on some 1M-context models</p> | |
| 413 | -<p>• Fixed background-session classifier losing the user's goal when a scheduled /command fires</p> | |
| 414 | -<p>• Fixed pinned background sessions respawning every minute after a Claude Code update, causing repeated agent-start notifications and process churn at idle</p> | |
| 415 | -<p>• Fixed background sessions stuck at "blocked", "running", or "working" not retiring after the idle grace period</p> | |
| 416 | -<p>• Fixed subagents in background sessions bypassing the worktree-isolation guard and writing to the shared checkout</p> | |
| 417 | -<p>• Fixed orphaned claude --bg-pty-host processes spinning at 100% CPU after the daemon exits on macOS</p> | |
| 418 | -<p>• Fixed number key shortcuts not working for options shown below the divider in option dialogs</p> | |
| 419 | -<p>• Fixed worktree.baseRef: "head" resolving to the main checkout's HEAD instead of the current worktree's HEAD when spawning subagents or calling EnterWorktree from inside a linked worktree</p> | |
| 420 | -<p>• Fixed a stray leading space on wrapped lines when the previous line ended exactly at the terminal width</p> | |
| 421 | -<p>• Fixed intermittent terminal rendering corruption in VS Code by capping the number of distinct colors the thinking spinner produces</p> | |
| 422 | -<p>• Fixed plan file names including [Image #N] / [Pasted text #N] placeholders when a plan-mode prompt starts with pasted images or text</p> | |
| 423 | -<p>• Fixed a phantom expand/click affordance on colored tool output: short ANSI-colored lines that fit on screen no longer show a "ctrl+o to expand" hint</p> | |
| 424 | -<p>• Fixed a single invalid allowedMcpServers/deniedMcpServers entry in managed settings discarding all managed-settings policy; the bad entry is now dropped with a claude doctor warning</p> | |
| 425 | -<p>• Fixed API 400 errors on models that don't support the effort parameter when CLAUDE_CODE_ALWAYS_ENABLE_EFFORT is set</p> | |
| 426 | -<p>• Windows: Fixed update failures caused by claude.exe being in use showing a generic error instead of telling you to close other sessions and retry</p> | |
| 427 | -<p>• Removed the stale "&amp; for background" hint from the shortcuts help panel</p> | |
| 428 | -<p>• [VSCode] Auto mode no longer requires the bypass-permissions setting to appear in the mode picker, and a dismissable notice on the new-session screen explains auto mode the first time it's active</p> | |
| 429 | -<p>• Fixed the task panel below the prompt showing a stray unselectable "main" row when only a workflow is running</p> | |
| 430 | -<p>• Fixed /mcp tools list and tool detail rendering when MCP servers have long or multi-line tool names or long descriptions</p> | |
| 431 | -<p>• Fixed the /model picker not showing fast mode pricing on the Default option for API (pay-as-you-go) users when fast mode is on</p> | |
| 432 | -<p>• Fixed auto mode incorrectly blocking actions with "could not evaluate this action" when the safety classifier ran out of output tokens while reasoning</p></content> | |
| 433 | - </entry> | |
| 434 | 412 | </feed> |